This isn’t really how it works anymore. Agents rely heavily on tool use and the ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

emp17344 70 days ago | parent | context | favorite | on: GPT-5.6

This isn’t really how it works anymore. Agents rely heavily on tool use and the agentic harness to perform tasks. Pre-training is no longer very effective.

HDThoreaun 70 days ago [–]

I thought models werent allowed tools on arc-agi?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact