Dev questions whether valuable in-context learning knowledge is lost forever
flowersslop · x · 2026-10-06
flowersslop raises a concern that the massive amounts of new knowledge produced by models through in-context learning may be getting lost forever, even when highly valuable. While labs keep improving their models, he doubts they explicitly train on the new knowledge generated at inference time.
More from Models
- Abliterated Qwen3.8-Flash GGUF quants land on Hugging Face — SC117 · 2026-10-06
- Several Western open-weight models launching this month, Reflection AI's first to rival top Chinese models — latkins · 2026-10-06
- GPT, Claude, Gemini and Grok suggest nearly identical teammate names — homogenization everywhere — sergeykarayev · 2026-10-06
- SemiAnalysis: Anthropic subscriptions offer 5x+ more value than OpenAI's — scaling01 · 2026-10-06
- Model census probes every text model daily across OpenRouter, Bedrock, Anthropic APIs — repligate · 2026-10-06
- Indie chatbot Auro V8 adds cross-session memory, claims self-iterating training loop — TheMoonMidas · 2026-10-06