Hacker News Reader

Comment by wonnage | Hacker News Reader

That works for well trod paths, e.g “fix ci” works exceedingly well. “why app slow” obviously doesn’t work because the task is underspecified. But in order to properly specify you either need an experienced engineer who knows how to narrow the problem domain, or you have to provide some template instructions/output formats (e.g, skills) which will invariably never fit the problem perfectly

View on HN

> . “why app slow” obviously doesn’t work because the task is underspecified.

Not always. In my case LLM goes to grafana mcp, pulls metrics/traces/cpu profiles. Figures out what is slow and proposes a solution.

I wouldn't agree. Sota models can do self-directed sampling, profiling, benchmarking, read call trees, etc. to give you a report of the app's bottlenecks and then recommend solutions that can be vetted.

I do this constantly.

As the upstream comment points you, you don't need to specify. Sota models are that good. And by being overprescriptive you can accidentally shut off branches that they would've taken, downgrading the quality of their work.

> “why app slow” obviously doesn’t work because the task is underspecified

Definitely not true and like everyone else is saying, shows how people still underestimate these models.

I have been working on a simple vite + react app lately and commonly ask Gemini/Antigravity to just "improve speeds", "x is running slow, check it out" and have no complaints.

Reply on news.ycombinator.com