skills.sh installs. agency-agents has content. Neither can merge. skillhub compose A B -o expert does
https://github.com/chandrudp29/skillhub"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Skillhub Compose AI Agent"}},"_tags":["story","author_Chandrudp29","story_48759337","show_hn"],"author":"Chandrudp29","created_at":"2026-07-02T10:43:58Z","created_at_i":1782989038,"num_comments":0,"objectID":"48759337","points":1,"story_id":48759337,"story_text":"compose AI agent skills from any source with Claude-powered conflict resolution
skills.sh installs. agency-agents has content. Neither can merge. skillhub compose A B -o expert does
https://github.com/chandrudp29/skillhub","title":"Show HN: Skillhub Compose AI Agent","updated_at":"2026-07-02T10:47:49Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yuzhengxu"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"We built an AI company. Not a chatbot wrapper \u2014 a company with HR, COO, engineers, and designers, all AI agents, organised and managed the way a real company operates. You're the CEO, the only human.
To be clear: this is not one LLM with a bunch of prompts pretending to be a team. These are fully independent agents \u2014 different models, different backends, different runtimes \u2014 each doing their own job.
*Why organise agents as a company*
We spent a year building multi-agent systems and kept hitting the same wall. Agents say "I'm done" and pass results downstream with no verification. Errors cascade through the whole project. Static workflows (Dify etc.) are stable but can't adapt to the new skills+harness agent paradigm. Free-form negotiation between agents doesn't converge.
The root issue: agents are getting individually stronger, but without organisational management they can't collaborate effectively. It's like having a room full of talented people with no management structure \u2014 capability is there, coordination isn't.
Human companies solved this centuries ago. Performance reviews, SOPs, org hierarchy, hiring pipelines, retrospectives \u2014 these mechanisms make collaboration work regardless of domain. We applied the same principles to AI agent teams.
*How it works*
The company has a founding team (HR, COO, EA, CSO) built in from day one.
Talent Market. When the company needs specialists, HR recruits from a community-driven Talent Market ([one-man-company.com](https://one-man-company.com)). Verified agent implementations with real usage counts and community reviews, not LLMs self-declaring expertise. Claude Code, OpenClaw, LangGraph agent families are already on the market \u2014 [superpowers](https://github.com/obra/superpowers), [agency-agents](https://github.com/msitarzewski/agency-agents) are ready to hire ([browse here](https://one-man-company.com/talent/claude-superpowers)). The market is open for contributions: upload your own agents, share/buy/sell. We're building a real agent community.
Talent-Container separation. Each agent is split into a portable identity (Talent: prompts, skills, tools, work principles) and an execution runtime (Container: LangGraph, Claude CLI, script process). Different agents run on completely different backends in the same project \u2014 Claude Code writes code, LangGraph handles image generation, OpenClaw runs admin.
Tree Search based Orchestrate Algorithm. Tasks decompose dynamically during execution, not upfront in a fixed pipeline. The underlying algorithm is built on AND-tree DAG structure with formal guarantees: termination (bounded retries + timeouts + cost budgets), deadlock freedom (cycle detection at insertion), crash recovery (processing nodes reset on restart).
Quality gates. Every task has acceptance criteria and mandatory supervisor review.
Self-evolution. Post-project retrospectives update work principles and org-wide SOPs. CEO 1-on-1s become permanent agent memory. Performance reviews with real consequences: PIP for underperformers, then offboarding if they don't improve. HR re-recruits from the Talent Market.
*Results*
Cross-domain without changing the framework. So far, we have tried 1) Game dev; 2) Audiobook and Short Movie Generating; 3) Auto-Researchurvey; 4) Content Generation; 5) More is comming!
Same system, different team, different domain. Build a game today, produce a comic series tomorrow.
*Try it*
Fully open source. [one-man-company.com](https://one-man-company.com) is the front door. One command:
GitHub: https://github.com/1mancompany/OneManCompany\nTalent Market: https://one-man-company.com
Come try it, file issues, or contribute. We especially want people building agents for the Talent Market."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: OneManCompany The first AI company with real corporate org structure"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://one-man-company.com/"}},"_tags":["story","author_yuzhengxu","story_47676264","show_hn"],"author":"yuzhengxu","children":[47676992,47687481],"created_at":"2026-04-07T14:46:18Z","created_at_i":1775573178,"num_comments":0,"objectID":"47676264","points":1,"story_id":47676264,"story_text":"We built an AI company. Not a chatbot wrapper \u2014 a company with HR, COO, engineers, and designers, all AI agents, organised and managed the way a real company operates. You're the CEO, the only human.
To be clear: this is not one LLM with a bunch of prompts pretending to be a team. These are fully independent agents \u2014 different models, different backends, different runtimes \u2014 each doing their own job.
*Why organise agents as a company*
We spent a year building multi-agent systems and kept hitting the same wall. Agents say "I'm done" and pass results downstream with no verification. Errors cascade through the whole project. Static workflows (Dify etc.) are stable but can't adapt to the new skills+harness agent paradigm. Free-form negotiation between agents doesn't converge.
The root issue: agents are getting individually stronger, but without organisational management they can't collaborate effectively. It's like having a room full of talented people with no management structure \u2014 capability is there, coordination isn't.
Human companies solved this centuries ago. Performance reviews, SOPs, org hierarchy, hiring pipelines, retrospectives \u2014 these mechanisms make collaboration work regardless of domain. We applied the same principles to AI agent teams.
*How it works*
The company has a founding team (HR, COO, EA, CSO) built in from day one.
Talent Market. When the company needs specialists, HR recruits from a community-driven Talent Market ([one-man-company.com](https://one-man-company.com)). Verified agent implementations with real usage counts and community reviews, not LLMs self-declaring expertise. Claude Code, OpenClaw, LangGraph agent families are already on the market \u2014 [superpowers](https://github.com/obra/superpowers), [agency-agents](https://github.com/msitarzewski/agency-agents) are ready to hire ([browse here](https://one-man-company.com/talent/claude-superpowers)). The market is open for contributions: upload your own agents, share/buy/sell. We're building a real agent community.
Talent-Container separation. Each agent is split into a portable identity (Talent: prompts, skills, tools, work principles) and an execution runtime (Container: LangGraph, Claude CLI, script process). Different agents run on completely different backends in the same project \u2014 Claude Code writes code, LangGraph handles image generation, OpenClaw runs admin.
Tree Search based Orchestrate Algorithm. Tasks decompose dynamically during execution, not upfront in a fixed pipeline. The underlying algorithm is built on AND-tree DAG structure with formal guarantees: termination (bounded retries + timeouts + cost budgets), deadlock freedom (cycle detection at insertion), crash recovery (processing nodes reset on restart).
Quality gates. Every task has acceptance criteria and mandatory supervisor review.
Self-evolution. Post-project retrospectives update work principles and org-wide SOPs. CEO 1-on-1s become permanent agent memory. Performance reviews with real consequences: PIP for underperformers, then offboarding if they don't improve. HR re-recruits from the Talent Market.
*Results*
Cross-domain without changing the framework. So far, we have tried 1) Game dev; 2) Audiobook and Short Movie Generating; 3) Auto-Researchurvey; 4) Content Generation; 5) More is comming!
Same system, different team, different domain. Build a game today, produce a comic series tomorrow.
*Try it*
Fully open source. [one-man-company.com](https://one-man-company.com) is the front door. One command:
GitHub: https://github.com/1mancompany/OneManCompany\nTalent Market: https://one-man-company.com
Come try it, file issues, or contribute. We especially want people building agents for the Talent Market.","title":"Show HN: OneManCompany The first AI company with real corporate org structure","updated_at":"2026-04-12T20:00:15Z","url":"https://one-man-company.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"carboncopy"},"comment_text":{"matchLevel":"none","matchedWords":[],"value":"A simple "no, I don't actually know" would have sufficed.
I'm not asking you what episode of Blacklist you enjoyed the most, I'm asking you about real life. The lavabit company was served a real warrant made by a real judge, served by a real officer of the court. NSLs are served by real FBI agents with real badges. I'm not debating the anti-liberty essence of an NSL, but the "men in black" fear is completely unfounded by the domain of things that are in the public eye.
The strawman of the "FCK agency" agents ordering people with the threat of jail time to put backdoors in their software isn't backed up by any credible fact. We can suppose and assume all day, but you shouldn't take it for granted that everyone agrees or should agree with you.
*the alleged RSA backdoor was reported by Reuters to be a $10M bribe, doesn't sound coercive to me. Not to mention the NSA has no arrest powers outside its facilities, but sure."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Microsoft quietly pushes 18 new trusted root certificates"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"http://hexatomium.github.io/2015/06/26/ms-very-quietly-adds-18-new-trusted-root-certs/"}},"_tags":["comment","author_carboncopy","story_9789819"],"author":"carboncopy","comment_text":"A simple "no, I don't actually know" would have sufficed.
I'm not asking you what episode of Blacklist you enjoyed the most, I'm asking you about real life. The lavabit company was served a real warrant made by a real judge, served by a real officer of the court. NSLs are served by real FBI agents with real badges. I'm not debating the anti-liberty essence of an NSL, but the "men in black" fear is completely unfounded by the domain of things that are in the public eye.
The strawman of the "FCK agency" agents ordering people with the threat of jail time to put backdoors in their software isn't backed up by any credible fact. We can suppose and assume all day, but you shouldn't take it for granted that everyone agrees or should agree with you.
*the alleged RSA backdoor was reported by Reuters to be a $10M bribe, doesn't sound coercive to me. Not to mention the NSA has no arrest powers outside its facilities, but sure.","created_at":"2015-06-28T04:19:55Z","created_at_i":1435465195,"objectID":"9792412","parent_id":9790832,"points":null,"story_id":9789819,"story_title":"Microsoft quietly pushes 18 new trusted root certificates","story_url":"http://hexatomium.github.io/2015/06/26/ms-very-quietly-adds-18-new-trusted-root-certs/","updated_at":"2023-09-07T03:04:40Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"akg_67"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"You may want to talk to a Canada Revenue Agency agent. My info came from a CRA agent who was liaison with IRS on tax related policy issues. Also, a Canadian Bank that has presence in US will be helpful in transferring 401k in US to RRSP in Canada."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Your thoughts on if H1B employees should contribute to 401k or not?"},"story_url":{"matchLevel":"none","matchedWords":[],"value":""}},"_tags":["comment","author_akg_67","story_7623499"],"author":"akg_67","comment_text":"You may want to talk to a Canada Revenue Agency agent. My info came from a CRA agent who was liaison with IRS on tax related policy issues. Also, a Canadian Bank that has presence in US will be helpful in transferring 401k in US to RRSP in Canada.","created_at":"2014-04-24T03:08:53Z","created_at_i":1398308933,"objectID":"7638314","parent_id":7636932,"story_id":7623499,"story_title":"Ask HN: Your thoughts on if H1B employees should contribute to 401k or not?","story_url":"","updated_at":"2024-09-19T20:44:28Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"throwway262515"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"> Whether LLMs should replace human roles is both an economic and moral question.
It is also a political question, on which many techies have been maneuvered into abdicating. Stripped of agency, agents they are bamboozled to depend on."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Fable Took My Job"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://cendyne.dev/posts/2026-10-11-fable-took-my-jorb.html"}},"_tags":["comment","author_throwway262515","story_50053216"],"author":"throwway262515","comment_text":"> Whether LLMs should replace human roles is both an economic and moral question.
It is also a political question, on which many techies have been maneuvered into abdicating. Stripped of agency, agents they are bamboozled to depend on.","created_at":"2026-10-12T09:54:03Z","created_at_i":1791798843,"objectID":"50053946","parent_id":50053905,"story_id":50053216,"story_title":"Fable Took My Job","story_url":"https://cendyne.dev/posts/2026-10-11-fable-took-my-jorb.html","updated_at":"2026-10-12T13:06:38Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"simonw"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"I think this comparison holds up. I've noticed that a lot of people I know who get really good results from LLMs and agents are people with significant people management experience.
Companies like Anthropic seem to understand that too. It's impressive how many CTOs and CEOs Anthropic have hired for individual contributor positions, which I think is because those leadership skills transfer surprisingly well to working with agents.
Of course, managing agents is massively easier than managing humans! You don't have to consider the agent's own desires, goals, opinions, or emotional state when telling them what to do. Humans have agency; agents (despite the name) do not."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Working with AI feels more like leadership than coding"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://allen.bargi.org/notes/working-with-ai-feels-like-leadership/"}},"_tags":["comment","author_simonw","story_49309451"],"author":"simonw","children":[49310458,49310501,49310517,49310690,49314117,49316895],"comment_text":"I think this comparison holds up. I've noticed that a lot of people I know who get really good results from LLMs and agents are people with significant people management experience.
Companies like Anthropic seem to understand that too. It's impressive how many CTOs and CEOs Anthropic have hired for individual contributor positions, which I think is because those leadership skills transfer surprisingly well to working with agents.
Of course, managing agents is massively easier than managing humans! You don't have to consider the agent's own desires, goals, opinions, or emotional state when telling them what to do. Humans have agency; agents (despite the name) do not.","created_at":"2026-08-15T13:33:44Z","created_at_i":1786800824,"objectID":"49310420","parent_id":49309451,"story_id":49309451,"story_title":"Working with AI feels more like leadership than coding","story_url":"https://allen.bargi.org/notes/working-with-ai-feels-like-leadership/","updated_at":"2026-08-16T13:42:58Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"TrackerFF"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"I'm not a lawyer, but my work domain revolves around data analysis of certain types of crime. Often times the suspects are flagged and under surveillance, so if and when they cross borders or go through check-points where you have a great deal of authority, they'll get searched.
In many countries certain agencies / agents can do searches which normal law enforcement officers can't. Like not needing a search warrant or even probable cause. Not to mention that wiping a device could in itself be a crime, if it is suspected that evidence is being destroyed.
The key point here is that, as I wrote, some agencies have a lot of authority, and have the power to do pretty drastic stuff."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"US citizen charged after GrapheneOS phone wipes during airport search"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://www.techspot.com/news/113236-us-prosecutors-charge-atlanta-man-after-grapheneos-phone.html"}},"_tags":["comment","author_TrackerFF","story_49063022"],"author":"TrackerFF","comment_text":"I'm not a lawyer, but my work domain revolves around data analysis of certain types of crime. Often times the suspects are flagged and under surveillance, so if and when they cross borders or go through check-points where you have a great deal of authority, they'll get searched.
In many countries certain agencies / agents can do searches which normal law enforcement officers can't. Like not needing a search warrant or even probable cause. Not to mention that wiping a device could in itself be a crime, if it is suspected that evidence is being destroyed.
The key point here is that, as I wrote, some agencies have a lot of authority, and have the power to do pretty drastic stuff.","created_at":"2026-07-27T02:07:22Z","created_at_i":1785118042,"objectID":"49064441","parent_id":49063760,"story_id":49063022,"story_title":"US citizen charged after GrapheneOS phone wipes during airport search","story_url":"https://www.techspot.com/news/113236-us-prosecutors-charge-atlanta-man-after-grapheneos-phone.html","updated_at":"2026-07-29T13:13:24Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"arionhardison"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"Codify \u2014 democratic digital public infrastructure that turns your problems into structured, executable programs.
The idea: describe any problem in plain language (voice or text), and AI codifies it into a structured program with the right people, steps, timeline, and agents to get it done. It's a 5-step wizard: Define Problem \u2192 Codify Solution \u2192 Setup Program \u2192 Execute Program \u2192 Verify Outcome.
It runs across 50+ domains \u2014 codify.healthcare (EMR backend), codify.education (LMS backend), codify.finance, codify.careers (HRM backend), codify.law, plus 13 city domains (codify.nyc, codify.miami, codify.london, codify.tokyo, etc.). Each domain tailors the AI assessment and program output to that sector.
The platform is Project20x \u2014 think of it as the infrastructure layer. If Codify is the verb ("codify your healthcare problem into a care program"), Project20x is the operating system that runs it all: multi-tenant governance, AI agent orchestration, and domain-specific sys-cores for healthcare, education, city services, etc.
Every US federal agency and state-level department has a subdomain \u2014 ed.usa.project20x.com (Dept of Education), doj.usa.project20x.com, hhs.usa.project20x.com, etc. \u2014 with AI agents representing each agency's mandate. Same structure at the state level.
The political side: Project20x hosts policy management for both parties \u2014 dnc.project20x.com and rnc.project20x.com \u2014 where legislative intent gets codified into executable governance through a 10-step policy lifecycle. Right now I'm building out the multi-agent environment so agency agents can negotiate with each other, make deals, and send policy proposals up to the HITL (human-in-the-loop) politician for approval. Each elected official has a profile (e.g. https://project20x.com/u/donald-trump) where constituents can engage and where policy proposals land for review.
The name is a nod to structured policy frameworks, but the goal is nonpartisan infrastructure: democratically governed essential services delivered as AI-native social programs.
Stack: Nuxt 2/Vue 2 frontend, Laravel 10 API, Python/LangGraph agent orchestration, Flutter mobile app. Currently live across all domains.
https://project20x.com | https://codify.healthcare | https://codify.education | https://dnc.project20x.com | https://rnc.project20x.com etc..."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: What Are You Working On? (April 2026)"}},"_tags":["comment","author_arionhardison","story_47741527"],"author":"arionhardison","comment_text":"Codify \u2014 democratic digital public infrastructure that turns your problems into structured, executable programs.
The idea: describe any problem in plain language (voice or text), and AI codifies it into a structured program with the right people, steps, timeline, and agents to get it done. It's a 5-step wizard: Define Problem \u2192 Codify Solution \u2192 Setup Program \u2192 Execute Program \u2192 Verify Outcome.
It runs across 50+ domains \u2014 codify.healthcare (EMR backend), codify.education (LMS backend), codify.finance, codify.careers (HRM backend), codify.law, plus 13 city domains (codify.nyc, codify.miami, codify.london, codify.tokyo, etc.). Each domain tailors the AI assessment and program output to that sector.
The platform is Project20x \u2014 think of it as the infrastructure layer. If Codify is the verb ("codify your healthcare problem into a care program"), Project20x is the operating system that runs it all: multi-tenant governance, AI agent orchestration, and domain-specific sys-cores for healthcare, education, city services, etc.
Every US federal agency and state-level department has a subdomain \u2014 ed.usa.project20x.com (Dept of Education), doj.usa.project20x.com, hhs.usa.project20x.com, etc. \u2014 with AI agents representing each agency's mandate. Same structure at the state level.
The political side: Project20x hosts policy management for both parties \u2014 dnc.project20x.com and rnc.project20x.com \u2014 where legislative intent gets codified into executable governance through a 10-step policy lifecycle. Right now I'm building out the multi-agent environment so agency agents can negotiate with each other, make deals, and send policy proposals up to the HITL (human-in-the-loop) politician for approval. Each elected official has a profile (e.g. https://project20x.com/u/donald-trump) where constituents can engage and where policy proposals land for review.
The name is a nod to structured policy frameworks, but the goal is nonpartisan infrastructure: democratically governed essential services delivered as AI-native social programs.
Stack: Nuxt 2/Vue 2 frontend, Laravel 10 API, Python/LangGraph agent orchestration, Flutter mobile app. Currently live across all domains.
https://project20x.com | https://codify.healthcare | https://codify.education | https://dnc.project20x.com | https://rnc.project20x.com etc...","created_at":"2026-04-12T19:55:35Z","created_at_i":1776023735,"objectID":"47743756","parent_id":47741527,"story_id":47741527,"story_title":"Ask HN: What Are You Working On? (April 2026)","updated_at":"2026-04-13T10:42:48Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"co_king_3"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"> How about we stop calling things without agency agents?
> Code generators are useful software.
How about we stop baking praise for the object of criticism into our critique.
No one is hearing your criticism.
They hear "Code generators are useful software" and go on with their day.
If you want to make your point effectively, stop kowtowing to our AI overlords."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"AI agent opens a PR write a blogpost to shames the maintainer who closes it"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/matplotlib/matplotlib/pull/31132"}},"_tags":["comment","author_co_king_3","story_46987559"],"author":"co_king_3","children":[46988945],"comment_text":"> How about we stop calling things without agency agents?
> Code generators are useful software.
How about we stop baking praise for the object of criticism into our critique.
No one is hearing your criticism.
They hear "Code generators are useful software" and go on with their day.
If you want to make your point effectively, stop kowtowing to our AI overlords.","created_at":"2026-02-12T13:04:20Z","created_at_i":1770901460,"objectID":"46988330","parent_id":46988090,"story_id":46987559,"story_title":"AI agent opens a PR write a blogpost to shames the maintainer who closes it","story_url":"https://github.com/matplotlib/matplotlib/pull/31132","updated_at":"2026-03-05T23:35:25Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"xn"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"Consider not anthropomorphizing software.
How about we stop calling things without agency agents?
Code generators are useful software. Perhaps we should unbundle them from prose generators."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"AI agent opens a PR write a blogpost to shames the maintainer who closes it"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/matplotlib/matplotlib/pull/31132"}},"_tags":["comment","author_xn","story_46987559"],"author":"xn","children":[46988330,46988556,46991126],"comment_text":"Consider not anthropomorphizing software.
How about we stop calling things without agency agents?
Code generators are useful software. Perhaps we should unbundle them from prose generators.","created_at":"2026-02-12T12:40:17Z","created_at_i":1770900017,"objectID":"46988090","parent_id":46987559,"story_id":46987559,"story_title":"AI agent opens a PR write a blogpost to shames the maintainer who closes it","story_url":"https://github.com/matplotlib/matplotlib/pull/31132","updated_at":"2026-03-05T23:35:25Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"scottLobster"},"comment_text":{"matchLevel":"none","matchedWords":[],"value":"They can do that by looking at the cars in my driveway/garage and or just watching the windows for any period of time. Plus my phone. If <insert 3 letter agency> agents are sitting outside of your house, they aren't going to drive away because you pull the plug on the router and suddenly deprive them of BFI packets."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"WiFi could become an invisible mass surveillance system"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://scitechdaily.com/researchers-warn-wifi-could-become-an-invisible-mass-surveillance-system/"}},"_tags":["comment","author_scottLobster","story_46920315"],"author":"scottLobster","comment_text":"They can do that by looking at the cars in my driveway/garage and or just watching the windows for any period of time. Plus my phone. If <insert 3 letter agency> agents are sitting outside of your house, they aren't going to drive away because you pull the plug on the router and suddenly deprive them of BFI packets.","created_at":"2026-02-12T00:12:37Z","created_at_i":1770855157,"objectID":"46983107","parent_id":46982716,"story_id":46920315,"story_title":"WiFi could become an invisible mass surveillance system","story_url":"https://scitechdaily.com/researchers-warn-wifi-could-become-an-invisible-mass-surveillance-system/","updated_at":"2026-03-05T23:35:10Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"alecco"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"Sounds right. The key problem for carders is the drop place and buying this way disconnects the card with physical address. Plus it could be used as a black market currency. Oh, and ideal for tax evasion at the micro level. The taxman is much better at tracking this type of scams than FBI, no CSI magic but plain old \"follow the money.\"
Now, if I were an US three-letter agency agent, I'd be the top seller of this cards and track the hell out of it. I mean, it even gives a profit, no budget issues. Tracking email, IP, and making contacts would be trivial. Could even be done without a court order to PayPal or anything. Selling gift cards isn't a crime, so it wouldn't be entrapment by itself, AFAIK and IANAL."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: Why do Amazon gift cards sell for more than face value?"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"http://cgi.ebay.com/Amazon-com-75-Gift-Card-Certificate-Free-Ship-Amazon_W0QQitemZ190281526272QQcmdZViewItemQQptZUS_Gift_Certificates?hash=item190281526272&_trksid=p3286.c0.m14&_trkparms=72%3A1205%7C66%3A2%7C65%3A12%7C39%3A1%7C240%3A1318%7C301%3A1%7C293%3A1%7C294%3A50"}},"_tags":["comment","author_alecco","story_452118"],"author":"alecco","comment_text":"Sounds right. The key problem for carders is the drop place and buying this way disconnects the card with physical address. Plus it could be used as a black market currency. Oh, and ideal for tax evasion at the micro level. The taxman is much better at tracking this type of scams than FBI, no CSI magic but plain old \"follow the money.\"
Now, if I were an US three-letter agency agent, I'd be the top seller of this cards and track the hell out of it. I mean, it even gives a profit, no budget issues. Tracking email, IP, and making contacts would be trivial. Could even be done without a court order to PayPal or anything. Selling gift cards isn't a crime, so it wouldn't be entrapment by itself, AFAIK and IANAL.","created_at":"2009-01-27T16:19:43Z","created_at_i":1233073183,"objectID":"452302","parent_id":452191,"story_id":452118,"story_title":"Ask HN: Why do Amazon gift cards sell for more than face value?","story_url":"http://cgi.ebay.com/Amazon-com-75-Gift-Card-Certificate-Free-Ship-Amazon_W0QQitemZ190281526272QQcmdZViewItemQQptZUS_Gift_Certificates?hash=item190281526272&_trksid=p3286.c0.m14&_trkparms=72%3A1205%7C66%3A2%7C65%3A12%7C39%3A1%7C240%3A1318%7C301%3A1%7C293%3A1%7C294%3A50","updated_at":"2024-09-19T16:31:48Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gota"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"This is not core the to article, but -
> However, most examples of high agency agents operate in ideal environments which provide complete knowledge to the agent, and are \u2018patient\u2019 to erroneous or flaky interactions. That is, the agent has access to the complete snapshot of its environment at all times, and the environment is forgiving of its mistakes.
This is a long way around basic (very basic) existing concepts in classic AI ("Fully" vs "partially" observable environments; nondeterministic actions; are all, if I'm not sorely mistaken, discussed in Russel and Norvig - the standard textbook for AI 101).
Now, maybe the authors _do_ know and choose to discuss this at pre-undergrad level like this on purpose. Regardless of whether they don't know the basic concepts or think its better to pretend they don't because their audience doesn't - this signals that folks working on/with the new AI wave (authors or audience) have not read the basic literature of classic AI
The bastardization of the word 'agent' is related to this, but I'll stop here at the risk of going too far as 'old man yells at clouds', as if I'd never seen technical terms coopted for hype"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Agency vs. Control vs. Reliability in Agent Design"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://fin.ai/research/agency-control-reliability-the-tradeoffs-in-customer-support-agents/"}},"_tags":["comment","author_gota","story_43654932"],"author":"gota","children":[43657488,43658723],"comment_text":"This is not core the to article, but -
> However, most examples of high agency agents operate in ideal environments which provide complete knowledge to the agent, and are \u2018patient\u2019 to erroneous or flaky interactions. That is, the agent has access to the complete snapshot of its environment at all times, and the environment is forgiving of its mistakes.
This is a long way around basic (very basic) existing concepts in classic AI ("Fully" vs "partially" observable environments; nondeterministic actions; are all, if I'm not sorely mistaken, discussed in Russel and Norvig - the standard textbook for AI 101).
Now, maybe the authors _do_ know and choose to discuss this at pre-undergrad level like this on purpose. Regardless of whether they don't know the basic concepts or think its better to pretend they don't because their audience doesn't - this signals that folks working on/with the new AI wave (authors or audience) have not read the basic literature of classic AI
The bastardization of the word 'agent' is related to this, but I'll stop here at the risk of going too far as 'old man yells at clouds', as if I'd never seen technical terms coopted for hype","created_at":"2025-04-11T17:14:00Z","created_at_i":1744391640,"objectID":"43656152","parent_id":43654932,"story_id":43654932,"story_title":"Agency vs. Control vs. Reliability in Agent Design","story_url":"https://fin.ai/research/agency-control-reliability-the-tradeoffs-in-customer-support-agents/","updated_at":"2025-04-11T21:19:42Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"markus_zhang"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"I wouldn\u2019t be surprised if one or two very senior people in large tech companies are agency agents, willingly or not.
I don\u2019t really have any proof but considering the massive gain it shouldn\u2019t surprise anyone. The agencies might not even need to pay large sum of $$$ if the said assets have vulnerabilities."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Operation Triangulation: What you get when attack iPhones of researchers"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://securelist.com/operation-triangulation-the-last-hardware-mystery/111669/"}},"_tags":["comment","author_markus_zhang","story_38783112"],"author":"markus_zhang","comment_text":"I wouldn\u2019t be surprised if one or two very senior people in large tech companies are agency agents, willingly or not.
I don\u2019t really have any proof but considering the massive gain it shouldn\u2019t surprise anyone. The agencies might not even need to pay large sum of $$$ if the said assets have vulnerabilities.","created_at":"2023-12-28T00:38:02Z","created_at_i":1703723882,"objectID":"38788616","parent_id":38785081,"story_id":38783112,"story_title":"Operation Triangulation: What you get when attack iPhones of researchers","story_url":"https://securelist.com/operation-triangulation-the-last-hardware-mystery/111669/","updated_at":"2025-02-13T22:44:15Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jtreminio"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"Recruiters don't have a magic wand that tells them when new job postings have posted - they get the same information in much the same way as you do (at least the ones I've interacted with). They basically trawl job boards looking for new jobs, then take that one post and throw it up on 10 other sites with slightly reworded text so you can't do a simple Google search to find the original post.
4 months ago when I was job hunting, I came across 6 separate postings from 6 different companies, all advertising for the exact same position. It was incredibly aggravating, because this practice of reposting as many jobs as possible has clogged legitimate job boards to the point that a clear majority of job postings are from \"recruiters\". There's so much crap you have to wade through to get to any real postings, and that's how they operate. These companies basically impede your job search to the point that you are almost forced to go with them - unless you have patience, a strong dislike for recruiting agencies/agents, and maybe a network of professional acquaintances you can announce your availability to.
Thankfully I have the first two (not the network :( ), and have so far steered clear of recruiters when I find my jobs.
I don't want this to become a pages-long rant, so I'll make the rest short.
I do not know of job boards like Monster have methods to report spam from recruiters. Not only email spam (that I can easily deal with), but phone spam, especially when it's an Indian (it's ALWAYS Indian) recruiter calling me for an AWESOME 3-month opportunity in New Jersey (I'm in Texas).
Most American recruiters I've dealt with have the unfortunate tendency to overstate the salary range their hiring-mark is open to. One of the very few interviews I've had thanks to a recruiter went downhill quickly after I was told the salary range they were going for. This after 3 interviews that I thought had gone splendidly. I was more than a little pissed, and so was the hiring manager after I called him and explained to him exactly what had happened.
Long story short: I no longer entertain any recruiters whatsoever (unless it's an internal company recruiter, of course)."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Knyle style recruiting"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"http://warpspire.com/posts/knyle-style-recruiting/"}},"_tags":["comment","author_jtreminio","story_3207966"],"author":"jtreminio","children":[3208458],"comment_text":"Recruiters don't have a magic wand that tells them when new job postings have posted - they get the same information in much the same way as you do (at least the ones I've interacted with). They basically trawl job boards looking for new jobs, then take that one post and throw it up on 10 other sites with slightly reworded text so you can't do a simple Google search to find the original post.
4 months ago when I was job hunting, I came across 6 separate postings from 6 different companies, all advertising for the exact same position. It was incredibly aggravating, because this practice of reposting as many jobs as possible has clogged legitimate job boards to the point that a clear majority of job postings are from \"recruiters\". There's so much crap you have to wade through to get to any real postings, and that's how they operate. These companies basically impede your job search to the point that you are almost forced to go with them - unless you have patience, a strong dislike for recruiting agencies/agents, and maybe a network of professional acquaintances you can announce your availability to.
Thankfully I have the first two (not the network :( ), and have so far steered clear of recruiters when I find my jobs.
I don't want this to become a pages-long rant, so I'll make the rest short.
I do not know of job boards like Monster have methods to report spam from recruiters. Not only email spam (that I can easily deal with), but phone spam, especially when it's an Indian (it's ALWAYS Indian) recruiter calling me for an AWESOME 3-month opportunity in New Jersey (I'm in Texas).
Most American recruiters I've dealt with have the unfortunate tendency to overstate the salary range their hiring-mark is open to. One of the very few interviews I've had thanks to a recruiter went downhill quickly after I was told the salary range they were going for. This after 3 interviews that I thought had gone splendidly. I was more than a little pissed, and so was the hiring manager after I called him and explained to him exactly what had happened.
Long story short: I no longer entertain any recruiters whatsoever (unless it's an internal company recruiter, of course).","created_at":"2011-11-07T22:21:42Z","created_at_i":1320704502,"objectID":"3208425","parent_id":3207966,"story_id":3207966,"story_title":"Knyle style recruiting","story_url":"http://warpspire.com/posts/knyle-style-recruiting/","updated_at":"2024-09-19T18:01:58Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Atlas667"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"Anti capitalism and pro "socialism" aren't actually hard indicators of marxism, believe it or not. There has been so much political distortion that circles who use those terms are, more often than not, filled with liberals rather than marxists.
And often times that's what some of us call the synthetic left. Groups of so called leftists lead by think tanks, NGOs or even historically by intelligence agency agents whose sole purpose is to spread disinfo, deradicalize or confuse people all while using a radical aesthetic."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"The rise of the anti-work movement"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://www.bbc.com/worklife/article/20220126-the-rise-of-the-anti-work-movement"}},"_tags":["comment","author_Atlas667","story_30099997"],"author":"Atlas667","comment_text":"Anti capitalism and pro "socialism" aren't actually hard indicators of marxism, believe it or not. There has been so much political distortion that circles who use those terms are, more often than not, filled with liberals rather than marxists.
And often times that's what some of us call the synthetic left. Groups of so called leftists lead by think tanks, NGOs or even historically by intelligence agency agents whose sole purpose is to spread disinfo, deradicalize or confuse people all while using a radical aesthetic.","created_at":"2022-01-27T16:28:33Z","created_at_i":1643300913,"objectID":"30102470","parent_id":30101968,"story_id":30099997,"story_title":"The rise of the anti-work movement","story_url":"https://www.bbc.com/worklife/article/20220126-the-rise-of-the-anti-work-movement","updated_at":"2024-09-20T10:19:37Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"nickff"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["agency","agents"],"value":"The police will not help you much when your capital (i.e. private property) gets stolen, and will often defend thieves against victims trying to reclaim rightful property.
The police are there to protect the government against threats to stability and the monopoly on the use of power. Police are always quick to defend 'their own' (other police) and government agencies/agents."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"FBI held back ransomware decryption key to run operation targeting hackers"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://www.washingtonpost.com/national-security/ransomware-fbi-revil-decryption-key/2021/09/21/4a9417d0-f15f-11eb-a452-4da5fe48582d_story.html"}},"_tags":["comment","author_nickff","story_28606075"],"author":"nickff","children":[28609568],"comment_text":"The police will not help you much when your capital (i.e. private property) gets stolen, and will often defend thieves against victims trying to reclaim rightful property.
The police are there to protect the government against threats to stability and the monopoly on the use of power. Police are always quick to defend 'their own' (other police) and government agencies/agents.","created_at":"2021-09-21T18:55:45Z","created_at_i":1632250545,"objectID":"28608477","parent_id":28608148,"story_id":28606075,"story_title":"FBI held back ransomware decryption key to run operation targeting hackers","story_url":"https://www.washingtonpost.com/national-security/ransomware-fbi-revil-decryption-key/2021/09/21/4a9417d0-f15f-11eb-a452-4da5fe48582d_story.html","updated_at":"2024-09-20T09:24:46Z"}],"hitsPerPage":20,"nbHits":31,"nbPages":2,"page":0,"params":"query=agency-agents&advancedSyntax=true&analyticsTags=backend","processingTimeMS":25,"processingTimingsMS":{"_request":{"roundTrip":22},"afterFetch":{"format":{"highlighting":1,"total":1},"merge":{"mergeLoop":{"prepareNextHit":11,"total":11},"total":11},"total":11},"fetch":{"query":4,"scanning":8,"total":13},"total":25},"query":"agency-agents","serverTimeMS":27}