Dev: live voice + tool-calling + image gen now combine into a workable 'Her'-like experience
andreisavu · x · 2026-10-16
Developer andreisavu says this past week completely reset his priors: combining live voice models, tool-calling delegation, and image generation into a cohesive, low-latency experience is now effectively possible — Her-like experiences (yes, the movie) are here, just expensive.
The takeaway from this first-hand experiment: the three capabilities have crossed the usability threshold when assembled together, with cost, not feasibility, now the main bottleneck.
More from AGI Musings
- Terence Tao: OpenAI's 300-paper dump wiped out junior research projects overnight — Hesamation · 2026-10-16
- Paper warns of "agentic flooding": AI tools are straining courts worldwide — TuhinChakr · 2026-10-16
- NYMag: China's biggest AI-course seller has 80,000 paying members and a pyramid-like system — kevinsxu · 2026-10-16
- Pedro Domingos: Recursive Self-Improvement Hasn't Happened Even Once — pmddomingos · 2026-10-16
- OpenAI's Will DePue: I'll never have to be good at digital chores again — willdepue · 2026-10-16
- China uses AI to speed fusion R&D, cutting tokamak shot prep from days to 30 minutes — teortaxesTex · 2026-10-16