71–80 of 182 posts
The finding that self-generated skills provide negative benefit (-1.3pp) while curated skills give +16.2pp is the most interesting result here imo. Big discrepancy, but makes sense. Aligns with the thought that LLMs are better consumers of procedural knowledge than producers of it. +4.5pp for software engineering is suspiciously low compared to +51.9pp for healthcare. I suspect this reflects that frontier models alre…
[flagged]
Earlier quoted context omitted.
And that's why my whole schtick when it comes to agent design is that agents need to learn online, continuously, and in adapter space via some PEFT mechanism (I like soft prompts and prefix tuning), because it's really hard to ascend gradients in discrete domains like tokens.
> The model knows damn well when it's written ugly code. You can just ask it. That's not been my experience at all, what model and prompt would you use for that? Every single one I've tried is oblivious to if a design makes sense or not unless explicitly prompted for it with constraints, future ideas and so on.
Chaos Congress talk on this from a couple months ago, jump to the coding loops part: https://media.ccc.de/v/39c3-breaking-bots-cheating-at-blue-t... . The talk focuses mostly on MCPs, but we now use the same flow for Skills.
This kind of experience makes me more hesitant to take on plugin and skill repos lacking evals or equivalent proving measurable quality over what the LLM knows and harness can handle. Generally a small number of things end up mattering majorly, but they end up being pivotal to get right, and the rest is a death by a thousand cuts.
Also generating skills using top of the line model to keep using them later in cheap open weights model seems like a good use of resources.
Online sharing of skills generated in such manner also seems like a wonderful idea.
Earlier quoted context omitted.
Sincerely, perhaps you should publish on arxiv before a researcher reads it to run it and write a study. It's fairly common we notice these types of threads where one thing is being postulated and then there's comments upon comments of doer's showing what they have done.
somehow sad that some random dude on hn seems to have more brain than most scientists publishing on something about agents or prompting.
But it seems pretty surprising to me. The training corpus contains so much information and the models operate at the level of… a bright novice. It seems like there obviously ought to be more insights to derive from looking harder at aspects of the corpus.
Why isn’t this considered astonishing?
In general terms, we get these kinds of results that seem to indicate that LLMs can’t really “create” new information using inference. LLM generated skills don’t help. Training on content that was generated by LLMs causes models to collapse or something. It seems like it is accepted as really intuitive. But it seems pretty surprising to me. The training corpus contains so much information and the models operate at th…