korrents

Simon Willison

@simon-willison · 7 positions · 0 changes of mind

Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.

Simon Willison did not write this page. We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it.

  1. 1 Sept 2026

    The pelican-drawing benchmark's correlation with genuine model capability has weakened since 2025.

    its connection to how good the models were at other tasks didn’t seem to hold as strongly as it did back in 2025

    Claude Fable 5.1 made me a really nice animated pelicansimonwillison.net

  2. 3 weeks earlier
  3. 10 Aug 2026

    Claude Haiku hallucinates badly enough that its use inside Claude Code's WebFetch tool is a hallucination risk on every fetched URL.

    Claude Haiku is my current least favorite model - it hallucinates wildly, and is out-performed now by other similarly priced models like GPT-5.6-Luna Even worse: it seems to still be used by the Claude Code WebFetch tool, which means hallucination risk any time you fetch a URL!

    @simonw on Xx.com

  4. 2 days earlier
  5. 8 Aug 2026

    Auto-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

    coding agents

  6. 1 day earlier
  7. 7 Aug 2026

    Giving consumer-facing models and API models separate brand names is needlessly confusing.

    I really do think that having separate brand names for the consumer-facing models and the API models is needlessly confusing

    @simonw on Xx.com

  8. 7 months earlier
  9. 31 Dec 2025

    MCP 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

    MCPcoding agents

  10. 31 Dec 2025

    Running 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

    coding agents

  11. 12 months earlier
  12. 31 Dec 2024

    Concerns about the energy cost of an individual LLM prompt are no longer credible, though the environmental impact of the AI datacenter buildout remains a real worry.

    There’s still plenty to worry about with respect to the environmental impact of the great AI datacenter buildout, but a lot of the concerns over the energy cost of individual prompts are no longer credible.

    Things we learned about LLMs in 2024simonwillison.net