News for hackers. Stuff that matters.
Re:GLM-5: From Vibe Coding to Agentic Engineering by reliabilityguy on Wednesday February 11, 2026 @05:13PM (#46981948)
Your objective has explicit instruction that car has to be present for a wash. Quite a difference from the original phrasing where the model has to figure it out.
Re:GLM-5: From Vibe Coding to Agentic Engineering by J_cst on Wednesday February 11, 2026 @05:48PM (#46982341)
That's the answer of his LLM which has decomposed the question and built the answer following the op prompt obviously. I think you didn't get it.
Re:GLM-5: From Vibe Coding to Agentic Engineering by reliabilityguy on Wednesday February 11, 2026 @08:37PM (#46983822)
> I think you didn't get it.

I did get it, and in my view my point still stands. If I need to use special prompts to ask such a simple question, then what are we doing here? The LLMs should be able to figure out a simple contradiction in the question the same way we (humans) do.

Re:GLM-5: From Vibe Coding to Agentic Engineering by vardalab on Friday February 20, 2026 @01:41PM (#47091974)
Not really a special prompt. It's basically my custom instruction to ChatGPT, the purpose of that instruction is to disambiguate my ramblings, basically. It's pretty effective. I always use speech to text, so it's messy and this cleanup really helps.
Re:GLM-5: From Vibe Coding to Agentic Engineering by bwat49 on Wednesday February 11, 2026 @05:43PM (#46982290)
> Your objective has explicit instruction that car has to be present for a wash.

Which is exactly how you're supposed to prompt an LLM, is the fact that giving a vague prompt gives poor results really suprising?

Re:GLM-5: From Vibe Coding to Agentic Engineering by reliabilityguy on Wednesday February 11, 2026 @05:48PM (#46982344)
In this case, with such a simple task, why even bother to prompt it?

The whole idea of this question is to show that pretty often implicit assumptions are not discovered by the LLM.