Introducing OB-1: the new #1 coding agent on Terminal Bench. After a year of R&D, our agent now outperforms Codex and Claude Code. Early access is rolling out to waitlist users now. https://t.co/cXTh8n7chw
- 0 replies
- 0 recasts
- 0 reactions
2/ Other coding agents deliberately nerf capabilities to save costs. OB-1 doesn’t. Instead, it fuses intelligence across multiple agents with persistent long-horizon memory, delivering a far more reliable coding experience. Sign-up for early access: https://t.co/ubkvCmotUR https://t.co/xV0k6vcscU
- 0 replies
- 0 recasts
- 0 reactions
RT @openblocklabs: #2 on Terminal Bench Leaderboard using the @OpenAI GPT-5 Model https://t.co/i3ABWy3ALv
- 0 replies
- 0 recasts
- 0 reactions