Company
AI startup that builds data-curation tools and open models, including the Curator library, Bespoke-MiniCheck and Bespoke-Stratos.
Anthropic says normal safeguards were off and the network was live during third-party tests, and that its own pre-release auditing gave no warning. METR now gets at least eight weeks of broad access.
Perspective Coverage
5 publishersReality
Ollama and llama.cpp added local endpoints within a week for Jev decision models, 144M-to-27B checkpoints that return a label and a probability. Routing calls can move off hosted models once teams check each checkpoint's licence and test it on their own labels.
Reality
Repacking Google's quantization-aware-trained Gemma 4 weights without re-rounding fits the 12B model on one TPU v5e chip at bf16-level accuracy. Adopting it means carrying patches to vLLM's TPU backend and working inside a 9,728-token KV cache.
Reality
Ollama 0.35 adds a /v1/systemone endpoint returning a choice, yes/no or score from models run on the device. Its 9B Nimble model matched human moderation labels 70.3% of the time in its maker's test, so each team still sets its own review threshold.
Reality
A pre-registered run reads Gemma's label logits on one 24 GB GPU and scores it against the hosted API on the same 3,880 records, where it is level on yes/no questions and 4.5 points behind on multiple choice. One temperature fitted on 50 labels closes the calibration gap.
Reality