%20--%3E%3Cmetadata%20xmlns%3Ardf%3D%22http%3A%2F%2Fwww.w3.org%2F1999%2F02%2F22-rdf-syntax-ns%23%22%20xmlns%3Axsi%3D%22http%3A%2F%2Fwww.w3.org%2F2001%2FXMLSchema-instance%22%20xmlns%3Adc%3D%22http%3A%2F%2Fpurl.org%2Fdc%2Felements%2F1.1%2F%22%20xmlns%3Adcterms%3D%22http%3A%2F%2Fpurl.org%2Fdc%2Fterms%2F%22%3E%3Crdf%3ARDF%3E%3Crdf%3ADescription%3E%3Cdc%3Atitle%3EShadows%3C%2Fdc%3Atitle%3E%3Cdc%3Acreator%3EDiceBear%3C%2Fdc%3Acreator%3E%3Cdc%3Asource%20xsi%3Atype%3D%22dcterms%3AURI%22%3Ehttps%3A%2F%2Fwww.dicebear.com%3C%2Fdc%3Asource%3E%3Cdcterms%3Alicense%20xsi%3Atype%3D%22dcterms%3AURI%22%3Ehttps%3A%2F%2Fcreativecommons.org%2Fpublicdomain%2Fzero%2F1.0%2F%3C%2Fdcterms%3Alicense%3E%3Cdc%3Arights%3E%E2%80%9CShadows%E2%80%9D%20(https%3A%2F%2Fwww.dicebear.com)%20by%20%E2%80%9CDiceBear%E2%80%9D%2C%20licensed%20under%20%E2%80%9CCC0%201.0%E2%80%9D%20(https%3A%2F%2Fcreativecommons.org%2Fpublicdomain%2Fzero%2F1.0%2F)%3C%2Fdc%3Arights%3E%3C%2Frdf%3ADescription%3E%3C%2Frdf%3ARDF%3E%3C%2Fmetadata%3E%3Cdefs%3E%3Cg%20id%3D%22shoulders-narrow-45e9bf6e%22%3E%3Cpath%20d%3D%22M11%2050C11%2018%2023.6%200%2039%200s28%2018%2028%2050Z%22%20fill%3D%22%23733662%22%2F%3E%3C%2Fg%3E%3Cg%20id%3D%22tops-afro-45e9bf6e%22%3E%3Cg%3E%3Ccircle%20cx%3D%2228%22%20cy%3D%2229%22%20r%3D%2217.5%22%20fill%3D%22%23733662%22%2F%3E%3Ccircle%20cx%3D%2211.3%22%20cy%3D%2226%22%20r%3D%227.5%22%20fill%3D%22%23733662%22%2F%3E%3Ccircle%20cx%3D%2216%22%20cy%3D%2216%22%20r%3D%227.5%22%20fill%3D%22%23733662%22%2F%3E%3Ccircle%20cx%3D%2225%22%20cy%3D%2212.3%22%20r%3D%227.5%22%20fill%3D%22%23733662%22%2F%3E%3Ccircle%20cx%3D%2235.2%22%20cy%3D%2213.6%22%20r%3D%227.5%22%20fill%3D%22%23733662%22%2F%3E%3Ccircle%20cx%3D%2243%22%20cy%3D%2221%22%20r%3D%227.5%22%20fill%3D%22%23733662%22%2F%3E%3Ccircle%20cx%3D%2245.2%22%20cy%3D%2231%22%20r%3D%227.5%22%20fill%3D%22%23733662%22%2F%3E%3C%2Fg%3E%3C%2Fg%3E%3Cg%20id%3D%22heads-tall-45e9bf6e%22%3E%3Cuse%20transform%3D%22matrix(.89%200%200%20.89%205.95%20-.32)%20rotate(3%2C%2028%2C%2025)%22%20href%3D%22%23tops-afro-45e9bf6e%22%2F%3E%3Cellipse%20cx%3D%2231%22%20cy%3D%2237%22%20rx%3D%2217%22%20ry%3D%2223%22%20fill%3D%22%23733662%22%2F%3E%3C%2Fg%3E%3CclipPath%20id%3D%22clip-45e9bf6e%22%3E%3Crect%20width%3D%22100%22%20height%3D%22100%22%20rx%3D%220%22%20ry%3D%220%22%2F%3E%3C%2FclipPath%3E%3C%2Fdefs%3E%3Cg%20clip-path%3D%22url(%23clip-45e9bf6e)%22%3E%3Crect%20width%3D%22100%22%20height%3D%22100%22%20fill%3D%22%23ede6d6%22%2F%3E%3Cuse%20transform%3D%22translate(11%2051)%22%20href%3D%22%23shoulders-narrow-45e9bf6e%22%2F%3E%3Cuse%20transform%3D%22translate(19%201)%22%20href%3D%22%23heads-tall-45e9bf6e%22%2F%3E%3C%2Fg%3E%3C%2Fsvg%3E)
At BTD26, Konstantin Dunas & Florian Brand from Prime Intellect joined us for two talks: Scaling #LLM-RL for #agents, training infrastructure, and why #LLM #benchmark scores depend on harnesses, infrastructure, and more. 🔹Konstantin: youtu.be/MIdkU5n_RSE 🔹Florian: youtu.be/kmTMc-fVSXw #tngbtd
0 reposts0 likes