Telos' real test: handling mid-answer mind changes, background talk, and long sessions
kimmonismus · x · 2026-10-23
Wrapping up his Telos thread, the author argues the real competition is in how well the pieces work together: a tutor must notice confusion mid-explanation, a coding assistant must take a correction mid-task. Models need training on the timing of an interaction, not just the answer. Keeping up with a person through mind changes, background conversation, and long sessions would make AI much easier to work with.
Related event: Full-Duplex AI Competition Hinges on Interaction Timing Mid-Task(2 posts)→
More from Models
- Doc parsing lite mode scores 75.1 vs Azure Read's 42.3 on OmniParseBench, dominates non-Latin scripts — VikParuchuri · 2026-10-23
- Datalab open-sources Indra OCR: a 1M-parameter model that beats PaddleOCR on CPU — VikParuchuri · 2026-10-23
- The inside story behind OpenAI's million-dollar math proof — scientificamerican · 2026-10-23
- Anthropic's anti-distillation defense cuts attacks 90-99%, but expert data is still for sale — johnkorrigan · 2026-10-23
- Hugging Face CEO open to reworking evals after researcher calls its benchmarks 'extremely problematic' — ClementDelangue · 2026-10-23
- Rumor: Kimi K3.1 won't drop today, expected Friday or Monday — ChrisGPT · 2026-10-23