News for hackers. Stuff that matters.
Re:Characterizing Emergent Phenomena in Large Language Models by evrimoztamur on Monday December 19, 2022 @08:50AM (#34051975)
Has there been any efforts in processing calculation prompts, where instead of letting it internally 'compute', it's trained to identify equations and process them with an external calculator instead (perhaps one which outputs not only the result but the individual steps too)?
Re:Characterizing Emergent Phenomena in Large Language Models by obiefernandez on Monday December 19, 2022 @10:21AM (#34053086)
Been wondering the same
Re:Characterizing Emergent Phenomena in Large Language Models by vutekst on Monday December 19, 2022 @12:45PM (#34055024)
Re:Characterizing Emergent Phenomena in Large Language Models by visarga on Monday December 19, 2022 @05:07PM (#34058422)
Language models with toys. The calculator, Python REPL, search engine, database, simulation, games, other AI's can easily blend with large language models lifting some weight off their shoulders.

For example, for a physics question the LM could write a small simulation, run the simulation and interpret results back to the user. That's possible when models can do code execution.