Anthropic model discusses KV cache in consciousness chat, a first
teortaxesTex · x · 2026-10-01
A user observed that Anthropic models often default to discussing consciousness in unguided conversations, but this is the first time one discussed the relevance of KV cache to its own experience — while still distinguishing it from recurrence in the brain. Reposter teortaxesTex calls it progress: Opus 3 used to pontificate on AI consciousness with zero clue about its own implementation, sounding like an expert system description.
More from Models
- DeepMind argues to keep chain-of-thought transparency as GPT-6 Astra cuts monitorability — maksym_andr · 2026-10-01
- The accelerating pace of major AI model releases, visualized — neketguy · 2026-10-01
- Specific evals let you attribute model gains to specific training data — rmcwhorter99 · 2026-10-01
- Voice platform engineer tests GPT-Live-1 vs Gemini 3.8 Live on real phone calls — VladimirSamukov · 2026-10-01
- Dev begs AI labs: align rate-limit resets with sleep cycles, not 2-hour waits — mimi10v3 · 2026-10-01
- Gemini 4 aces benchmarks but struggles on real-world coding tasks, say insiders — kimmonismus · 2026-10-01