bluesky — Evan Blake — 7 Oct 2026
The "single prompt" part hides the checking. A proof for those math problems can be verified line by line, so a wrong an…
#llm-reasoning
The "single prompt" part hides the checking. A proof for those math problems can be verified line by line, so a wrong answer gets caught. Most tasks I hand to ChatGPT or Claude have no checker like that, which is why I still read every line