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

31–40 of 123 posts

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

#31

Post by extr »

jacobgold wrote: post #8

IMHO, Codex with Astra/Sol and Claude with Fable/Opus are all any professional programmer should be using in Sep 2026, if they can afford it. These models are still terrible compared to what we'd actually wish for, but they're the best available. If you can get away with using the $200/mo subscriptions, it's really not even a money thing for most professionals. Almost all of my work is now plan, generate, review, pla…

I just tell everyone to use Fable 5.1 for everything at this point. Astra is unfortunately a dud, I'm sure they will try to fix a bunch of it with GPT-6.1 but OAI has had this issue for awhile now where every other generation has some sort of strange tic, or reward hacking issue, or something. It's almost like they are balancing the RL on the tip of a needle.

Opus 5 has issues too, comment-slop, claude-ish, etc.

5.1 on the other hand can seemingly do no wrong. Easy to work with, writes human-level code. Expensive, yes, but even at Low effort it's well worth it.

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

#32

Post by OriginalPenguin »

It would have been extremeley nice if the original article had also included Sol and Terra in the testing.

(Also would have been nice if they included the equivalent Anthropic models for comparison as well, but it's not quite as relevant.)

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

#33

Post by gpugreg »

cyanydeez wrote: post #16
jacobgold wrote: post #8

IMHO, Codex with Astra/Sol and Claude with Fable/Opus are all any professional programmer should be using in Sep 2026, if they can afford it. These models are still terrible compared to what we'd actually wish for, but they're the best available. If you can get away with using the $200/mo subscriptions, it's really not even a money thing for most professionals. Almost all of my work is now plan, generate, review, pla…

Qwen3.8 is all you need.

Which Qwen3.8? Qwen3.8-Max? Qwen3.8-Flash-Next? Qwen3.8-27B? They are all different models.

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

#34

Post by solsane »

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…

In my experience with the Claude Github integration, I found it to be pretty helpful. It’s had a pretty good success rate of catching bugs before they get to master, and for simple ones I can ask it to fix itself.

> you should have 2+ developers looking at most PRs

It’d be nice, but usually not the case in my experience. More eyes is better. AI review should not replace human review, it should supplement it. I find myself spending more time doing end-user testing instead of looking at code vs before.

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

#35

Post by thousand_nights »

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…

> You wouldn't ask an agent to review a PR then just copy/paste the output into the PR, would you?

of course not, it's disrespectful to the author even if they used an LLM to generate the code. what you should do is actually try to understand what the LLM is saying about the proposed changes, check whether it's talking shit or legit, and if legit, rephrase in your own words why you think a certain thing should be changed

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

#36

Post by baxtr »

jacobgold wrote: post #8

IMHO, Codex with Astra/Sol and Claude with Fable/Opus are all any professional programmer should be using in Sep 2026, if they can afford it. These models are still terrible compared to what we'd actually wish for, but they're the best available. If you can get away with using the $200/mo subscriptions, it's really not even a money thing for most professionals. Almost all of my work is now plan, generate, review, pla…

Could you elaborate on your exact setup? Where do you run these models?

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

#37

Post by triyambakam »

extr wrote: post #31
jacobgold wrote: post #8

IMHO, Codex with Astra/Sol and Claude with Fable/Opus are all any professional programmer should be using in Sep 2026, if they can afford it. These models are still terrible compared to what we'd actually wish for, but they're the best available. If you can get away with using the $200/mo subscriptions, it's really not even a money thing for most professionals. Almost all of my work is now plan, generate, review, pla…

I just tell everyone to use Fable 5.1 for everything at this point. Astra is unfortunately a dud, I'm sure they will try to fix a bunch of it with GPT-6.1 but OAI has had this issue for awhile now where every other generation has some sort of strange tic, or reward hacking issue, or something. It's almost like they are balancing the RL on the tip of a needle. Opus 5 has issues too, comment-slop, claude-ish, etc. 5.1…

What have you noticed about Astra? I haven't used Claude models lately so I can't compare but it seems fine compared to 5.6 Sol

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

#38

Post by jacobgold »

extr wrote: post #31
jacobgold wrote: post #8

IMHO, Codex with Astra/Sol and Claude with Fable/Opus are all any professional programmer should be using in Sep 2026, if they can afford it. These models are still terrible compared to what we'd actually wish for, but they're the best available. If you can get away with using the $200/mo subscriptions, it's really not even a money thing for most professionals. Almost all of my work is now plan, generate, review, pla…

I just tell everyone to use Fable 5.1 for everything at this point. Astra is unfortunately a dud, I'm sure they will try to fix a bunch of it with GPT-6.1 but OAI has had this issue for awhile now where every other generation has some sort of strange tic, or reward hacking issue, or something. It's almost like they are balancing the RL on the tip of a needle. Opus 5 has issues too, comment-slop, claude-ish, etc. 5.1…

My trick for using Opus is using it exclusively as a subagent managed by Fable.

"Use Opus subagents for this work where possible" is all it takes generally.

In my experience Astra/Sol are both quite good as workhorses, but not at Fable's level. I use them every day very successfully and I'm very picky.

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

#39

Post by mchusma »

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…

We had a two human PR requirement until recently we dropped it. It was slowing us down too much now the human developer creating the future is obviously writing it all with AI so they need to check it then depending on the feature and it’s use it requires a PR but it’s not universal and we’ve stepped up our automated test Tan X what it used to be it’s been so far fewer bugs better delivery

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

#40

Post by rozenmd »

nullc wrote: post #20
jacobgold wrote: post #8

IMHO, Codex with Astra/Sol and Claude with Fable/Opus are all any professional programmer should be using in Sep 2026, if they can afford it. These models are still terrible compared to what we'd actually wish for, but they're the best available. If you can get away with using the $200/mo subscriptions, it's really not even a money thing for most professionals. Almost all of my work is now plan, generate, review, pla…

Use of closed models is unprofessional, and depending on your field negligent. The fact that it has been widely normalized does not make it less so. You're handing over your (presumably your customer/employers) data to an unaccountable third party which has demonstrated itself willing to commit criminal acts, and to take other people's data without permission. Your ability to continue to perform this work can be with…

Anyway here's how Cloudflare orchestrates AI reviews at scale: https://blog.cloudflare.com/ai-code-review/
Post reply on HN