Cross-model review: another lab's model checks the work
Technique
One model writes the code and a model from a different lab reviews it before you merge. The reviewer brings a different view, like a friend at another company, and catches problems the writer missed. They can go back and forth until both agree.
Theo's current stance
Theo keeps Opus as his main coder and uses OpenAI's GPT-6.1 Sol for reviews because it is more thorough; its loop caught three real security holes. He calls the Sol loop an earlier, simpler version of Council.
Try it
- After your main agent writes a change, hand it to a different, more nitpicky model to review.
- Tell them to go back and forth with minimal fixes until both agree the change is good.
- Set a round budget, e.g. Theo's three rounds, five only for security or data-loss risks.
- Expect some noise in the findings and triage what matters.
First seen
25:17
I do still find that Claude isn't the best at computer use compared to Codex, especially on macOS. So, if you have a Codex sub, even like a cheaper one, set up and on your computer, you can have Fable call Codex to do the computer use stuff to verify…
Every mention
12:01
…very minimal version of this where I found that GPT-61 Sol was incredibly thorough at reviews. It would tear every little thing to pieces. So I'd have Opis make changes and call a delegate with Soul to review the changes and give feedback and then they go back and forth until both agree the changes are good.
15:18
Soul loop was super helpful when I was building this and it caught three real security holes.
5:16
The TLDR is that you should use GPT-4 Soul to review your code in a loop. Make the most minimal possible changes to appease the Soul reviewers. Be careful of scope creep and don't be scared to push back.
6:22
I found that Opus 5.5 is a much better collaborator, overall smarter, writes way better code, just more pleasant to work with in general. GPT-61 Soul is more thorough, though. It really does feel like the Rottweiler. It grabs onto the problem and doesn't let go, and I really like using it for…
38:45
Soul as an auditor. I have set up skills for all my agents where they use Opus as the thing that does the coding, and then they consult with Soul for opinions before they put up the PR, and I'm landing code so much faster simply because Soul catches all the dumb things Opus might miss.
31:49
…if you can do both, I personally get a ton of value from having Claude spin up sole sub-agents to review its work because Open AI models I've still found are a bit more thorough with their analysis and will find things deeper than Anthropic models tend to.
32:06
…a wield and the vast majority of my Codex usage is either me using it to like do my email and computer you or it's coming from Claude calling Codex via T3 code in order to review Claude's work. And for those tasks, I have found it to be incredible and I get plenty of…
27:51
I like using them in tandem because I find Soul to be way better at reviewing and digging into the details, but I find Opus a more pleasant collaborator and significantly better at actually implementing code without getting blocked constantly throughout…
29:47
…config because I already have it set up so that I can use Soul inside of Claude code because I want to make sure Opus knows this is the model to have review its work and investigate the things going on in the code base.
22:45
They just really dig into the details and won't let go of the thing until it's confident it's found everything. It'll report more stuff that doesn't matter, but it will occasionally find things that do matter…
23:00
So, personally, when I have Opus code being reviewed, I don't want just Opus reviewing it. I would like for Astra or even like Soul to give it a…
25:17
I do still find that Claude isn't the best at computer use compared to Codex, especially on macOS. So, if you have a Codex sub, even like a cheaper one, set up and on your computer, you can have Fable call Codex to do the computer use stuff to verify…
25:44
…recommend and how they review things, I found Astra to be a slightly better reviewer than Fable. But, obviously Fable's a much better writer of code than Astra. As such, I often will have Fable just go ask Astra to give it feedback on some changes or to go test the changes it made in order to verify…
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.