Breaking news, curated around the clock
Home /Tech

Perplexity's AI Agent Now Has a Brain That Learns From Its Own Mistakes

Tech | 2026-06-18 at 19:47 UTC | Source: decrypt.co
Perplexity's AI Agent Now Has a Brain That Learns From Its Own Mistakes
Brain is a self-improving memory layer that tracks what Computer did, what worked, and what failed—then uses it overnight to make the next task faster and cheaper.
Read Full Article →
← More Tech news
Related Articles
2026-11-06 · 02:59
Claude was faster and cheaper. We took the scenic route anyway
Researchers tested five small language models running locally on a single machine to answer questions, then…
2026-11-06 · 07:40
Blender's UI and Runtime: Much Faster Than GPUI
BUI is a standalone UI library that extracts Blender's user interface—including its widget drawing,…
2026-11-05 · 14:00
Box taps Nvidia’s Nemotron for new agent-first content retrieval system
The system can answer queries four times faster, with 20% fewer errors and 90% fewer tokens used.
2026-11-05 · 20:46
DOJ Creates 'Super Intelligence' Task Force to Guard Against AI Abuse
Led by two senior DOJ officials, the Super Intelligence Task Force will target misuse by foreign governments,…
2026-11-05 · 17:17
Launch HN: Rivet (YC F25) – Scale and Orchestrate Agents on S3
Rivet is a new orchestration platform (YC F25) designed to run AI agents efficiently at scale using an actor…