Skaly_Bull's banner
Skaly_Bull's profile picture

Skaly_Bull

@Skaly__Bull • 1,175 subscribers

predicting the future on @Polymarket

Shorts

You're still typing every turn The guy who built the tool wrote the loop that types them for him "I don't prompt Claude anymore I write loops that prompt Claude" A loop takes four shapes turn-based, you close it each round goal-based - all tests pass, stop after 5 tries time-based - every 10 min, fix what's red, overnight proactive - CI breaks, agents fix it and open a PR, no human at all A judge closes the loop, not you The prompt was never the unit of work the loop is Full breakdown below

You're still typing every turn The guy who built the tool wrote the loop that types them for him "I don't prompt Claude anymore I write loops that prompt Claude" A loop takes four shapes turn-based, you close it each round goal-based - all tests pass, stop after 5 tries time-based - every 10 min, fix what's red, overnight proactive - CI breaks, agents fix it and open a PR, no human at all A judge closes the loop, not you The prompt was never the unit of work the loop is Full breakdown below

12,558 views

Everyone assumes serious AI compute means renting someone else's datacenter This is the datacenter 1,000 Mac Mini M4s on steel shelves $599 each, paid once Replacing a $14K a month cloud GPU bill It started much smaller A dev posted his Claude Code bill, $170 in 10 days The top reply got bigger than the post "I bought a Mac Mini M4, haven't paid Anthropic since" 10-30 watts a box instead of 300-500 120 GB/s unified memory, the model loads once Ollama now speaks the Anthropic Messages API So Claude Code can point at the box under your desk instead of Anthropic's servers Nobody claims these beat frontier models They claim most of your prompts never needed one The bill was never the price of intelligence It's the price of renting it for work that never needed renting Full breakdown below

Everyone assumes serious AI compute means renting someone else's datacenter This is the datacenter 1,000 Mac Mini M4s on steel shelves $599 each, paid once Replacing a $14K a month cloud GPU bill It started much smaller A dev posted his Claude Code bill, $170 in 10 days The top reply got bigger than the post "I bought a Mac Mini M4, haven't paid Anthropic since" 10-30 watts a box instead of 300-500 120 GB/s unified memory, the model loads once Ollama now speaks the Anthropic Messages API So Claude Code can point at the box under your desk instead of Anthropic's servers Nobody claims these beat frontier models They claim most of your prompts never needed one The bill was never the price of intelligence It's the price of renting it for work that never needed renting Full breakdown below

10,597 views

Videos

No more content to load