←back to thread

The unreasonable effectiveness of an LLM agent loop with tool use

(sketch.dev)
435 points crawshaw | 1 comments | 15 May 25 19:33 UTC | HN request time: 0.202s | source
Show context
outworlder ◴[15 May 25 22:50 UTC] No.44000143[source]▶
> If you don't have some tool installed, it'll install it.

Terrifying. LLMs are very 'accommodating' and all they need is someone asking them to do something. This is like SQL injection, but worse.

replies(2): >>44001194 #>>44006744 #
1. nxobject ◴[16 May 25 15:38 UTC] No.44006744[source]▶
In an ideal world, this would require us as programmers to lean into our codebase reading and augmentation skills – currently underappreciated anyway as a skill to build. But when the incentives lean towards write-only code, I'm not optimistic.