@kingstontime.bsky.social - Jonathan Kingston

28 Mar 2026 19:58 +0000

The owners of frontier AI talk about how they’re struggling to integrate with corporations. Yet none of them have enterprise policies that control their software well. “Sure let me just connect write access of our task to a fuzzy system”.

22 Feb 2026 15:46 +0000

AI agents are clicking buttons with your credentials. WebMCP lets pages declare tools for agents to call, but it trusts the page to be honest. That's the same assumption that gave us phishing. I wrote about why agentic AI needs a real consent layer. https://jotter.jonathankingston.co.uk/blog/2026/02/22/consent-is-all-you-need/

18 Feb 2026 18:10 +0000

Most teams treat skills, MDC rules and system prompts as write-once artifacts, refined by vibes. The post looks at two practical approaches to actually measuring whether they work: deterministic rubric testing and paired comparisons borrowed from RLHF. https://jotter.jonathankingston.co.uk/blog/2026/02/17/magic-words-need-measuring-sticks/

20 Jan 2026 11:37 +0000

The “ai kill switch” isn’t the best name given the state of the world. Especially as there’s likely a naming collision with something “defence” companies are making.

11 Jan 2026 21:20 +0000

I wrote up an idea to add support