shipfeedAI news, curated daily

01:00:18 CET
28 SEPT01:00:18shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Learning from Real-World Mistakes

Perplexity Research post-trained its Computer model on user corrections and tool failures, cutting tool-call errors by 21.2% relative, though broader task-success gains were not confirmed.

Sep 21 · · primary fetch1 sourceupdated Sep 21 ·

Perplexity Research describes post-training a Perplexity Computer model using user corrections and tool failures. The reported online evaluation reduced tool-call failures from 2.24% to 1.77%, a statistically significant 21.2% relative reduction, while noting that fewer tool errors did not necessarily translate into broad task-success improvements.

read full article on perplexity.ai ↗
§ sources1 publication · timeline below
  1. perplexity.aiLearning from Real-World Mistakesprimary