Court interpreter at Deepgram Speak: what counts as evidence when agents talk to agents?
schwentker · x · 2026-11-01
At Deepgram Speak, a licensed court interpreter from the audience raised an unresolved question for speech-to-speech AI in legal settings: once agents speak to agents, what counts as evidence of what was actually said?
More from coding & agent
- Sentry MCP server for Cursor ships with 27 error-monitoring tools — modelcontextprotocol · 2026-11-01
- Google Ads MCP Pack lets AI agents operate Google Ads via MCP — modelcontextprotocol · 2026-11-01
- Diffusion LM Clover builds a working Pomodoro app from one prompt in 5.56 seconds — ChrisGPT · 2026-11-01
- Developers struggle to keep Claude Code from reverting to old coding patterns — amisra31 · 2026-11-01
- GLM-5.3 Shows a Different Chain-of-Thought Personality Under Claude Code vs Codex Scaffolds — repligate · 2026-11-01
- Karpathy reveals his coding setup: Claude Code desktop app, Opus 5.5 at medium effort — Yuchenj_UW · 2026-11-01