@callable_com_ai · X

create your digital twin with your knowledge base for others to call (and make money?)

niklio · HN

You write 8 text completions and open models score how predictable each word was too them. Predictable => clanker. You can share results with your friends. The scoring checks every word you write against the model's logprobs. Right now I'm using Llama3.1, Deepseek v3 and Qwen3 to keep costs low. I tried to calibrate it so other models (chatgpt/claude) score 100% and interesting human responses score in the 10-30% range. Totally free, no signup

@Nathaniel148600 · X

BuildAI — Create an AI employee from your website in under a minute. And deploy it as a Widget, API, or AI phone agent.

fran-mora · HN

I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.

stan_kirdey · HN

Clark – AI assistant with own computer

@brankopetric00 · X

I've got two 😀: - automate your X presence - helps you break into DevOps