Hacker News Reader

Comment by DeathArrow | Hacker News Reader

I don't really think having an agent fleet is a much better solution than having a single agent.

We would like to think that having 10 agents working on the same task will improve the chances of success 10x.

But I would argue that some classes of problems are hard for LLMs and where one agent will fail, 10 agents or 100 agents will fail too.

As an easy example I suggest leetcode hard problems.

View on HN

I'm authoring a self-compiling compiler with custom lexical tokens via LLM. I'm almost at stage 2, and approximately 50 "stdlib" concerns have specifications authored for them.

The idea of doing them individually in the IDE is very unappealing. Now that the object system, ast, lexer, parser, and garbage collection have stabilized, the codebase is at a point where fanning out agents makes sense.

As stage 3 nears, it won't make sense to fan out until the fundamentals are ready again/stabilised, but at that point, I'll need to fan out again.

https://x.com/GeoffreyHuntley/status/1911031587028042185

We need The Mythical Man-Month: LLM version book.

The fleet approach can work well particularly because: 1) different models are trained differently, even though using mostly same data (think someone who studied SWE at MIT, vs one who studied at Harvard), 2) different agents can be given different prompts, which specializes their focus (think coder vs reviewer), and 3) the context window content influences the result (think someone who's seen the history of implementation attempts, vs one seeing a problem for the first time). Put those traits in various combinations and the results will be very different from a single agent.

Nit: it doesn't 10x the chance of success, it (the chance of failure)^10.

neither, probably

Reply on news.ycombinator.com