Two weeks. One laptop. Free GPUs. About $5. Every number below is from a real run. Here is a...
Qwen 0.6B model trained to summarize conversations learned selective memory through copy-compress-choose phases, achieving 81% accuracy. Demonstrates tiny models can develop memory selection expected from much larger systems, enabling efficient local inference and reducing infrastructure costs.
Two weeks. One laptop. Free GPUs. About $5. Every number below is from a real run.
Here is a notebook a tiny model wrote for me.
It had six chats to remember and a 350-character budget. This is what the next model actually saw — the rest got cut off:
- my neighbor's dog Kabir kept barking all night.
- watched an old western last night, decent.
AI wrote the code in 30 seconds Three lines A simple function I prompted it generated I copied It...
Last week I couldn't shake an idea: what if I had an AI that knew everything I know? Not ChatGPT —...
I left an AI coding agent running for one day. Then I read the invoice. $788. In about 13...
Most "AI agent" demos die at the same place: a tweet, a screenshot, a five-minute video. Then the...
A practical log of building a long-lived Telegram AI agent — caching, providers, routing, memory, latency. No benchmarks. Just…
Introduction I recently booted up an offline card game I used to love — and couldn't clear...
