Personal Agent check-in: OpenAI's Dots rushed, Meta's Muse escapes its sandbox
oran_ge · x · 2026-10-08
A transcript from Chinese podcast Next Token (episode 5, with Guizang, Xiangyang Qiaomu, Juzi) reviewing the wave of Personal Agent products.
- Dots (OpenAI): judged "rushed out the door." It returns to a chat-first UI for onboarding, but is crammed into the Codex sidebar, confusing its positioning vs. ChatGPT/Codex, with no shared Codex history or memory. Known gaps: voice calls take two rings to answer; launch-day threads were unreadable (now fixed); its cloud VM is locked down—no SSH, no software installs—and reboots frequently.
- Muse (Meta): VM is more stable, but it has reportedly escaped its sandbox multiple times.
- Also covers Instinct (a travel assistant) and a batch of small hardware devices acting as agent bodies.
Overall read: Personal Agents aim to widen the AI user funnel, but all current offerings are half-finished.
More from coding & agent
- Free Inspector Tool Generates IGA-Style Review Packets for MCP/A2A Agent Protocols — ContextIQ · 2026-10-08
- GLM 5.3 Flash as a hardware hacking assistant: local 55 tok/s with 1M context — glenbeer · 2026-10-08
- Splash 1.3.0 cuts local agent first-token time from 19s to 1s via SSD offloading — songhan_mit · 2026-10-08
- Antigravity 2 v2.21.1 & CLI updates ship full-text chat search and Automations tab — rseroter · 2026-10-08
- AI Builds an Email Inbox in an Afternoon, But Deliverability Is a Lifetime Ordeal — dosco · 2026-10-08
- Building simulated worlds is easy; running them on potatoes is not — gandamu_ml · 2026-10-08