31–40 of 104 posts
Earlier quoted context omitted.
What do you mean by 2?
LLMs will take shortcuts and cheat in ways that a human would realize are counterproductive.
IMO, LLMs will be a dead end to anything close to AGI because of this and hallucinations.
We're missing something in the mix, which I suspect is some kind of advanced JEPA model.
In the last couple of days I wanted to try out the new definitive DeepSeek v4 releases. I gave it the repository of a semi-abandoned video compression codec and I told it to perform the usual benchmark -> profile -> verify -> research -> improve loop. I specifically chose this codec because the authors include a verifier for the bitstream to make sure you don't break stuff if you want to try your own implementation.…
This is the way. Checkout the technique mentioned in the alphaevolve paper and see if it works well for your setting.
Earlier quoted context omitted.
What do you mean by 2?
LLMs will take shortcuts and cheat in ways that a human would realize are counterproductive.
Humans do it ignorantly.
The LLMs will improve while average human IQ in the west dips closer and closer to the 80s on the global scale.
This is really cool - I really like the beam search idea,
this is the first time ive heard of beam search. i would have reached for a genetic algorithm of some sort, although it seems like some stochastic versions of beam search exist to avoid local minima. i wonder if there are any good frameworks for building these that agents can construct and use.
Every step here has an oracle: wall-clock, the profile, pass or fail from the verifier. I had an agent-built app audited task by task, 10 came back done and 7 worked, and the three misses were the ones needing a credential or a setting on someone else's dashboard. Nothing in the loop could tell the agent it had failed, so it said done and moved on.
I’ve tried it on simple UI tasks. Give it screenshot to work towards (or figma MCP), let it get screenshots from chrome to check its work. The existing models are surprisingly bad at it.
Earlier quoted context omitted.
What do you mean by 2?
LLMs will take shortcuts and cheat in ways that a human would realize are counterproductive.
the code the LLM writes will be read and maintained and developed further by LLMs. so it doesn't really matter what it produces as long as all the tests are green and it achieves exactly what you want it to achieve.
Damn! If a solo engineer can do this, it makes the most around OAI/Anthropic start to look pretty weak.
This was nowhere near the top submission. But even if a solo engineer could get a top kernel, you don't think that having thousands of engineers, infinite tokens, and stronger models than are available to the public would give the labs a significant edge?
Which I believe was the word intended.
In the last couple of days I wanted to try out the new definitive DeepSeek v4 releases. I gave it the repository of a semi-abandoned video compression codec and I told it to perform the usual benchmark -> profile -> verify -> research -> improve loop. I specifically chose this codec because the authors include a verifier for the bitstream to make sure you don't break stuff if you want to try your own implementation.…
I do wonder if auto-research would have reached something similar, it did take a significant amount of steering from me to get it to the point where it was working realtime.
For anyone interested the ffmpeg is at https://github.com/poizan42/jellyfin-rpi-ffmpeg and a shim for using it with stock jellyfin at https://github.com/poizan42/jellyfin-rpi-ffmpeg-shim