AI · Video
Stop Picking the Wrong Model: Opus 5.5 and Fable 5.2 Are All You Need for Coding
Theo - t3.gg ·
At a glance
Developer YouTuber Theo argues that Anthropic's Opus 5.5 and Fable 5.2 are the only AI models worth using for coding, and explains from his own experience when to pick each. He says a Claude subscription gets far more work done for the money than other models, even on a tight budget, that there is little reason to pick Sonnet 5.5 directly, and that Haiku 5.5 should find patterns in large amounts of data rather than write code.
Key points
- Opus 5.5 is like a teacher's pet: it follows instructions closely and double- and triple-checks its work, so it rarely misses things, but it applies every piece of feedback and lets features and code bloat.
- Fable 5.2 questions the premise and finds solutions others would not think of, but it sometimes brushes off small instructions and details.
- Opus is enough for work you can verify, such as moving a program to another language; for creative work with no right answer, or to finish a task Opus keeps circling, he recommends Fable.
- Both run at almost the same speed, about 112 and 106 tokens per second, and for Opus he finds the high effort level best while advising against max, which makes the model overthink even simple tasks.
Why it matters
These are concrete criteria from a developer who has compared both models in real work, useful when choosing a model and effort level in a coding agent.
Original source
Stop Picking The Wrong Model
Theo - t3.gg · Nov 13, 11:34 KST
Watch on YouTube ↗AI summarized the video content. Check the original for accuracy. Copyright belongs to Theo - t3.gg.
More from this field
- Google Drops Search Button and Adds AI Sidebar to Its Search Homepage
Google has officially rolled out a redesigned desktop search homepage after a successful test. The Google Search button next to the search bar is gone, and a row of AI buttons now sits under the bar. Logged-in users also get a sidebar showing their recent AI Mode conversations.
Ars Technica · Nov 21, 06:58 KST - Meta Rethinks 2030 Net-Zero Goal as AI Data Center Emissions Hit Record High
Meta's 2026 sustainability report said the company is re-evaluating its 2030 net-zero goal. Its emissions rose about 40 percent from 2024 to 2025, the largest jump among the big US tech companies.
Ars Technica · Nov 21, 06:47 KST - Anthropic Mathematician Says Claude Helped Crack the Riemann Hypothesis
Levent Alpöge, a mathematician at Anthropic, says he has proved the Riemann hypothesis with help from Claude, Anthropic's AI system. Instead of a regular math paper, he posted a four-page note and linked to computer code that he says checks the result. The claim still needs to be verified.
The New York Times · Nov 21, 06:47 KST - Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST