Skip to main content

Share story

AI

Pensieve developer reports 18% lower costs for coding-agent lookups

Pensieve: one search across your files, repos and agent sessions, on your Mac Image: Primary
Pensieve's developer reports that Claude Code using its local search tool cost 18% less per code lookup and used 16% fewer tokens in a benchmark across four repositories. The tool gives coding agents relevant passages with file names and line numbers through MCP, an interface for connecting agents to tools. The test ran the same 72 held-out tasks twice with each setup. Pensieve found the right file in 131 of 144 runs, compared with 123 using grep alone, and used 43% fewer tool calls. The Pensieve setup also included added agent instructions. For exact error messages, a single grep search performed better.
Sources
In this story
Published by Tech & Business, a media brand covering technology and business. This story was sourced from tedhaley.ca and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
AI Products
AI Products

Tencent plans about $5 billion bond offering to help fund AI spending

Tencent told fixed-income investors Monday that a planned bond offering of about $5 billion would help finance AI-related capital expenditures, Bloomberg reported, citing people familiar with the matter. The offering would provide...

Security
Security

CloudConnect CRM flaw reportedly allows data theft without a login

Attackers are exploiting a CloudConnect vulnerability to remotely access and steal customer data and internal business records without logging in, The Tech Edvocate reported. The flaw in the cloud platform, which businesses use to...

Robotics
Robotics

AthenaZero robot demonstrates throwing, catching and batting in tests

Researchers at the Robotics and AI Institute in Cambridge, Massachusetts, have demonstrated a dual-arm robot throwing, catching and batting balls, Electronics For You reported. Called AthenaZero, the system combines low-inertia ar...

AI Science
AI Science

AutoIndexer preprint demonstrates a model that edits its earlier output

Researchers report that AutoIndexer can insert, replace and delete text it has already generated, addressing a limitation of models that produce text in a fixed sequence. Their preprint says the method demonstrates editing after g...