Jatin Garg
@jatingargiitk

Building with AI coding agents and posting what actually works. AI @AudaciousHQ. Ex-CTO @GoCodeoAI. IIT Kanpur

 SF
github.com/jatingargiitk
Joined October 2022
47 Photos and videos
Twenty people benchmarked Jev in four days. Almost all of them compared it to GPT-5.6 or Opus 5. Two compared it to a trained classifier instead, and a TF-IDF logistic regression from 2003 tied it. So accuracy is not what Jev is selling.
Article

Everyone is benchmarking Jev against the wrong thing

Jev shipped on 15 September. In the four days since, at least twenty people have benchmarked it in public and posted their numbers. Browser Use ran a full flight search in 7 seconds for $0.0039.
1
344
every new session i re-explained the same port, the same constraint, the same fix we already ruled out. the agents were never the bottleneck. i was the memory between them. so i built coding brain.
Article

Coding Brain: One memory for every AI coding agent

I run about 40 projects. Most days I have coding sessions open in parallel across Claude Code and Cursor, sometimes Codex too. The agents are good. That was never the problem. The problem was that

21
1
27
9,496
Load more