Microsoft Hid BitNet Training Code for Over a Year, Dev Shares It
QuixiAI · x · 2026-07-07
Developer QuixiAI criticized Microsoft for hiding the training code for BitNet (a 1-bit neural network architecture) for over a year and directly shared links to the relevant code. BitNet has garnered significant academic interest due to its extremely low bit-width, and the lack of training code had previously hindered community reproduction and further research.
Related event: Developer Replicates BitNet Training Code on MacBook(2 posts)→
More from Models
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11