Critique of current AI assistants lacking global context and proactivity
willdepue · x · 2026-08-22
The author criticizes current AI assistants (like Codex) for not being designed as true "super assistants." Key pain points include the lack of a single, persistent global context, and the absence of proactivity and programmatic scheduling. The experience feels like a reskinned programming tool rather than a "super app" for managing personal life and affairs.
Desired agent capabilities include:
- Automatically reading info from multiple channels (email, SMS, X) to handle scheduling;
- Auto-updating to-do lists across docs and messages;
- Possessing full personal and business context to identify people via nicknames;
- Handling calls and wait times on behalf of the user.
More from coding & agent
- Vercel AI SDK Adding Support for Claude and Codex — jasonkneen · 2026-08-22
- MCP Isn't Replacing APIs: It's Changing Who APIs Are Designed For — kush_patil · 2026-08-22
- Same Model Benchmark: Agent A (45/50) vs Agent B (43/50) with Similar Cost — donk8r · 2026-08-22
- The trust crisis of AI coding: "Claude said it was fine" — uwukko · 2026-08-22
- GitHub Repo Lists LLM Skills for Claude, Gemini, and Custom Agents — tom_doerr · 2026-08-22
- A SKILL.md that forces Cursor and Claude into Fred George's programming style — cti97 · 2026-08-22