🚨 An open-source stack just beat Claude Code + Opus 4.8 - at 1/12th the cost PRAXIST put up 65.3% gold on the full 75-task MLE-Bench. 49 golds. $3,054 in tokens. Claude Code + Opus 4.8 spent $38,370…

Sapient Intelligence released PRAXIST Beta, an autonomous R&D system that carries experimental evidence across generations. On the full 75-task MLE-bench: - Sapient's PRAXIST got 49 gold medals and…

finally an AI that runs on research and gets better every time instead of guessing once Sapient just dropped PRAXIST an actual R&D team in a loop basically a software that acts like a small research…

found a way to run an autonomous R&D team at ~1/12th the cost of claude code 😳 sapient open sourced praxist agents explore competing approaches in parallel, share findings, and a PI panel picks the…

AN OPEN-SOURCE MODEL JUST BEAT AN OPUS 4.8 STACK ON 75 RESEARCH TASKS AND SPENT A TWELFTH OF THE BUDGET > Praxist: 49 golds across the full MLE-Bench set, $3,054 in tokens > Claude Code + Opus 4.8:…

Introducing PRAXIST Beta, your autonomous research team🚀 Define the objective, constraints, and what success looks like. PRAXIST discovers the path. From there, PRAXIST takes on the experimental…