Hacker News Reader

Comment by skissane | Hacker News Reader

> I'm not sure that Claude's "Realigned the shape of the load-bearing ownership gate to reduce the blast radius of the design contract; confirmed, not assumed" is more meaningful than "fix".

For PR/commit descriptions, I mainly use Claude Sonnet 4.5. It isn’t perfect, but it produces significantly less of this weird gibberish than 5.x models or even Opus 4.x do

I also use an iterative process in which it writes the description, I read it, and then either manually edit it or ask it to make changes

View on HN

I use Astra at Very High, and shit is still bad. It doesn't actually understand anything, so it often says things which are clearly not needed to be stated. Recently, I've learned that I have very high standards for these things. For example, "fixes" as a commit msg just is NOT acceptable and would never fly where I work.

Astra is such a mixed bag. It makes some amazing reviews and sometimes architecture suggestions that I like. But it’s also lazy and will just make up things.

hence adversarial review

I’m familiar with how those are used, but not sure what you mean in this context.

Have another model (or even another instance of the same model) review the output of the first.

Models will hallucinate. They are also quite good at spotting hallucinations in other models' output (with some more hallucinations thrown in). With a threshold for confirmation, and a few iteration loops, you arrive at a fixed point where every claim is supported.

Very high does not improve the model, fyi.

Wat, what am I paying for then?

Dario's yacht and FOMO.

Arguably, your LLM provider might be paying you, in a sense

As OpenAI's IPO troubles seem to indicate, that's an OpenAI skill issue.

Touchy OpenAI employees? :-)))

A few things, but generally more chain of thought before generating a response. So the model is tuned to think more. Given that what it outputs for this task is a summary of its thinking, tuning it to think more will just make a more verbose, less useful commit message.

Tune your model parameters to what is right for the task, not the highest you can afford.

Honestly you probably want a model that has only been trained on language and literature. Nothing from online discourse.

And even then… writing is personal expression. Here people are talking about commit messages. That’s fine but AI doing writing for anyone and I WILL NOT READ IT unless it’s literally basic tech manual.

We read to hear and engage with people’s thoughts. If someone outsources that to AI then they should be shunned.

Reply on news.ycombinator.com