"Generalist models "fail miserably" at the benchmarks used to measure how AI performs scientific tasks, Alex Zhavoronkov, Insilico's founder and CEO, told Fortune. " You test it five times at the same task, and you can see that it's so far from state of the art...It's basically worse than random. It's complete garbage." Far better are specialist AI models that are trained directly on chemistry or biology data."
"Enter Insilico's new "Science MMAI gym," designed to train a generalist large language model into something that can perform as well as specialist models. The gym is a pivot for Insilico, which calls it part of its "long-term roadmap toward Pharmaceutical Superintelligence." The startup is part of a group of biotech companies trying to use machine learning and artificial intelligence to research and devise new drugs."
Insilico Medicine is launching the Science MMAI gym to adapt general-purpose large language models for biology and chemistry tasks. Generalist models perform poorly on scientific benchmarks, while specialist models trained on domain data perform better but lack plain-language prompting and broader capabilities. The gym will train models using domain-specific datasets, reward models, and reinforcement learning to improve performance up to tenfold on key chemistry and biology benchmarks and approach specialist-model levels. The service targets biotech and pharmaceutical companies and is positioned as part of Insilico's long-term roadmap toward Pharmaceutical Superintelligence.
Read at Fortune
Unable to calculate read time
Collection
[
|
...
]