News for hackers. Stuff that matters.
Re:Anthropic hits $2T in Nasdaq debut by ratelimitsteve on Thursday November 19, 2026 @02:56PM (#50565399)
"I want it to search and be fast"

vs

"I want to pre-sort during idle time so that I can effectively implement a binary search"

You can tell me either of these and get the same product. You can pick one of these and tell an LLM to do it three times and get three different products.

Re:Anthropic hits $2T in Nasdaq debut by blobbers on Thursday November 19, 2026 @04:10PM (#50566414)
And the LLM can also implement something way better than idle pre sort.

Sorry, this cope.

Re:Anthropic hits $2T in Nasdaq debut by tyg13 on Thursday November 19, 2026 @04:22PM (#50566562)
Left to its own devices, the AI may choose to implement things efficiently and correctly, or it may choose to implement things inefficiently and incorrectly. Without clear guidance, acceptance criteria, and hand-holding, it will make assumptions that are wrong, and as the demands of the product grow, it will continue to build off of those wrong assumptions. This is my experience with Gemini, Claude, GPT -- any of the models. They need guidance or they will build crap.

Now, this may be acceptable (tons of businesses are built on broken products), but what is absolutely cope is this moronic idea that the LLM is always smarter than the average engineer and will magically produce the most efficient and correct solution.

Re:Anthropic hits $2T in Nasdaq debut by ratelimitsteve on Thursday November 19, 2026 @04:28PM (#50566640)
> Without clear guidance, acceptance criteria, and hand-holding, it will make assumptions that are wrong

Yeah but the person you're replying to isn't gonna see that because they already made several assumptions about the problem I put in front of them