By end of 2026, the majority of code written and PRs created (and reviewed) will be done by parallelized async software engineering agents, not in IDEs or CLIs

DM me if you want to early access to the best (no ones churned yet)

cofounder @ohara-ai — mini apps! building software generation on @base. primarily posting about the latest AI news

Barista in the morning, AI engineer by day, and parent (with @shiwen) by night ||
Host at /clickcast /cpg

Hacker founder using ai to coordinate onchain economies /tenfold, nounish channel client /comint

More: rubinovitz.com

I can’t get any parallelized agents to work for lmk if you find one that works