Day 2 of #AILent: writing a small Express-based API, a lot of ideas actually came to mind when letting my mind flow freely, instead of using a plan mode to iterate (why use Apigee, Express has enough middleware for rate limiting and auth already), can I export the entire database to a JSON file and use HTTP Range Headers to seek through it?

The hard part has been finding information, websearch is terrible, I'm spending 5-10 seconds proving to Cloudflare that yes, I AM HUMAN. Luckily Express is heavily documented and has tonnes of QA on Stackoverflow.

I did really miss looking at my kitted out neovim config, which I was kinda robbed from with Claude Code.

Pausing #AI use made me realise that the human desire to create intelligence in the image of ourselves might be doing more harm than good.

Anthropomorphisining AI makes us encode the same biases, hierarchies and heuristics that humans use due to either constraints on cognition, communication or specialisation.

Who says AIs need to have specialisation, there's nothing intrinsically specialised about frontier models? Who says AI has to follow workflows we follow due to our fleshly constraints?

Most breakthrough happended by cutting out human assumptions: AlphaGo's self-play leading to the infamous Move 37 v. DeepBlue's opening book of more than 4,000 positions and 700,000 grandmaster games.

#AILent #LLM #FrontierModels

Day 1 of #AILent : cancelled Claude Max, uninstalled Claude Code (we won't be needing them for the next 40 days).

Wrote a small Nix package, vim motions feeling rusty.

Also feels much harder to think how to structure a piece of code. Definitely feeling the atrophy

#AI #NoAI