Matching the model to the job
Technique
Choose models by what each job needs instead of using one model for everything. Weigh strengths like design taste, review depth or speed, and judge cost by the whole task, not the price per token.
Theo's current stance
Theo now splits work across models by strength. For games, OpenAI models make better images and 3D assets, while Anthropic models make the game more pleasant to play. He is trying Astra as play tester and Fable as builder.
Try it
- Check which model your agent is pinned to for each project.
- Compare models on total cost per finished task, and decide what quality the job really needs before paying for the top model.
- Give visual assets to an OpenAI model and building and polish to an Anthropic model.
- Try one model as tester and another as builder, and compare.
First seen
26:02
very spiky and weird. I think Opus is probably the right default for the vast majority of stuff. But you should not be as scared to reach to Fable for front end still, especially when you're doing like a marketing page or some big design overhaul. I still think Fable is a
Every mention
19:58
graphically, it's great. Once again, if you want the absolute best, it's probably a combination of using an OpenAI model for asset gen and 3D asset creation and then using anthropic models to actually make the game pleasant to play because uh yeah, open II still not
32:18
combo. Still figuring out what goes where exactly. It does seem like 62 Astra is really good at play testing, so I might have it be the play tester and then keep using Fable as the implement.
7:14
what. At that point, optimizing for the cheapest model for the input token read is probably the right call. If you're doing agentic dev work, things like caching, reliability, and token efficiency suddenly matter a hell of a lot more. We're also not looking at this
7:58
massively. Like if you're happy with a 45 to a 46 as the score here, your cost will be 82 cents per task. Where if you want to bump up into the 50s, suddenly it's $3.26. So for just a few more points, you're spending three times more money. I still
24:44
machines. This is now going to be 61 Soul high fast because I think it's a really good balance of speed, capability, and performance in general when I'm trying to do tasks where I'm managing the machines in my network. Not for writing code and deploying, but for working on
26:02
very spiky and weird. I think Opus is probably the right default for the vast majority of stuff. But you should not be as scared to reach to Fable for front end still, especially when you're doing like a marketing page or some big design overhaul. I still think Fable is a
22:23
planning on using this model to very thoroughly review code and find every single thing wrong with it or suggest sweeping improvements to your codebase, might not be as strong at those things as OpenAI's Frontier is. But, I'm going
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.