HeyGen Founder Joshua Xu: Agents Should Explain with Video, Not Text Reports
toolstelegraph · x · 2026-10-21
HeyGen founder Joshua Xu argues the debate over reviewing hundreds of agent-generated videos misses the point: output format should match task. Text remains best when the agent needs a decision or feedback, but for explanations, video can replace an hour of reading docs — he cites using an agent to make a video explaining how JEV works. Agents' interface is heading beyond text into multimodal output.
More from AGI Musings
- Fields medallist says OpenAI's 700+ AI math manuscripts left him in tears — miniapeur · 2026-10-21
- DeepMind robotics head joins Berkeley, Boston Dynamics panel on humanoid motion & perception — VLA vs agentic coding debate — chris_j_paxton · 2026-10-21
- Anthropic taps law firms to teach AI agents how to negotiate deals — jkubicki · 2026-10-21
- komorama's weekly: the AI Peter Principle—first 90% never faster, second 90% never slower — lennysan · 2026-10-21
- Multi-agent swarm architectures are being discovered, not designed — shared state emerges as the norm — JensHonack · 2026-10-21
- a16z talks health AI with OpenAI's Karan Singhal: 300M people weekly ask ChatGPT health questions — a16z · 2026-10-21