News for hackers. Stuff that matters.
Re:Claude Sonnet 4 now supports 1M tokens of context by jacobr1 on Tuesday August 12, 2025 @03:51PM (#44881090)
Beyond code-gen I think some techniques are very underutilized. One can generate tests, generate docs, explain things line by line. Explicitly explaining alternative approaches and tradeoffs is helpful too. While, as with everything in this space, there are imperfection, I find a ton of value in looking beyond the code into thinking through the use cases, alternative approaches and different ways to structure the same thing.
Re:Claude Sonnet 4 now supports 1M tokens of context by pornel on Tuesday August 12, 2025 @04:09PM (#44881242)
I've wasted time debugging phantom issues due to LLM-generated tests that were misusing an API.

Brainstorming/explanations can be helpful, but also watch out for Gell-Mann amnesia. It's annoying that LLMs always sound smart whether they are saying something smart or not.

Re:Claude Sonnet 4 now supports 1M tokens of context by Miraste on Tuesday August 12, 2025 @05:16PM (#44881891)
Yes, you can't use any of the heuristics you develop for human writing to decide if the LLM is saying something stupid, because its best insights and its worst hallucinations all have the same formatting, diction, and style. Instead, you need to engage your frontal cortex and rationally evaluate every single piece of information it presents, and that's tiring.
Re:Claude Sonnet 4 now supports 1M tokens of context by valenterry on Wednesday August 13, 2025 @01:06AM (#44884802)
It's like listening to a politician or lawyer, who might talk absolute bullshit in the most persuading words. =)