📄 文章列表
414 篇文章
VentureBeat
Reflection's Beam aims to undercut Chinese open models with fewer tokens, not cheaper tokens
TDS
Prompt Regression Tester
TDS
A Scaffold at the Gate: Building AI Applications That Can Evolve
TDS
Coding Agents Can Solve the Task — But How Much Work Did They Waste?
TDS
Stop Using AI. Start Hiring It.
TDS
Where Does the Money Go Across Long-Running Coding Agents?
VentureBeat
Why giving AI agents more compute isn't enough—and what Meta proposes instead
TDS
A Google Team Measured Half of My Argument, and Left the Other Half Open
TDS
The Consistency Quadrant: A Visual Guide to LLM Reliability
TDS
How to Govern AI Agents
VentureBeat
New MIT and Sakana AI framework uses an LLM judge to cut evaluation costs for self-improving coding agents
TDS
Insight Is Still the Currency of Data Science
VentureBeat
Developers say OpenAI and Anthropic safeguards are flagging routine work and costing them time
TDS
Towards Spec-Driven Test Automation: Part 2
VentureBeat
Autoheal wants to manage the work AI coding agents leave behind, claiming cost reductions of up to 30% per task
VentureBeat
OpenAI's GPT-6.1 Sol offers Astra-like performance at 1/5th price. A new Ultrafast tier clocks at 300 tokens per second.
VentureBeat
Nvidia's OpenShell controls what AI agents can access, even when they ignore instructions
VentureBeat
Anthropic launches Claude Sonnet 5.5 with 30% cost reduction per-task due to faster speeds and fewer tool calls
TDS
Good Architecture Deletes the Signals Your Agent Depends On
TDS