Hacker News Reader

I understand what you mean but Test First Development by LLM's will solve lots of problems with hallucinations and soon LLM's will be much better at coding than humans. I am always surprised that so many highly intelligent people don't understand this.

View on HN

Have you tried writing tests with an LLM?

Because I have, and it's not been the experience you're describing. The LLM hallucinated the error message it was testing for (that it had itself written 5 minutes earlier, in the file it had been given as the source to test).

I don't think this can be solved with the current methodology we're using to create these assistants. I remain arguably highly intelligent and definitely convinced that LLMs need to evolve more to surpass humans as coders.

Assuming the end goal is to serve humanity. Will a human always be better at using an LLM or will LLM’s eventually be better at using LLM’s to serve humanity?

Reply on news.ycombinator.com