Goalposts

Hacker News has set AI a lot of challenges over the years. Which ones has it met?

2023 Augustworrycue

About whether LLMs reason or only memorise, given that they hallucinate.

The biggest evidence that LLMs can’t reason is hallucinations. If it could reason it would have rejected fictional generated output that make no sense.

An LLM reliably recognizes and rejects its own fabricated, nonsensical output instead of presenting it.

Has this happened?

Yes 39 (29%)Not sure 32 (24%)No 63 (47%)

Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.