# Perplexity says a later Computer checkpoint reduced tool-call failures 21.2% in a live A/B test

Perplexity post-trained a Computer model to learn from its own errors using hint-guided self-distillation. It said the 21.2% reduction was relative to an earlier checkpoint.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T06:08:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/c7607be49c6d44e9aef59e5c.html

Content language: en
Localization state: sameLanguage

Source: Perplexity · Published 9/22/2026, 13:32:27

Perplexity post-trained a Computer model to learn from its own errors using hint-guided self-distillation. In a live A/B test, Perplexity said, a later trained checkpoint reduced tool-call failures by 21.2% relative to an earlier checkpoint.

Tags: Perplexity, Research, Self-distillation, Tool calls

[View original post](https://x.com/perplexity_ai/status/2102493613192298913)