Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it
AI Hot frames this as an actionable signal for AI agents, AI coding, or LLM release decisions — not a general news recap.
What happened
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. Wi
Why it matters
This AIitem is part of today's AI agents / AI coding / LLM releases signal feed. It is worth checking because it may affect product decisions, developer workflows, model choices, market timing, or policy risk. Open the original source for full context and verification.
Who should care
builders, founders, and product people who need a quick read on today’s AI shifts.
What to do next
Use this as a AI decision signal: compare it with your agent workflow, coding stack, model watchlist, or launch roadmap; then save or share it if it changes a build, buy, or positioning decision.
Original sources
AI Hot summarizes public source material and links back for verification. Use the original source for full reporting, quotes, and context.