September 2023 Summaries
2 posts from AI21 Labs
Filter
Month:
Year:
Post Summaries
Back to Blog
The text discusses a multi-expert problem involving green energy companies, where data is fetched from Wiki API, last month dates are extracted from the calendar, and share prices are retrieved from a database. The largest increase in share prices is then computed by a calculator, and the answer is formatted using a language model. The text also mentions challenges in implementing multi-expert knowledge systems (MRKL) such as training discrete experts, interfacing with neural networks, routing among modules, and avoiding model explosion. It highlights the advantages of Jurassic-X, including its ability to read and update databases using free language, enabling users to interact with their data in natural language queries.
Sep 29, 2023
295 words in the original blog post.
The text discusses a multi-expert problem involving green energy companies, where data is fetched from Wiki API, calendar, and a database. It then computes the largest increase in share prices using a calculator and formats the answer with a language model. Technical challenges include training discrete experts, interfacing them with neural networks, routing among modules, and avoiding model explosion. Jurassic-X offers advantages such as reading and updating databases in free language, enabling users to analyze their data and join multiple databases.
Sep 12, 2023
295 words in the original blog post.