rasbt pushes back on MIT CSAIL paper claiming harnesses won't be obsolete
rasbt · x · 2026-11-22
A new MIT CSAIL paper argues stronger LLMs will NOT make harnesses obsolete: harnesses compose model capabilities to generalize across longer, deeper and more strategic tasks while enabling more data-efficient training. Sebastian Raschka counters that the root LLM still needs a harness to make subcalls — a core open question for the long-term value of agent frameworks.
More from coding & agent
- Gemini Neon builds an interactive USL lock-contention UI exposing a testing blind spot — tianyin_xu · 2026-11-22
- Claude Code can now be approved from your iPhone, ending the 14-minute permission wait — BLCNYY · 2026-11-22
- AMD and PyTorch ship a playbook to run GPT-OSS-20B inference locally with ROCm — PyTorch · 2026-11-22
- Keep context out of the prompt: RLM-27B beats base Qwen3-27B by 26.9% — dosco · 2026-11-22
- instant_record compiles Rails ActiveRecord models to WASM for instant, offline browser apps — danshipper · 2026-11-22
- Client demoing your AI build internally without prompting is the real adoption signal — aryanXmahajan · 2026-11-22