Viewing profile — xianshou

A lovely example of a study that is both obviously true and misses the point. Music with lyrics directly interferes with any task that has a verbal component, and the worse you are…

Even as someone extremely firmly on the other side of the AI debate, I must appreciate the craft. Now, to give Claude the steganogravy skill...

From the file: "Answer is always line 1. Reasoning comes after, never before." LLMs are autoregressive (filling in the completion of what came before), so you'd better have thinkin…

I appreciate not having to read this guy again.

Great work! Why no benchmarks though?

Nice! 5 bucks says you can swap this in for your average software kanban and it does a better job.

Safer than clawdbot/moltbot, I'll bet.

Incidentally, Chroma also produced the single best study on long-context degradation that I've come across: https://research.trychroma.com/context-rot Before that, I cited nolima (…

Came to point out that this is transparently LLM-authored, was not disappointed. The signs: - neatly formatted lists with cute bolded titles (lower-casing this one just for that) -…

I initially read the title as "My 2.5 year old can write Space Invaders in JavaScript now (GLM-4.5 Air)." Though I suppose, given a few years, that may also be true!

Rug pulls from foundation labs are one thing, and I agree with the dangers of relying on future breakthroughs, but the open-source state of the art is already pretty amazing. Given…

In many of their key examples, it would also be unclear to a human what data is missing: "Rage, rage against the dying of the light. Wild men who caught and sang the sun in flight,…

The self-edit approach is clever - using RL to optimize how models restructure information for their own learning. The key insight is that different representations work better for…

The key insight here is that DGM solves the Gödel Machine's impossibility problem by replacing mathematical proof with empirical validation - essentially admitting that predicting …

AI is, currently, coming not for the coders who made it but for the coders who didn't contribute to or ignored it. The foundation labs are all quite committed to recursive self-imp…

Duplicate of https://news.ycombinator.com/item?id=44040883

Both Google and Microsoft have sensibly decided to focus on low-level, junior automation first rather than bespoke end-to-end systems. Not exactly breadth over depth, but rather re…

Amusingly, about 90% of my rat's-nest problems with Sonnet 3.7 are solved by simply appending a few words to the end of the prompt: "write minimum code required" It's not even that…

Calling it now - RL finally "just works" for any domain where answers are easily verifiable. Verifiability was always a prerequisite, but the difference from prior generations (not…