Teknium: Train on Multiple Harnesses to Keep Models Portable Across Evals
Teknium · x · 2026-09-07
Replying to concerns that models are increasingly hard to separate from their native harness, Teknium argues the fix is simply training on multiple harnesses — noting Chinese models, Fable, and even Muse all behave well across harnesses.
Related event: OpenAI Models Criticized for Overfitting to Native Harness(3 posts)→
More from Models
- Dev benchmarking skills finds Sol at 17 tok/s vs Opus 5.5 at 70 tok/s — lucasmeijer · 2026-10-26
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26