Loading activity…
@ryan_marten
Building @harborframework and @terminalbench
AI
Epoch AI labels nine of its initial 15 benchmarks “Flawed” and four “Verified,” with insufficient information to review two. A Terminal Bench contributor questions the audit’s rigor.
Technology
Scientists from labs worldwide shared their actual research workflows to test AI agents. The result? Even top models solve just 30 percent of these authentic tasks.
AI
Andy Konwinski says Terminal-Bench will now receive frequent version updates like software.
AI
Z.ai released the GLM-5.3 API optimized for coding and agentic work at the same price as GLM-5.2.
