More than the tool it’s the principles outlined in this article that are interesting if you think about what are the parts/systems/rules that would make a harness successful.

short guide to build mcp servers (sample)

See: https://github.com/jamiebeach/lisp-agent

Forge is the open-source runtime for Anthropic’s Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already operate. Write a SKILL.md. Compile to a portable, hardened agent. Deploy it anywhere containers run: Kubernetes, on-prem, air-gapped, embedded in CI, or as an A2A endpoint.

Pretty much every organization finds it easy to reward “productivity” as expressed by lines of code emitted, but the benefits of doing thorough and thoughtful design, analysis, and code review very difficult to reward. In this world, an LLM is an invaluable tool for the sociopathic ladder-climber, particularly if your legacy organization is still structuring their workflows as if the person prompting the bot is “writing” the code, and then they get to foist off the act of “reviewing” the code onto someone else. / Here, the prompter effectively externalizes the cost of the LLM’s failures but internalizes any benefits.

When a student is asked to write an essay, the teachers see the effort as both intrinsically worthwhile for the student, as well as useful as a pedagogical tool to evaluate and react to the student’s progress. The student, by contrast, sees a stumbling block designed to knock them off the path to success and into a permanent underclass.

via: https://liamoc.net/forest/2026-W26/index.xml

With reference to SNAP as an illustration

I think from this blog you may misunderestimate how absolutely giddy I am about AI. I did hacking from 2007-2014, after that my whole career has been devoted to AI. I love the progress. I’m so excited for the new LLMs, self driving cars, video generation models, and coding agents. I set up a Linux box with opencode on my local GLM-5.2 last week and wow like just saying install tmux with the geohot configuration works; the Year of the Linux Desktop is finally here!

I’m a software engineer and (reluctant) policy wonk with an interest in complex human problems, often having to do with institutions.

Met him at an event he hosted in summer 2023 while he was doing an Interact Fellowship. He stopped posting regularly to his blog that summer, and now irregularly writes a newsletter. After moving between various gigs, he’s now at Anthropic. Damn, does this company swallow up everyone.

see: https://daveguarino.substack.com/

Around 2000 I took an AI course at the University of Guelph. I don’t think I learned too much. We didn’t talk about neural networks, as far as I can remember. My end of term project was, I think, a pathfinding algorithm wearing an AI costume. There were certainly no discussions of transformers. No CUDA. No PyTorch. None of that existed.But what I remember doing a lot of was coding in Lisp - a lot of Lisp in the dark University of Guelph CIS lab.

See: https://developers.google.com/edge/litert

For later usage.

Researchers rushing to adopt AI without understanding the limitations risk committing scientific misconduct.