This is the PR with the changes in case people missed it: https://github.com/mie... | Hacker News

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

		thanhhaimai 3 months ago \| parent \| context \| favorite \| on: Tau² benchmark: How a prompt rewrite boosted GPT-5... This is the PR with the changes in case people missed it: https://github.com/mieciu/tau2-bench/pull/1/files

nitwit005 3 months ago | [–]

That seems so strongly directed, that it feels like an attempt to reproduce a classic chat bot.

blndrt 3 months ago | | [–]

Thanks! I also updated the post with the link on the website.

catlifeonmars 3 months ago | [–]

Can one customer get the model to return the bill details for another customer?

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