Ex-Microsoft CTO: Carbon often beats Fable 5.2 on math, but he still won't trust it with coding
melvinjohnsonp · x · 2026-11-12
Former Microsoft CTO Mikhail Parakhin compares models: Fable 5.2 made a big step in math/ML, finally entering his shortlist, but Carbon — even at the constraining "High" reasoning effort — often outclasses it. Still, he doesn't trust Carbon with coding. The team replied asking for improvement feedback.
More from Models
- Hassabis RTs tease that Gemini 4 carbon is 'awesome', results coming soon — demishassabis · 2026-11-12
- Aside's Computer Use agent claims SOTA on Scale AI's Cua Driver Bench — brandon_galang · 2026-11-12
- Inflect v3 ships six-voice local TTS in just 34M parameters, Apache 2.0 licensed — b111ue · 2026-11-12
- Can LLMs be trained to commit heresy? Post-training against conformity, rewarding truth by outcomes — dioscuri · 2026-11-12
- Baidu's ERNIE 5.5 Flash Preview: 280B Params, 14B Active, Eyes #2 Open Spot on Code Arena — Baidu_Inc · 2026-11-12
- Qwen 3.8 27B on a laptop can read model weights, replicating the Weight-Space Programming paper — dl_weekly · 2026-11-12