News for hackers. Stuff that matters.
Re:GLM-5: From Vibe Coding to Agentic Engineering by vardalab on Wednesday February 11, 2026 @04:23PM (#46981234)
This is really just a meme. People don't know how to use these tools.

Here is the response from Gpt-5.2 using my default custom instructions in the mac desktop app.

OBJECTIVE: Decide whether to drive or walk to a car wash ~50 meters from home, given typical constraints (car must be present for wash).

APPROACH: Use common car-wash workflows + short-distance driving considerations (warm engine, time, parking/queue). No web sources needed (stable, local decision).

OUTPUT: • Default choice: Drive. A car wash generally requires the car on-site, and 50 meters of driving is trivial. • When walking makes sense: • You’re going to drop the car off (hand-wash/detail) and pick it up later. • You want to avoid moving the car now (ice, tight parking, you’ve been drinking, etc.) and someone else will handle the car. • Micro-guidance: • If it’s an automatic wash you stay in, drive. • If it’s detail/hand wash with a wait, drive there, then walk home (or just wait).

CONFIDENCE: 92/100 Assumptions: It’s a normal car wash that requires your car to be there; conditions are safe to drive 50 meters.

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.

Re:GLM-5: From Vibe Coding to Agentic Engineering by pegasus on Wednesday February 11, 2026 @06:05PM (#46982498)
Interesting, what were the instructions if you don't mind sharing?
Re:GLM-5: From Vibe Coding to Agentic Engineering by sph on Wednesday February 11, 2026 @05:02PM (#46981797)
"You're holding it wrong."
Re:GLM-5: From Vibe Coding to Agentic Engineering by chillfox on Wednesday February 11, 2026 @09:24PM (#46984188)
None of that stuff is necessary, they all get it right with the initial question and no further prompt if you dial the reasoning effort up.
Re:GLM-5: From Vibe Coding to Agentic Engineering by nananana9 on Thursday February 12, 2026 @08:14AM (#46988451)
> given typical constraints (car must be present for wash).

"It's very good at thinking if you do the thinking for it"