About whether LLMs can really learn and improve like human developers.
Has this happened?
Yes 10 (8%)Not sure 22 (18%)No 90 (74%)
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
Hacker News has set AI a lot of challenges over the years. Which ones has it met?
About whether LLMs can really learn and improve like human developers.
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
I think you neatly summarise why the current pre-trained LLM paradigm is a dead end. If these models were really capable of artificial reasoning and learning, they wouldn’t need more training data at all. If they could learn like a human junior does, and actually progress to being a senior, then I really could believe that we’ll all be out of a job—but they just do not.