You'll need nerves of steel to work with AI agents

Re:You'll need nerves of steel to work with AI agents by anonymous908213 on Wednesday November 04, 2026 @09:20PM (#50374296)

Oh, fuck off. For one, I work in an LLM startup and work on the harness for our own models, and we're 8-digit profitable, so I'd say I know a thing or two about prompting. For two, there is no prompt that makes Luna work. It ignores your fucking prompt. The OP related how Cursor has a quotation mark tic and blatantly ignored a single constraint not to use quotation marks. Luna also has the same deficiency. You can give it a single paragraph prompt with a single sentence constraint not to do X and it will do X every time if it's in the average path for the prompt.

[ Parent | on HN ]

Re:You'll need nerves of steel to work with AI agents by slopinthebag on Wednesday November 04, 2026 @10:03PM (#50374625)

well, i and many other people have been able to make luna work. heck, people make a 27b model work locally. so if you can't manage that, and you're working on something like a harness, what else could it be?

[ Parent | on HN ]

Re:You'll need nerves of steel to work with AI agents by yubblegum on Thursday November 05, 2026 @07:51AM (#50378504)

Why are you apologizing?

Your comment could be misread as rude by an insecure ("8 digit") person who read that as a challenge to their intelligence and skills, however the reply they gave to your comment is the very defition of rude.

[ Parent | on HN ]

Re:You'll need nerves of steel to work with AI agents by iJohnDoe on Thursday November 05, 2026 @10:41AM (#50380515)

Yes, but then you’re saying Sol Max isn’t good enough. Sol is very capable.

Also, unless I’m overlooking something, you’re spending time within non-codex models, so you’re not going to get the results you’re looking for.

[ Parent | on HN ]