Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

entelligence.ai

Post reply on HN
Print view View original

141–150 of 166 posts

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#141

Post by rwiggins »

tharkun__ wrote: post #115
epolanski wrote: post #85

Earlier quoted context omitted.

I don't get the point of AI pr review. If the AI can review the pr, it can do so before the PR exists in the first place. It's a tool/skill/prompt. Just share it with the end user or encode it in the codebase in some files. It may actually be even more useful as that person will use it often and improve it or can it.

That sounds good. But it doesn't work in practice from my experience. The exact same skill in the hands of one person will have vastly different outcomes in the hands of a different person. The review skill I built myself has been shared with folks. They (say they) use it before they put up a PR. I still catch things with the same skill. That is evolving as I catch the model(s) at BSing. Even if I would re-share it a…

Have you tried running the same review skill back to back in fresh sessions? My experience has been: 1) build complicated thing with LLM, 2) run code review, 3) it finds like 8 things, 4) fix them, 5) run another code review, 6) it finds another new 8 things, rinse and repeat.

I'd guess people truly are finding things pre-review. It's just that LLM review seems to have a limit to the number of problems it can or will find. While at the same time, LLM-written code can be an almost limitless source of bugs and errors.

It has no sense of when an architecture is doomed and needs fundamental changes. Instead, it will happily continue to chase individual bugs nearly to infinity.

But, maybe your review skill is better than the ones I've tried.

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#142

Post by CharlieDigital »

therealdrag0 wrote: post #111
CharlieDigital wrote: post #81

I found Luna and even 5.4-mini to be quite good at code review provided a few things: 1. Run it in multiple cycles, only on the diff, and only emit a few findings at a time. 2. Give it a memory so each cycle, it knows the previous finding to check if it's been fixed. 3. Give it access to canonical docs that encode your human reviewer heuristics. I exposed these as tool calls so they could be tracked via telemetry. 4.…

Only on the diff? Why? I found AI reviews garbage until they stopped being only on the diff and were actually able to query real context.

Because your local agent can already see the full codebase; the code review only needs to see what's changing and evaluate the change.

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#143

Post by epolanski »

jacobgold wrote: post #94
epolanski wrote: post #89

Earlier quoted context omitted.

[flagged]

Low IQ: "Just use Claude and Codex" Midwit: "No, you see, you need a deterministic 12-stage multi-agent orchestration framework with vector embedding semantic routing, and five open weight models with custom harnesses!" Genius: "Just use Claude and Codex"

Now you only need to figure which of the 3 you really are.

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#144

Post by epolanski »

jamienicol wrote: post #101
epolanski wrote: post #83

Earlier quoted context omitted.

I'm glad I work in places where there's no such silly pointless rules like how many people need to review a PR. The PR author asks for feedback if it needs feedback, otherwise it merges it, period. I don't know why and when the world got convinced that all this bureaucracy is a "best practice", when it's just a practice, that can be good, or a waste of time depending on many factors. Like do doctors when analyzing yo…

My partner gave birth last month and the hospital had a system where every hour a second midwife would come into the room and look at all the charts and review their colleague’s work with a second, fresh pair of eyes.

Double-checking in medicine is a practice that is usually used only for specific high-risk scenarios.

Maybe yours was, albeit it sounds strange because hourly it doesn't even happen in intensive maternity-unity cares where there's a high risk for the child's health.

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#145

Post by rationalist »

oblio wrote: post #125
rationalist wrote: post #96

Earlier quoted context omitted.

Unfortunately ChatGPT just stopped allowing people to upgrade to the $200/mo subscription. I started my first paid subscription ($100/mo) last week, and now I want to upgrade and I can't :-(

Hardware capacity limitations?

They've been losing money on the $200/mo plan, so that's my guess.

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#146

Post by oscarestudillom »

SwellJoe wrote: post #6

I was using Copilot Code Review pretty religiously for a while, as I get access for free (the $10 plan) due to my Open Source work, but it recently introduced a monster of a misfeature that caused a massive increase in complexity over time, while I wasn't paying close enough attention to it. Every subsequent model saw that change and the explanation for it in the changelog and assumed it was policy rather than a mode…

[flagged]

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#149

Post by aduwah »

nonethewiser wrote: post #18

AI should be used for code review but not in CI. You should already have 2+ developers looking at most PRs. And these developers should absolutely use AI. The PR author should use AI. But what you should not do is pipe the AI output directly into the PR and tell the PR author to deal with it. That's adding noise to the PR review process. Everything it says is something the PR author needs to validate as relevant, hel…

2+ devs looking at PRs? U have never seen that in 20+ years.

Re: GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?

#150

Post by jacobgold »

micw wrote: post #132
jacobgold wrote: post #41

Earlier quoted context omitted.

Since you asked, the answer is that I built and use an agent multiplexer called Clor https://clor.com I have a $200/mo Claude subscription and a $200/mo Codex subscription, and I'm signed in to both. The Docker containers keep each session isolated, so dev servers, browser testing, etc. can work without conflicts. It includes `/ask-claude` and `/ask-codex` skills that I use very frequently to have the Claude or Codex…

How do you access Claude from the multiplexer? AFAIK Anthrophic allows the use with their official tools only. I have created wrappers for Codex ( https://github.com/micw/codex-wrapper-advanced ) and claude ( https://github.com/micw/claude-wrapper-advanced ) that uses their SDK (Codex) and the CLI (Claude) internally to align with the subscription ToS and still have a common API ;-) This way I can use both in any har…

Clor uses the official `claude` and `codex` harnesses directly, with a web interface, or via a web TUI interface.
Post reply on HN