so deepseek 4 pro researched and implemented feature today (pi-dev & openrouter), total cost is 5 cents. crazy times. there is no way 1T valuation for anthropic and openai is justified.
@vohvohh look for something advanced like pdtr or kinesiology. your knee pain is consequence, you need fix the root cause. even if you fix your knee with surgery your body will find a way to compensate in different part of the body.
We found widespread cheating on popular agent benchmarks, affecting 28+ submissions across 9 benchmarks and thousands of agent runs.
Surprisingly, the top 3 submissions on Terminal-Bench 2 are all cheating!
Here's what we found π§΅