@carnage4life Every accusation is a confession.

@shayman 😈🧑‍🤝‍🧑📍🏞️🏙️🧻🎱

@carnage4life Watch and see how long that lasts once this kind of thing recedes from the front pages.

@bens I think that’s largely what OpenClaw is doing—skills and integrations with agents as glue and orchestration. As amazing as the tech is, and as much as it appears to be gaining in sophistication, it’s still built on a fundamentally unpredictable foundation. Even *with* tool calling it’s perfectly capable of going off the rails at any moment. MCP calendar might help, but it might sucker you into trusting it too much.

@arroz @stroughtonsmith Kudos to Steve for boosting this rebuttal. I have been thinking about LLMs as abstraction layer for a while now. _If_ you want to apply that framework here, you have to come up with a term of art to describe nondeteminism in a layer. A leaky abstraction exposes lower-level details; a *freaky* abstraction has some level of unpredictability. I am coding with LLMs but remain clear-eyed about their inherent unreliability. A compiler or assembler they’re not. Useful? Depends.

@shayman “beverge“ 🤣

@shayman But, Steve, “AI!” <waves hands wildly>