OpenAI’s Models Reshaped Its Jalapeño Chip in Ways It Couldn’t Explain
3 Articles
3 Articles
OpenAI’s models reshaped its Jalapeño chip in ways it couldn’t explain
OpenAI’s own AI models changed parts of its Jalapeño chip, and its engineers could not always say why. In one example, they saved more than 13% of die area, Richard Ho told Ian Cutress of More Than Moore. Ho leads OpenAI’s hardware team, and the interview was published on 30 September. “Well, I still don’t […] This story continues at The Next Web
OpenAI now uses its own artificial intelligence models to contribute to the design of its chips. And experience gives rise to a paradoxical situation to say the least: the models have managed to optimize some parts of the Jalapeño chip without engineers always understanding precisely how or why their changes were working. Richard Ho, who [...] OpenAI article: His IA models have modified his Jalapeño chip without always understanding why appeared…
OpenAI models proposed changes that reduced more than 13% of the area of a part of the Jalapeño chip, in an example described by hardware manager Richard Ho. Manager acknowledges that engineers did not always understand why some proposals worked and that he still keeps caution against AI-assisted design.
Coverage Details
Bias Distribution
- 100% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
