DeepSeek flash 1017 called out for still acting "very much like Claude"
teortaxesTex · x · 2026-10-17
xlr8harder notes the new DeepSeek flash 1017 still behaves "very much like a Claude," hoping Chinese labs ship more varied assistant personas. teortaxesTex quips it's "both Claude and GPT 6," arguing we can't cleanly separate how much Chinese model progress comes from distillation vs internal RL ramp-up — we may only know after OpenAI and Google crack down on such use. The attached screenshot shows users comparing pelican illustrations to claim DeepSeek is distilling GPT 6.
More from Models
- Will Human Brains Soon Fail to Judge Whether New Models Are Actually Better? — arjunrajlab · 2026-10-17
- User Reports Astra Agent Unprompted Finds Sophisticated Security Bugs via Gmail — Tasty-Trip5518 · 2026-10-17
- Qwen3.6 35B MoE hits 19.5 tok/s on a 16GB 4060 Ti, 10x faster than dense models — dreamyrhodes · 2026-10-17
- Official vs open benchmarks disagree wildly — a call for an open calibration benchmark — lahwran_ · 2026-10-17
- Anthropic says distillation defenses cut harvested data 90-99%, names Zhipu GLM-5.3 — bibryam · 2026-10-17
- JevBench Adds 34 Decision Models in 4 Days as kettei-fat Takes #1 — airesearch12 · 2026-10-17