Stealing Reasoning Traces from Proprietary LLM APIs
Paper • 2608.09867 • Published • 122
Théophile Lafargue
ox-ox
AI & ML interests
Founder & CTO, Sub Specie Aeternitatis — sovereign LLM inference over 2G/SMS, LoRa & satellite.
Apple Silicon: MLX, GGUF, quantization, speculative decoding, KV-cache. Patent FR2511116.
Recent Activity
liked a model about 5 hours ago
Cloudflare/clef liked a Space about 6 hours ago
FineEnvs/multi-harness-rl liked a model 26 days ago
ivanfioravanti/Qwen3.8-Flash-Next-DS4-Q4Organizations
upvoted a paper about 2 months ago
upvoted a collection 6 months ago
upvoted a changelog 6 months ago
Hugging Face Changelog
Protected Spaces with Public URLs
• 130
upvoted a collection 7 months ago
upvoted a collection 8 months ago
upvoted an article 9 months ago
Article
New in llama.cpp: Anthropic Messages API
ggml-org
• • 48 upvoted a collection 9 months ago
upvoted a collection 11 months ago
upvoted a collection about 1 year ago
upvoted a changelog about 1 year ago
Hugging Face Changelog
Introducing HF Jobs: Run scalable compute jobs on Hugging Face
• 206
upvoted a collection about 1 year ago
upvoted an article about 1 year ago
Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf
• • 799 upvoted an article over 1 year ago
Article
SmolVLM Grows Smaller – Introducing the 256M & 500M Models!
- +1
andito, mfarre, merve
• • 196