Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

When AI Builds Itself: Our progress toward recursive self-improvement

anthropic.com

Post reply on HN
Print view View original

501–510 of 738 posts

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#501

Post by matheusmoreira »

raptor99 wrote: post #428
matheusmoreira wrote: post #404

Earlier quoted context omitted.

I measured an ~8x increase in the number of commits I've been pushing, and I've actually been trying to restrain myself. I could do a lot more if I stopped reviewing and editing the code. I think it's got more to do with my executive ability than raw productivity though. AI essentially cured my ADHD by making the execution of my ideas virtually painless.

LOL "I measured an 8x increase in the number of commits Ive been pushing" is an absolutely useless statement

Subscribed to Claude a few months ago. I immediately started working with it on my programming language. Since then, I've implemented a compacting garbage collector, a size class based memory allocator, a unified value heap, deeply optimized hash tables and even implemented shapes like V8 and Self, redesigned the value representation, created a Common Lisp style condition system, implemented UTF-8 text decoding, refined the generators API, increased the number of tests from ~200 to ~1200 and improved the test suite to the point it runs all of those tests in parallel in under two seconds, implemented stack protection support, added an aarch64 matrix to the GitHub CI, fixed a zillion bugs, improved performance, perfected tail call optimization. I did so much stuff I'm probably forgetting some. And these aren't "lol just do it" prompts either, I'm putting effort into refining design and implementation. I review every line. Just finished designing safe hash table iteration in spite of mutability: generation counters that get bumped whenever the table is reallocated. It's actually gonna be more powerful than what other languages do. Next up on my todo list is to implement my language's unified pattern matcher, static allocation for all interpreter internal data in order to get rid of all initialization code and achieve nearly zero startup time, and then finally a bytecode interpreter to close the performance gap on the likes of Python.

Dramatically improved my static site generator Pugneum to the point it's better than markdown and added Atom and RSS feeds, used it to write several articles about my language. Pace is so fast I actually need to write those articles by hand in order to crystalize the knowledge I learned. If I don't I'm afraid I'll just forget everything. No LLMs for the articles themselves, but they sure as hell took all the pain away from writing them. Pugneum even has back references and table of contents generation now. Claude even helped me refine my website's CSS, something I'm not very good at.

Also created my own invoicing system for $DAYJOB so I can invoice companies from my terminal. Started a decompilation project for my cherished childhood games and I've already almost finished decompiling one game's engine after just a few days. Been working on my cyberdeck project too, this one's a bit slow because I got to the point where I'll actually need to spend money on it to move forward. All this inside the rootless development virtual machine system built on top of QEMU and systemd that I developed together with Claude, whose network isolation I'm currently hardening. Started reverse engineering my laptop again! And I'm actually making progress! Made a color scheme app for the keyboard LEDs controller I made many years ago, with loads and loads of color schemes! Found some kind of bug in my keyboard while doing it, in less than an hour I had the root cause and a fix applied locally, sent the fix to systemd, it got merged. Planning to ramp up my free and open source software participation as well now that exploring codebases is a breeze. Already have some mesa patches ready for upstream. Have been playing with strace since I use it so much.

Better?

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#502

Post by cookiengineer »

aleqs wrote: post #40

Okay, so anthropic has amazing AI which supposedly writes most of their code and can continuously improve... meanwhile they have outages on a regular basis, and any kind of long-running work will now consistently hit 'API Error: Server is temporarily limiting requests'. Not sure of this is intentional to force a reduction of token usage, but at this point I need to build around these throttling limits and outages wit…

The main reason I am building my own agentic environment is that I need full control and reproducibility of what I am building.

Post November and post openclaw agentic environments need to be built differently, and for selfhosting models the context size problem really requires a strong harness which intelligently helps reduce context size.

Planner/orchestrator architecture, agent to agent summarizer, specification based tools (fck all this markdown memory bullshit btw), tool call shrinking, and workflow management are all really important because of the context size problem.

Nobody has enough VRAM for the large K/V caches, and nobody can afford f16/f32 caches in terms of memory, which are also necessary for longer conversations. MoE 30b models have improved so much though, qwen 3/3.6 coder is the real champion doing almost the same things with less than 1/10th the memory requirements. Just think about that in terms of engineering and what your bet is going to be. Haiku pales in comparison.

Currently my focus with exocomp is trying to figure out how I can record, replay, restart, and debug workflow sessions of agents in a better manner so that I as a human can understand what's going on. Currently I think that UI will be something like a gantt chart where you have a graph with connections representing agent to agent communication. And yes, that's a lot of fiddling with SVG as it turns out, so I'm not quite there yet.

Anyways, in case you're interested. I'm manually building this env and trying to unit test the critical parts. [1]

[1] https://github.com/cookiengineer/exocomp

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#503

Post by danny_codes »

SimianSci wrote: post #41

Anthropic is looking to IPO here soon. A key aspect of this is to prove profitability. Shifting their focus from Training new models to instead serving inference, they would greatly reduce their spend. In fact this is something being reported on that they are already doing, which is the reason for their first ever profitable quarter. Its awfully convenient that the company which has greatly reduced its spend on train…

Their model lead is tiny. If they cut training focus they'll be quickly overtaken, one imagines. Seems dicey, if any of the OSS players comes out with a better model.. well, there are a bunch of better harnesses than Claude code you can download.

This is a very undifferentiated, swappable product. Kind of like tissue paper in that respect

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#504

Post by jachee »

weakfish wrote: post #480
c-hendricks wrote: post #468

Earlier quoted context omitted.

> ChatGPT has 1 billion MAU. People are now getting life advice, financial advice, and mental health help from chatbots Personally not the kind of breakthrough I'm psyched about

Yeah, the thing that worries me is that an LLM can be guided to agree with any premise and will rarely ever take a hard stance.

…which is why it’s led to more than zero suicides.

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#505

Post by danny_codes »

Theodores wrote: post #247
SimianSci wrote: post #41

Anthropic is looking to IPO here soon. A key aspect of this is to prove profitability. Shifting their focus from Training new models to instead serving inference, they would greatly reduce their spend. In fact this is something being reported on that they are already doing, which is the reason for their first ever profitable quarter. Its awfully convenient that the company which has greatly reduced its spend on train…

Honest question: Is anyone here looking to put their own money into the Anthropic, OpenAI or SpaceX IPOs? Maybe it is my poverty mindset that is holding me back, however, I can't imagine becoming an investor in any of the AI 'startups'. There are plenty of pundits able to advise others on where to put their money, and sometimes there is everyone and their dog advising you to get into Bitcoin, gold or some other schem…

I mean, my passive funds will be forced to buy a little bit I assume, given recent entry changes to indexes. So.. yes? I guess?

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#506

Post by jachee »

Quarrelsome wrote: post #347
pizlonator wrote: post #321

Earlier quoted context omitted.

Yeah, this is a good point. But the clock is ticking.

on what? Who the fuck would go full transparency of what's in their black box in this hostile culture of AI hatred? None of us can put a number on what code we've used in our services that was written by humans and long may it last.

They literally can’t go full-transparency. I know a high-level insider, and the fact is that even the folks implementing things don’t actually know how it works, only that it does, and how to get it to generally behave.

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#507

Post by jimbokun »

killbot5000 wrote: post #246
drivebyhooting wrote: post #208

Earlier quoted context omitted.

You still need wizards to cast the spells..

Not if your spells cast their own spells.

Read the article.

They are saying very clearly the models are not casting their own spells…yet. But looking at trends and speculating when they may start doing so.

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#508

Post by jachee »

yoyohello13 wrote: post #335
wild_egg wrote: post #289

Earlier quoted context omitted.

What does a breakthrough look like?

How about a Windows file browser that opens in less than 5 seconds.

That sounds like a your-system issue. I hit Win+E (admittedly on an old Win10 box) and it instantly pops up an explorer window.

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#509

Post by thordenmark »

aleqs wrote: post #40

Okay, so anthropic has amazing AI which supposedly writes most of their code and can continuously improve... meanwhile they have outages on a regular basis, and any kind of long-running work will now consistently hit 'API Error: Server is temporarily limiting requests'. Not sure of this is intentional to force a reduction of token usage, but at this point I need to build around these throttling limits and outages wit…

Growing pains of being successful. These are solvable problems and will be. Can they maintain their momentum without pissing off too much of their customer base before these issues are resolved?
Post reply on HN