korrents

coding agents

What people on korrents have said about coding agents, newest first — 6 positions from 4 people.

  1. TL

    25 Aug 2026

    Tobias Lütke quoted

    HoldsCoding agents should read the shared AGENTS.md convention; insisting on a tool-specific CLAUDE.md creates split-brain problems across a team.

    I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc. Insisting on only reading CLAUDE.md sometimes leads to split brain problems when different team members use different tools. Just unnecessary.

    ↗@tobi on Xx.com

  2. 6 days earlier
  3. TP

    19 Aug 2026

    Thomas Ptacek quoted

    HoldsCoding agents make every plugin interface you ever blew off trivially usable, which is a large productivity win.

    I can't say enough how excellent a coding agent is at customizing Chrome with extensions. A huge productivity win. Every plugin interface you've ever blown off is now trivially usable.

    ↗@tqbf on Xx.com

  4. 11 days earlier
  5. SW

    8 Aug 2026

    Simon Willison quoted

    HoldsAuto-mode does not yet convincingly fix prompt-injection risk for coding agents.

    I REALLY want to believe that this fixes prompt injection risks for coding agents, but I'm just not there yet

    ↗@simonw on Xx.com

  6. 2 months earlier
  7. DH

    1 Jun 2026

    David Heinemeier Hansson quoted

    HoldsAI coding agents advance open source's founding goal by letting far more people modify software, so barring AI-assisted contributions protects a guild rather than the mission.

    Agents aren't perfect, slop is a problem, but giving more people the power to enjoy malleable computers is undoubtedly a huge win for the founding vision of open source.

    ↗Let the agents democratize open sourceworld.hey.com

  8. 5 months earlier
  9. SW

    31 Dec 2025

    Simon Willison quoted

    HoldsMCP may turn out to be a one-year wonder, because coding agents that can run arbitrary shell commands make Bash the best general-purpose tool interface.

    The reason I think MCP may be a one-year wonder is the stratospheric growth of coding agents. It appears that the best possible tool for any situation is Bash—if your agent can run arbitrary shell commands, it can do anything that can be done by typing commands into a terminal.

    ↗2025: The year in LLMssimonwillison.net

  11. SW

    31 Dec 2025

    Simon Willison quoted

    HoldsRunning coding agents without approval prompts is a normalization-of-deviance risk: the fact that it has not caused a disaster yet is itself the problem.

    I run in YOLO mode all the time, despite being deeply aware of the risks involved. It hasn’t burned me yet... ... and that’s the problem.

    ↗2025: The year in LLMssimonwillison.net