You can now run Harbor evals on Vercel Sandbox. Harbor is the open-source harness behind Terminal-Bench , whose registry includes many other benchmarks such as SWE-bench, tau3-bench and OSWorld. Pass --env vercel to harbor run and each tria…
Firehose
Filtered to Companies, tagged “open-weight models” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
New OpenAI Economic Research shows how workers use AI beyond traditional roles and which new activities become recurring parts of their work.
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking from Google are now available on AI Gateway. Both models support real-time spoken interactions for voice assistants, conversational experiences, and applications that respond through aud…
The AI SDK harness layer now supports authenticating harnesses through their native subscriptions, where the underlying harness supports them. The harness layer runs different coding agents through the same HarnessAgent interface, so you ca…
You can now build and deploy long-running, tool-using agents with the OpenAI Agents API on Vercel. OpenAI manages the agent loop and session state, while Vercel hosts the application and connects each session to Vercel Sandbox for code exec…