For all my daily use + Codex Desktop and some local AIs in Ollama/LM Studio (which power my Home Assistant Voice Assistants) I have an Mac Studio M4 Max with 48GB of RAM (Which I bought early last year IIRC)
It's a complete beast and runs GPT-OSS 20B at over 100 tok/sec. The GUI never slows down, and I run Sequoia still, so it is always smooth and polished. I've also never heard the fans.
I got mine for $2250 USD because I am eligible for the student discount. I got the base 512GB SSD because I store most stuff on external SSDs/HDDs anyway."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Ask HN: What computer are you using for AI coding tools?"}},"_tags":["comment","author_inventor7777","story_48498766"],"author":"inventor7777","children":[48498837],"comment_text":"5-10 sessions?! Wow, not sure how you keep track of those.
For all my daily use + Codex Desktop and some local AIs in Ollama/LM Studio (which power my Home Assistant Voice Assistants) I have an Mac Studio M4 Max with 48GB of RAM (Which I bought early last year IIRC)
It's a complete beast and runs GPT-OSS 20B at over 100 tok/sec. The GUI never slows down, and I run Sequoia still, so it is always smooth and polished. I've also never heard the fans.
I got mine for $2250 USD because I am eligible for the student discount. I got the base 512GB SSD because I store most stuff on external SSDs/HDDs anyway.","created_at":"2026-06-12T01:44:00Z","created_at_i":1781228640,"objectID":"48498823","parent_id":48498766,"story_id":48498766,"story_title":"Ask HN: What computer are you using for AI coding tools?","updated_at":"2026-06-12T01:47:15Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"zozbot234"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"> ...I'm not sure why people don't try to write more stuff in C to have more control / speed / less dependences.
Codex CLI is written in Rust, which should give comparable raw performance to C/C++. Of course you can care about the "less dependencies" point but this is somewhat less of a concern on a properly maintained project like Codex. That's not so much "wild, out of control" third-party dependencies and closer to the old ideal of proper software componentry.
> Also there is a lot more to imagine, TUI side. The problem is that most projects all copy what they already saw. For instance I just did this in 20 minutes.
This mockup is really nice and the sidebar display gives you a natural way to expose running multiple thinking flows in parallel, at least if you keep them from stepping on each other's toes with code edits (keep them all in read-only "plan" mode or working on completely separate directories/files). That's not so helpful on a 128GB MacBook where a single agentic flow brings you to thermal/power limits already, but it suddenly becomes useful on other hardware (DGX Spark, Strix Halo, lower-RAM machines with SSD offload, multiple nodes with pipeline parallelism) where you have more compute than you could use for single-stream decode."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"A few words on DS4"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://antirez.com/news/165"}},"_tags":["comment","author_zozbot234","story_48142108"],"author":"zozbot234","comment_text":"> ...I'm not sure why people don't try to write more stuff in C to have more control / speed / less dependences.
Codex CLI is written in Rust, which should give comparable raw performance to C/C++. Of course you can care about the "less dependencies" point but this is somewhat less of a concern on a properly maintained project like Codex. That's not so much "wild, out of control" third-party dependencies and closer to the old ideal of proper software componentry.
> Also there is a lot more to imagine, TUI side. The problem is that most projects all copy what they already saw. For instance I just did this in 20 minutes.
This mockup is really nice and the sidebar display gives you a natural way to expose running multiple thinking flows in parallel, at least if you keep them from stepping on each other's toes with code edits (keep them all in read-only "plan" mode or working on completely separate directories/files). That's not so helpful on a 128GB MacBook where a single agentic flow brings you to thermal/power limits already, but it suddenly becomes useful on other hardware (DGX Spark, Strix Halo, lower-RAM machines with SSD offload, multiple nodes with pipeline parallelism) where you have more compute than you could use for single-stream decode.","created_at":"2026-05-15T10:08:23Z","created_at_i":1778839703,"objectID":"48146736","parent_id":48146669,"story_id":48142108,"story_title":"A few words on DS4","story_url":"https://antirez.com/news/165","updated_at":"2026-05-15T14:14:44Z"},{"_highlightResult":{"author":{"fullyHighlighted":true,"matchLevel":"partial","matchedWords":["codex"],"value":"codex"},"comment_text":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ssd"],"value":"Completely agree. I would also be surprised if this weren't done at the block level, as ZFS does SSD acceleration, rather than at the file level as the article claims. It's just so much more efficient than caching at the file layer, for not that much more RAM cost (for indexing)."},"story_title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ssd"],"value":"Fusion Drive: Apple jumps on the SSD cache bandwagon"},"story_url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ssd"],"value":"http://www.extremetech.com/computing/138535-fusion-drive-apple-jumps-on-the-ridiculously-overpriced-ssd-cache-bandwagon"}},"_tags":["comment","author_codex","story_4693362"],"author":"codex","children":[4694387],"comment_text":"Completely agree. I would also be surprised if this weren't done at the block level, as ZFS does SSD acceleration, rather than at the file level as the article claims. It's just so much more efficient than caching at the file layer, for not that much more RAM cost (for indexing).","created_at":"2012-10-24T17:12:32Z","created_at_i":1351098752,"objectID":"4693893","parent_id":4693747,"points":null,"story_id":4693362,"story_title":"Fusion Drive: Apple jumps on the SSD cache bandwagon","story_url":"http://www.extremetech.com/computing/138535-fusion-drive-apple-jumps-on-the-ridiculously-overpriced-ssd-cache-bandwagon","updated_at":"2023-09-06T21:23:53Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"chrysoprace"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"There's a point at which these things become Good Enough though, and don't bottleneck your capacity to get things done.
To your point, React, while it has new updates, hasn't changed the fundamentals since 16.8.0 (introduction of hooks) and that was 7 years ago. Yes there are new hooks, but they typically build on older concepts. AWS hasn't deprecated any of our existing services at work (besides maybe a MySQL version becoming EOL) in the last 4 years that I've worked at my current company.
While I prefer pnpm (to not take up my MacBook's inadequate SSD space), you can still use npm and get things done.
I don't need to keep obsessing over whether Codex or Claude have a 1 point lead in a gamed benchmark test so long as I'm still able to ship features without a lot of churn."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"My AI Adoption Journey"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://mitchellh.com/writing/my-ai-adoption-journey"}},"_tags":["comment","author_chrysoprace","story_46903558"],"author":"chrysoprace","children":[46947822],"comment_text":"There's a point at which these things become Good Enough though, and don't bottleneck your capacity to get things done.
To your point, React, while it has new updates, hasn't changed the fundamentals since 16.8.0 (introduction of hooks) and that was 7 years ago. Yes there are new hooks, but they typically build on older concepts. AWS hasn't deprecated any of our existing services at work (besides maybe a MySQL version becoming EOL) in the last 4 years that I've worked at my current company.
While I prefer pnpm (to not take up my MacBook's inadequate SSD space), you can still use npm and get things done.
I don't need to keep obsessing over whether Codex or Claude have a 1 point lead in a gamed benchmark test so long as I'm still able to ship features without a lot of churn.","created_at":"2026-02-06T04:26:30Z","created_at_i":1770351990,"objectID":"46909112","parent_id":46909024,"story_id":46903558,"story_title":"My AI Adoption Journey","story_url":"https://mitchellh.com/writing/my-ai-adoption-journey","updated_at":"2026-03-05T23:30:56Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"arajnoha"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"hijacking this, what is the best local model (and tool to use it) for programming, if i only have 256gb ssd on a mac? im very used to codex and while i get that it will never be this smart locally, is there any coding model like it, not too heavy on space?"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"LM Studio 0.4"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://lmstudio.ai/blog/0.4.0"}},"_tags":["comment","author_arajnoha","story_46799477"],"author":"arajnoha","comment_text":"hijacking this, what is the best local model (and tool to use it) for programming, if i only have 256gb ssd on a mac? im very used to codex and while i get that it will never be this smart locally, is there any coding model like it, not too heavy on space?","created_at":"2026-01-29T15:49:20Z","created_at_i":1769701760,"objectID":"46811768","parent_id":46799477,"story_id":46799477,"story_title":"LM Studio 0.4","story_url":"https://lmstudio.ai/blog/0.4.0","updated_at":"2026-03-05T23:26:08Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"dudeinhawaii"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"I think it's hard because it's quite artistic and individualistic, as silly as that may sound.
I've built "large projects" with AI, which is 10k-30k lines of algorithmic code and 50k-100k+ lines of UI/Interface.
I've found a few things to be true (that aren't true for everyone).
1. The choice of model (strengths and weaknesses) and OS, dramatically affect how you must approach problems.
2. Being a skilled programmer/engineer yourself will allow you to slice things along areas of responsibility, domains, or other directions that make sense (for code size, context preservation, and being able to wrap your head around it).
3. For anything where you have a doubt, ask 3 or more models -- have them write their findings down in a file each -- and then have 3 models review the findings with respect to the code. More often than not, you march towards consensus and a good solution.
4. GPT-5-Codex via OpenAI Codex CLi on Linux/WSL was, for me, the most capable model for coding while Claude is the most capable for quick fixes and UI.
5. Tooling and ways to measure "success" are imperative. If you can't define the task in a way that success is easy to define -- neither a human nor AI would complete it satisfactorily. You'll find that most engineer tasks are laid out in very "hand-wavy" way -- particularly UI tasks. Either lay it out cleanly or expect to iterate.
6. AI does not understand the physical/visual world. It will fail hard on things which have an implied understanding. For instance, it will not automatically intuit the implication of 50 parallel threads trying to read from an SSD -- unless you guide it. Ditto for many other optimizations and usage patterns where code meets real-world. These will often be unique and interesting bugs or performance areas that a good engineer would know straight out.
7. It's useful to have non-agentic tools that can perform massive codebase analysis for tough problems. Even at 400k tokens context, a large codebase can quickly become unwieldy. I have built custom python tools (pretty easy) to do things like "get all files of a type recursively and generate a context document that will submit with my query". You then query GPT-5-high, Claude Opus, Gemini 2.5 Pro and cross-check.
8. Make judicious use of GIT. The pattern doesn't matter, just have one. My pattern is commit after every working agentic run (let's say feature). If it's a fail and taking more than a few turns to get working -- I scrap the whole thing and re-assess my query or how I might approach or break down the task.
9. It's up to you to guide the agent on the most thoughtful approaches -- this is the human aspect. If you're using Cloud Provider X and they provide cheap queues then it's on you to guide your agent to use queues for the solution rather than let's say a SQL db -- and it's on you to understand the tradeoffs. AI will perhaps help explain them but it will never truly understand your business case and requirements for reliability, redundancy, etc. Perhaps you can craft queries for this but this is an area where AI meets real world and those tend to fail.
One more thing I'd add is that you should make an attempt to fix bugs in your 'new' codebase on occasion. You'll get an understanding for how things work and also how maintainable it truly is. You'll also keep your own troubleshooting skills from atrophying."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Vibe Code Warning \u2013 A personal casestudy"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/jackdoe/pico2-swd-riscv"}},"_tags":["comment","author_dudeinhawaii","story_45874987"],"author":"dudeinhawaii","comment_text":"I think it's hard because it's quite artistic and individualistic, as silly as that may sound.
I've built "large projects" with AI, which is 10k-30k lines of algorithmic code and 50k-100k+ lines of UI/Interface.
I've found a few things to be true (that aren't true for everyone).
1. The choice of model (strengths and weaknesses) and OS, dramatically affect how you must approach problems.
2. Being a skilled programmer/engineer yourself will allow you to slice things along areas of responsibility, domains, or other directions that make sense (for code size, context preservation, and being able to wrap your head around it).
3. For anything where you have a doubt, ask 3 or more models -- have them write their findings down in a file each -- and then have 3 models review the findings with respect to the code. More often than not, you march towards consensus and a good solution.
4. GPT-5-Codex via OpenAI Codex CLi on Linux/WSL was, for me, the most capable model for coding while Claude is the most capable for quick fixes and UI.
5. Tooling and ways to measure "success" are imperative. If you can't define the task in a way that success is easy to define -- neither a human nor AI would complete it satisfactorily. You'll find that most engineer tasks are laid out in very "hand-wavy" way -- particularly UI tasks. Either lay it out cleanly or expect to iterate.
6. AI does not understand the physical/visual world. It will fail hard on things which have an implied understanding. For instance, it will not automatically intuit the implication of 50 parallel threads trying to read from an SSD -- unless you guide it. Ditto for many other optimizations and usage patterns where code meets real-world. These will often be unique and interesting bugs or performance areas that a good engineer would know straight out.
7. It's useful to have non-agentic tools that can perform massive codebase analysis for tough problems. Even at 400k tokens context, a large codebase can quickly become unwieldy. I have built custom python tools (pretty easy) to do things like "get all files of a type recursively and generate a context document that will submit with my query". You then query GPT-5-high, Claude Opus, Gemini 2.5 Pro and cross-check.
8. Make judicious use of GIT. The pattern doesn't matter, just have one. My pattern is commit after every working agentic run (let's say feature). If it's a fail and taking more than a few turns to get working -- I scrap the whole thing and re-assess my query or how I might approach or break down the task.
9. It's up to you to guide the agent on the most thoughtful approaches -- this is the human aspect. If you're using Cloud Provider X and they provide cheap queues then it's on you to guide your agent to use queues for the solution rather than let's say a SQL db -- and it's on you to understand the tradeoffs. AI will perhaps help explain them but it will never truly understand your business case and requirements for reliability, redundancy, etc. Perhaps you can craft queries for this but this is an area where AI meets real world and those tend to fail.
One more thing I'd add is that you should make an attempt to fix bugs in your 'new' codebase on occasion. You'll get an understanding for how things work and also how maintainable it truly is. You'll also keep your own troubleshooting skills from atrophying.","created_at":"2025-11-11T18:01:33Z","created_at_i":1762884093,"objectID":"45890629","parent_id":45880919,"story_id":45874987,"story_title":"Vibe Code Warning \u2013 A personal casestudy","story_url":"https://github.com/jackdoe/pico2-swd-riscv","updated_at":"2026-03-05T23:01:53Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"diggan"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"> Can you imagine if Excel worked like this?
I mean, why would I imagine that? Who would want that? It's like the argument against legal marijuana, and someone replies "But would you like your pilot to be high when flying?!". Right tool for the right job, clearly when you want 100% certainty then LLMs aren't the tool for that. Just because they're useful for some things don't mean we have to replace everything with them.
> Also, each try costs money!
I guess you're using some paid API? Try a different way then. I mostly use the web UI from OpenAI, or Codex lately, or ran locally with my own agent using local weights, neither is "each try costs money" more than writing data to my SSD is costing me money.
It's not a holy grail some people paint it, and not sure we're across the "productivity threshold" (https://news.ycombinator.com/item?id=44160664) yet, but it's worth trying it out probably before jumping to conclusions. But no one is forcing you either, YMMV and all that."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Cloudlflare builds OAuth with Claude and publishes all the prompts"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/cloudflare/workers-oauth-provider/"}},"_tags":["comment","author_diggan","story_44159166"],"author":"diggan","comment_text":"> Can you imagine if Excel worked like this?
I mean, why would I imagine that? Who would want that? It's like the argument against legal marijuana, and someone replies "But would you like your pilot to be high when flying?!". Right tool for the right job, clearly when you want 100% certainty then LLMs aren't the tool for that. Just because they're useful for some things don't mean we have to replace everything with them.
> Also, each try costs money!
I guess you're using some paid API? Try a different way then. I mostly use the web UI from OpenAI, or Codex lately, or ran locally with my own agent using local weights, neither is "each try costs money" more than writing data to my SSD is costing me money.
It's not a holy grail some people paint it, and not sure we're across the "productivity threshold" (https://news.ycombinator.com/item?id=44160664) yet, but it's worth trying it out probably before jumping to conclusions. But no one is forcing you either, YMMV and all that.","created_at":"2025-06-02T17:36:05Z","created_at_i":1748885765,"objectID":"44161193","parent_id":44160920,"story_id":44159166,"story_title":"Cloudlflare builds OAuth with Claude and publishes all the prompts","story_url":"https://github.com/cloudflare/workers-oauth-provider/","updated_at":"2025-06-03T16:49:00Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"kragen"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"The solutions for gradual forgetting and catastrophic forgetting are very different, though.
Let's consider the problem of media longevity \u2014 while, as you point out, it is not by itself sufficient to preserve knowledge, it does seem to be necessary, at least as we currently understand things. (Scholars of songlines may disagree, but of course oral traditions like songlines are even more vulnerable to catastrophic forgetting; even half a century of prohibition can obliterate them.)
If you preserve data on Flash, you need to refresh it every few years before the stored electrons leak away; standard datasheet retention times are 10\u201320 years, though presumably that's at 80\u00b0, so maybe you'll get a few centuries at room temperature. If you can trust in continuity of institutions, this is not a big problem; you just have an endowment sufficient to support a small number of sysadmins who make sure the SSD arrays get resilvered at the right interval, replace broken devices, etc.
But if your preservation medium has to survive the PRC nuking TSMC 18 months from now \u2014 or an invasion by a military dictatorship of genocidal religious fanatics who hunt down and kill the sysadmins and burn the archives, as happened with the Maya codices \u2014 Flash looks much less appealing (though perhaps still viable; see http://canonical.org/~kragen/eotf/ and https://dercuano.github.io/notes/atmospheric-pressure-harves...).
\u2014 \u2042 \u2014
I think this also bears on the question you're focusing on in the post, which as I understand it is more a question of curriculum design than of preserving physical storage media. If the target audience for the curriculum is the next generation, or three generations down the line, you can assume a lot of shared cultural background: shared celebrities, shared neologisms and modisms, shared values in a lot of ways. Hipparchos, by contrast, was writing for Ptolemaios, though he didn't know it. He died in 0120 BCE, and Ptolemaios was born in 0100 CE, 220 years later. Hipparchos was the most recent astronomer he could find to cite in the Almagest.
Amongst the civil warfare of the late Ptolemaic dynasty, none of the succeeding eleven generations had produced new astronomical observations, and the line of philosophical mentorship was broken, at least within the Hellenistic world. This bears quite directly on the problem of lost tacit knowledge you focus on in your post. Even Hipparchos was only able to do his work because he lived in Rhodos, on the periphery of the Alexandrian scientific world, which was sacked by Cassius in 043 BCE after a century of gradual reduction to servitude by Rome.
How do you design a curriculum so that it is still intelligible after eleven generations of cataclysmic cultural collapse, largely under a prescientific genocidal military dictatorship like that installed by the Roman invasion? The solution might look more like the Rosetta Project or the Cult of the Bound Variable and less like Surely You're Joking, Mr. Feynman. If Hipparchos had done a better job, maybe Ptolemaios (and consequently Colombo) wouldn't have gotten the size of the Earth so badly wrong. Maybe Ptolemaios, like Archimedes before the Romans killed him, would have followed the heliocentric model Aristarchos had developed 500 years before him (though Hipparchos did not.)"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Forgetting the Asbestos \u2013 how we lose knowledge and technologies"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://1517.substack.com/p/forgetting-the-asbestos"}},"_tags":["comment","author_kragen","story_33320294"],"author":"kragen","children":[33334120],"comment_text":"The solutions for gradual forgetting and catastrophic forgetting are very different, though.
Let's consider the problem of media longevity \u2014 while, as you point out, it is not by itself sufficient to preserve knowledge, it does seem to be necessary, at least as we currently understand things. (Scholars of songlines may disagree, but of course oral traditions like songlines are even more vulnerable to catastrophic forgetting; even half a century of prohibition can obliterate them.)
If you preserve data on Flash, you need to refresh it every few years before the stored electrons leak away; standard datasheet retention times are 10\u201320 years, though presumably that's at 80\u00b0, so maybe you'll get a few centuries at room temperature. If you can trust in continuity of institutions, this is not a big problem; you just have an endowment sufficient to support a small number of sysadmins who make sure the SSD arrays get resilvered at the right interval, replace broken devices, etc.
But if your preservation medium has to survive the PRC nuking TSMC 18 months from now \u2014 or an invasion by a military dictatorship of genocidal religious fanatics who hunt down and kill the sysadmins and burn the archives, as happened with the Maya codices \u2014 Flash looks much less appealing (though perhaps still viable; see http://canonical.org/~kragen/eotf/ and https://dercuano.github.io/notes/atmospheric-pressure-harves...).
\u2014 \u2042 \u2014
I think this also bears on the question you're focusing on in the post, which as I understand it is more a question of curriculum design than of preserving physical storage media. If the target audience for the curriculum is the next generation, or three generations down the line, you can assume a lot of shared cultural background: shared celebrities, shared neologisms and modisms, shared values in a lot of ways. Hipparchos, by contrast, was writing for Ptolemaios, though he didn't know it. He died in 0120 BCE, and Ptolemaios was born in 0100 CE, 220 years later. Hipparchos was the most recent astronomer he could find to cite in the Almagest.
Amongst the civil warfare of the late Ptolemaic dynasty, none of the succeeding eleven generations had produced new astronomical observations, and the line of philosophical mentorship was broken, at least within the Hellenistic world. This bears quite directly on the problem of lost tacit knowledge you focus on in your post. Even Hipparchos was only able to do his work because he lived in Rhodos, on the periphery of the Alexandrian scientific world, which was sacked by Cassius in 043 BCE after a century of gradual reduction to servitude by Rome.
How do you design a curriculum so that it is still intelligible after eleven generations of cataclysmic cultural collapse, largely under a prescientific genocidal military dictatorship like that installed by the Roman invasion? The solution might look more like the Rosetta Project or the Cult of the Bound Variable and less like Surely You're Joking, Mr. Feynman. If Hipparchos had done a better job, maybe Ptolemaios (and consequently Colombo) wouldn't have gotten the size of the Earth so badly wrong. Maybe Ptolemaios, like Archimedes before the Romans killed him, would have followed the heliocentric model Aristarchos had developed 500 years before him (though Hipparchos did not.)","created_at":"2022-10-25T15:45:19Z","created_at_i":1666712719,"objectID":"33332147","parent_id":33330105,"story_id":33320294,"story_title":"Forgetting the Asbestos \u2013 how we lose knowledge and technologies","story_url":"https://1517.substack.com/p/forgetting-the-asbestos","updated_at":"2024-09-20T12:22:42Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"radial_symmetry"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"A tool that runs Claude Code and Codex side-by-side in worktrees"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/stravu/crystal"}},"_tags":["story","author_radial_symmetry","story_45604621"],"author":"radial_symmetry","children":[45604670,45612624],"created_at":"2025-10-16T12:40:30Z","created_at_i":1760618430,"num_comments":2,"objectID":"45604621","points":3,"story_id":45604621,"title":"A tool that runs Claude Code and Codex side-by-side in worktrees","updated_at":"2026-03-05T22:48:14Z","url":"https://github.com/stravu/crystal"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ahmed1490"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"Use $10 promo code: 'DOIT10' to deploy an ssd server for free.
You may use my referral while u sign up:\nhttps://www.digitalocean.com/?refcode=5572bba1fb25"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"Digital Ocean promo code - ssd linux"},"url":{"matchLevel":"none","matchedWords":[],"value":""}},"_tags":["story","author_ahmed1490","story_7620323","ask_hn"],"author":"ahmed1490","created_at":"2014-04-21T08:53:34Z","created_at_i":1398070414,"num_comments":0,"objectID":"7620323","points":2,"story_id":7620323,"story_text":"Use $10 promo code: 'DOIT10' to deploy an ssd server for free.
You may use my referral while u sign up:\nhttps://www.digitalocean.com/?refcode=5572bba1fb25","title":"Digital Ocean promo code - ssd linux","updated_at":"2024-09-19T20:42:46Z","url":""},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"schizi"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"Flowyble Studio \u2013 Run Claude, Copilot and Codex Side-by-Side"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://flowyble.com/studio"}},"_tags":["story","author_schizi","story_47728908"],"author":"schizi","children":[47728909],"created_at":"2026-04-11T09:08:18Z","created_at_i":1775898498,"num_comments":0,"objectID":"47728908","points":2,"story_id":47728908,"title":"Flowyble Studio \u2013 Run Claude, Copilot and Codex Side-by-Side","updated_at":"2026-04-11T09:31:54Z","url":"https://flowyble.com/studio"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"sngnb"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"Built a tiny open-source repo that packages the same ASCII "FUCK YEAH" output for both Claude Code and Codex.
The Claude side is a minimal plugin. The Codex side is a minimal skill folder. No hooks, agents, or extra setup beyond the packaging.
I've been building and abandoning too many projects lately, and this one felt worth finishing.
Repo: https://github.com/nrtvai/fuckyeah"},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["codex"],"value":"Show HN: Fuckyeah, a minimal Claude Code plugin and Codex skill"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/nrtvai/fuckyeah"}},"_tags":["story","author_sngnb","story_47310960","show_hn"],"author":"sngnb","created_at":"2026-03-09T16:10:32Z","created_at_i":1773072632,"num_comments":0,"objectID":"47310960","points":1,"story_id":47310960,"story_text":"Built a tiny open-source repo that packages the same ASCII "FUCK YEAH" output for both Claude Code and Codex.
The Claude side is a minimal plugin. The Codex side is a minimal skill folder. No hooks, agents, or extra setup beyond the packaging.
I've been building and abandoning too many projects lately, and this one felt worth finishing.
Repo: https://github.com/nrtvai/fuckyeah","title":"Show HN: Fuckyeah, a minimal Claude Code plugin and Codex skill","updated_at":"2026-03-09T16:11:56Z","url":"https://github.com/nrtvai/fuckyeah"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"hoag"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"Hey HN! I'm a founder first, lawyer second. I understand code stacks well enough to explain them, but I've never been able to actually build software, and this has been a chip on my shoulder my entire life.
So Scribefully started as my first vibe coding project last summer. I'd read that building something with HN-style upvoting was a good learning project, and I was curious to try Claude Code.
The more I built, the more I realized I wanted what it evolved into: a single place to aggregate all my scattered professional work -\u2013 articles, papers, videos, code -\u2013 into one shareable page, with community upvoting baked in. Carrd and others offer portfolios, but none merge that with a social layer. Think HN meets a portfolio builder.
Example portfolios to check out: \n - https://scribefully.com/author/marc-hoag \n - https://scribefully.com/author/tawanda-kanhema
Browse everything without an account. Signup only required to comment or claim authorship. Completely free.
The hardest part was letting people use the site without signing up \u2013- even submitting anonymously -\u2013 but claiming authorship later. This auth flow alone probably took 40-50 of my ~100 total hours. Race conditions are brutal, but of course you know that already.
Tech: Next.js 15, React 19, Supabase, Tailwind, Render. Built with Claude Code and ChatGPT Codex.
Side effect: I got so frustrated with context window issues (and secrets management) that I built this: https://github.com/marchoag/Claude-Code-Setup-Wizard-MD
I've shared Scribefully with academics and professionals since last July; figured it was time to Show HN.
Building this \u2013- and an iOS app I shipped last week (FloodRoute for tracking flooded roads) \u2013- has been kind of emotional. You can't imagine what it means to finally build software after years of only understanding it.
What a fantastic, magical time to be alive."},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Scribefully is a portfolio/HN-style community for academics & pros"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://scribefully.com/"}},"_tags":["story","author_hoag","story_46715945","show_hn"],"author":"hoag","created_at":"2026-01-22T06:25:39Z","created_at_i":1769063139,"num_comments":0,"objectID":"46715945","points":1,"story_id":46715945,"story_text":"Hey HN! I'm a founder first, lawyer second. I understand code stacks well enough to explain them, but I've never been able to actually build software, and this has been a chip on my shoulder my entire life.
So Scribefully started as my first vibe coding project last summer. I'd read that building something with HN-style upvoting was a good learning project, and I was curious to try Claude Code.
The more I built, the more I realized I wanted what it evolved into: a single place to aggregate all my scattered professional work -\u2013 articles, papers, videos, code -\u2013 into one shareable page, with community upvoting baked in. Carrd and others offer portfolios, but none merge that with a social layer. Think HN meets a portfolio builder.
Example portfolios to check out: \n - https://scribefully.com/author/marc-hoag \n - https://scribefully.com/author/tawanda-kanhema
Browse everything without an account. Signup only required to comment or claim authorship. Completely free.
The hardest part was letting people use the site without signing up \u2013- even submitting anonymously -\u2013 but claiming authorship later. This auth flow alone probably took 40-50 of my ~100 total hours. Race conditions are brutal, but of course you know that already.
Tech: Next.js 15, React 19, Supabase, Tailwind, Render. Built with Claude Code and ChatGPT Codex.
Side effect: I got so frustrated with context window issues (and secrets management) that I built this: https://github.com/marchoag/Claude-Code-Setup-Wizard-MD
I've shared Scribefully with academics and professionals since last July; figured it was time to Show HN.
Building this \u2013- and an iOS app I shipped last week (FloodRoute for tracking flooded roads) \u2013- has been kind of emotional. You can't imagine what it means to finally build software after years of only understanding it.
What a fantastic, magical time to be alive.","title":"Show HN: Scribefully is a portfolio/HN-style community for academics & pros","updated_at":"2026-03-05T23:23:01Z","url":"https://scribefully.com/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"andrewflnr"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"Speaking of which, for the rethink people on the thread, how much of old "key-value store for SSDs" code is still active? Is the document store at all a layer on top of that?"},"story_title":{"matchLevel":"none","matchedWords":[],"value":"RethinkDB 1.9: Indexing and query runtime performance"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"http://rethinkdb.com/blog/1.9-release/"}},"_tags":["comment","author_andrewflnr","story_6368532"],"author":"andrewflnr","children":[6372615],"comment_text":"Speaking of which, for the rethink people on the thread, how much of old "key-value store for SSDs" code is still active? Is the document store at all a layer on top of that?","created_at":"2013-09-12T04:05:31Z","created_at_i":1378958731,"objectID":"6372000","parent_id":6369498,"points":null,"story_id":6368532,"story_title":"RethinkDB 1.9: Indexing and query runtime performance","story_url":"http://rethinkdb.com/blog/1.9-release/","updated_at":"2023-09-06T22:11:11Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"johnmurch"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"Whoa - Sweet Price.
If you want to compare to digital ocean they are having a coupon code on Twitter - Includes 512MB RAM, 20GB SSD Disk, & 1TB Transfer for $5/mo.! Use promo code \"SSDTWEET\" for a $10 credit."},"story_title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ssd"],"value":"1GB Ram & SSD Cloud Hosting for $6"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://www.ubiquityservers.com/cloud"}},"_tags":["comment","author_johnmurch","story_5478723"],"author":"johnmurch","comment_text":"Whoa - Sweet Price.
If you want to compare to digital ocean they are having a coupon code on Twitter - Includes 512MB RAM, 20GB SSD Disk, & 1TB Transfer for $5/mo.! Use promo code \"SSDTWEET\" for a $10 credit.","created_at":"2013-04-02T12:02:42Z","created_at_i":1364904162,"objectID":"5478779","parent_id":5478723,"story_id":5478723,"story_title":"1GB Ram & SSD Cloud Hosting for $6","story_url":"https://www.ubiquityservers.com/cloud","updated_at":"2024-09-19T19:30:49Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mitchwainer"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"We use KVM. Here is a $20 credit to try us out! =]
Promo Code: SSDPOWER20"},"story_title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ssd"],"value":"TechStars Graduate DigitalOcean Switches To SSD For Its $5 Per Month VPS"},"story_url":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["ssd"],"value":"http://techcrunch.com/2013/01/15/techstars-graduate-digitalocean-switches-to-ssd-for-its-5-per-month-vps-to-take-on-linode-and-rackspace/"}},"_tags":["comment","author_mitchwainer","story_5059723"],"author":"mitchwainer","comment_text":"We use KVM. Here is a $20 credit to try us out! =]
Promo Code: SSDPOWER20","created_at":"2013-01-15T16:52:11Z","created_at_i":1358268731,"objectID":"5061182","parent_id":5060831,"story_id":5059723,"story_title":"TechStars Graduate DigitalOcean Switches To SSD For Its $5 Per Month VPS","story_url":"http://techcrunch.com/2013/01/15/techstars-graduate-digitalocean-switches-to-ssd-for-its-5-per-month-vps-to-take-on-linode-and-rackspace/","updated_at":"2024-09-19T19:11:13Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Razengan"},"comment_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["codex","ssd"],"value":"> Google has a better image model in the majority of cases.
Not always. A couple months ago (before ChatGPT Images 2) I tried various prompts on both Google's Nano Banana or whatever and ChatGPT.
"Capybara riding a tricycle. It has 7 tentacles instead of legs"
Google got the number of tentacles completely wrong: https://i.postimg.cc/nzY30y7X/Capybara-Gemini-Nano.png
and after some additions like spotted fur and multicolored tentacles, it was no contest:
ChatGPT: https://i.postimg.cc/02c2LrxV/Capybara-Chat-GPT-before-Image... (although there's still kinda 1 extra tentacle)
And Google still seems to have that odd choice of a European plaza/square/cobblestone street background for everything.
> Claude Opus and Fable are like a billion times better.
NOT at ALL: https://i.imgur.com/jYawPDY.png
Subscribed to Claude Opus for 2 months, with a few months gap between subscriptions to try different versions.
The UX/UI around Anthropic's products was excruciatingly annoying, right from the payment process, and Claude's AI was often hilariously dumb and "trying too hard", constantly full of "oops, you're right" backtracking and often borderline dangerous.
I tried Claude and ChatGPT Codex side by side on some tasks, with the same prompts. Each time, my confidence in Claude fell.
I've been subscribed to the $20 ChatGPT plan for more than 1 year, and this month, I am trying the $100 plan for 1 month.
ChatGPT Codex has been actually helpful and made me more productive enough that I can't imagine going back to coding without it."},"story_title":{"matchLevel":"none","matchedWords":[],"value":"Leaked OpenAI financials show $38.5B loss and compute burn"},"story_url":{"matchLevel":"none","matchedWords":[],"value":"https://runtimewire.com/article/openai-leaked-financials-altman-compute-burn"}},"_tags":["comment","author_Razengan","story_48565130"],"author":"Razengan","children":[48571529],"comment_text":"> Google has a better image model in the majority of cases.
Not always. A couple months ago (before ChatGPT Images 2) I tried various prompts on both Google's Nano Banana or whatever and ChatGPT.
"Capybara riding a tricycle. It has 7 tentacles instead of legs"
Google got the number of tentacles completely wrong: https://i.postimg.cc/nzY30y7X/Capybara-Gemini-Nano.png
and after some additions like spotted fur and multicolored tentacles, it was no contest:
ChatGPT: https://i.postimg.cc/02c2LrxV/Capybara-Chat-GPT-before-Image... (although there's still kinda 1 extra tentacle)
And Google still seems to have that odd choice of a European plaza/square/cobblestone street background for everything.
> Claude Opus and Fable are like a billion times better.
NOT at ALL: https://i.imgur.com/jYawPDY.png
Subscribed to Claude Opus for 2 months, with a few months gap between subscriptions to try different versions.
The UX/UI around Anthropic's products was excruciatingly annoying, right from the payment process, and Claude's AI was often hilariously dumb and "trying too hard", constantly full of "oops, you're right" backtracking and often borderline dangerous.
I tried Claude and ChatGPT Codex side by side on some tasks, with the same prompts. Each time, my confidence in Claude fell.
I've been subscribed to the $20 ChatGPT plan for more than 1 year, and this month, I am trying the $100 plan for 1 month.
ChatGPT Codex has been actually helpful and made me more productive enough that I can't imagine going back to coding without it.","created_at":"2026-06-17T05:51:42Z","created_at_i":1781675502,"objectID":"48566274","parent_id":48565961,"story_id":48565130,"story_title":"Leaked OpenAI financials show $38.5B loss and compute burn","story_url":"https://runtimewire.com/article/openai-leaked-financials-altman-compute-burn","updated_at":"2026-06-17T17:37:54Z"}],"hitsPerPage":20,"nbHits":67569,"nbPages":50,"page":0,"params":"query=codex+ssd&advancedSyntax=true&analyticsTags=backend","processingTimeMS":36,"processingTimingsMS":{"_request":{"queue":1,"roundTrip":19},"afterFetch":{"format":{"highlighting":1,"total":1},"merge":{"mergeLoop":{"prepareNextHit":1,"total":1},"total":1},"total":1},"fetch":{"query":3,"scanning":29,"total":33},"total":36},"query":"codex ssd","serverTimeMS":39}
![https://i.postimg.cc/nzY30y7X/Capybara-Gemini-Nano.png](\"https://i.postimg.cc/nzY30y7X/Capybara-Gemini-Nano.png\"){kind=link}
![https://i.postimg.cc/02c2LrxV/Capybara-Chat-GPT-before-Image...](\"https://i.postimg.cc/02c2LrxV/Capybara-Chat-GPT-before-Images-2.png\"){kind=link}
![https://i.imgur.com/jYawPDY.png](\"https://i.imgur.com/jYawPDY.png\"){kind=link}