Why harnesses matter for energy (and token) efficiency

AI summary

Analysis of a month of agent traffic reveals that the harness, not just the model, determines the energy consumption of coding sessions.

Key points

•Data from one month of agent traffic was analyzed.
•The energy usage of coding sessions is determined by the harness, not just the model.
•Harness design significantly impacts energy and token efficiency.

#AI Agents #Semiconductors & Infrastructure

Read the original

TechCrunch10/17/2026

Replit is no longer working with Anthropic, CEO says

Replit CEO and co-founder Amjad Masad stated at TechCrunch Disrupt 2026 that the company is no longer working with Anthropic.

The Verge10/17/2026

Tesla driver says he was asleep and using FSD when he crashed into highway patrol cars

The California Highway Patrol warned that Full Self-Driving is not fully autonomous after a Tesla driver admitted to being asleep while using the feature during a crash into patrol cars.

Hacker News10/17/2026

How the Claude Code team does code review

The Claude Code team optimizes for the minimum amount of human review time that does not cause reverts or incidents, addressing the volume of code produced by agents.

Google Research10/17/2026

Grounding AI agents in biological reality: Building blocks for autonomous wet labs

Google Research published a piece on building blocks for autonomous wet labs that ground AI agents in biological reality.