Baseten's head of model training explains why RL extends reasoning but generalization needs domain-specific post-training
baseten · x · 2026-09-23
Connor O'Neill, Baseten's Head of Model Training, joined Dwarkesh Patel's podcast to break down horizon generalization: RL teaches models to work longer, but reasoning remains dependent on domain-specific post-training. The episode also covers what's next at the frontier of training longer-horizon models.
More from Models
- Third-party test: Claude Opus 5.5 renders finer 3D scenes but costs 13x more than GPT-6 Sol — testingcatalog · 2026-09-23
- Tester claims Claude Opus 5.5 has the best visual design output of any model tested — burny_tech · 2026-09-23
- GPT-6 Sol Codex system prompt leaked: over 294,000 characters dumped on GitHub — gaganghotra_ · 2026-09-23
- Claude 5.5 (live) keeps generating user turns, reports user — BlackHC · 2026-09-23
- Code benchmarks are mostly slop: dev calls for narrow evals per domain, not one score — almmaasoglu · 2026-09-23
- Grok 4.7 turns an envelope sketch into playable puzzle game Lightweave in minutes — luismbat · 2026-09-23