Skip to content
OpenAI News

Perplexity trusts GPT-6 Astra with end-to-end systems, checking in far less often

Perplexity trusts GPT-6 Astra with end-to-end systems

Perplexity co-founder Johnny Ho says GPT-6 Astra can now draft communications, edit live systems, and monitor production—tasks earlier models couldn't handle. They let Astra write its own test harnesses that simulate external API responses, running full end-to-end workflows. Because the model is more reliable, the team checks in much less often. The post gives only qualitative statements; no specific performance metrics or latency figures are disclosed.

Why it matters: Perplexity cofounder Johnny Ho says GPT-6 Astra edits real systems, monitors production software and writes its own test programs, cutting how often humans check its work.

Read the original ↗Export Markdown