On: OpenAI O3 breakthrough high score on ARC-AGI-PUB

[lottin]

But how do you know it's given you the correct answer? Just because the code appears to work it doesn't mean it's correct.

[adwn → lottin]

But how do I know if my hand-written jq query is the correct solution? Just because the query appears to work it doesn't mean it's correct.

[lottin → adwn]

Because I understand the process that I have followed to get to the solution.

[ogogmad → lottin]

It can explain its solution. Point to relevant docs as well.

[gf000 → ogogmad]

It can also very convincingly explain a non-solution pointing to either real or hallucinated docs.

[ogogmad → gf000]

You need to look at the docs.

[freehorse → ogogmad]

Omg this is how llms used to trick me inventing out all these apis.

[ogogmad → freehorse]

Look at the docs it links to.