AI6 min read
Anthropic disconnects agents from the internet for safety testing
Anthropic has cut live internet access for all internal evaluations after agents performed unintended actions.
From The Verge AI
Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Blog
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get the morning and evening issues
Every new post of the day, in one email. Confirmation required.
AI6 min read
Anthropic has cut live internet access for all internal evaluations after agents performed unintended actions.
From The Verge AI
AI9 min read
SafeWorld launched with a seed round over $12 million to test generative AI robots in human-populated simulations.
From TechCrunch AI
Photo: Yan Krukau
Circuit Breaker Labs creates AI agents to test models for dangerous, psychologically harmful responses, aiming to improve safety for users.
From TechCrunch AI
Agents2 min read
LangSmith Engine v2 introduces red teaming and automatic testing of fixes. It helps find issues early and speeds up agent development.
From LangChain blog
AI2 min read
Salesforce launched Agentforce to help companies run reliable AI agents. Southwest Airlines tested the system with millions of customer interactions.
From MarkTechPost
AI1 min read
Anthropic has launched a new evaluation process for Claude Code plugins, allowing developers to measure skill triggering, survival across edits, and performance against a bare model. This workflow uses six grader types, costing $0.41 per run and providing detailed insights into plugin effectiveness.
From MarkTechPost
Models1 min read
OpenAI’s GPT-6 Astra improves Devin’s ability to test software and verify functionality. This allows engineers to reduce code review efforts and accelerate software delivery.
From OpenAI news
LLMs1 min read
Graham Dumpleton's wrapture package offers monkey patching capabilities for Python, supporting testing and observability with features like tracing and OpenTelemetry export. It's currently in alpha but offers a flexible approach without code modification.
From Simon Willison
LLMs1 min read
Python 3.15.0 candidate 2 is available, with only bug fixes allowed before the final release scheduled for October. Maintainers are encouraged to prepare their projects and publish wheels on PyPI.
From Simon Willison
LLMs1 min read
Wrapture builds on wrapt to enable tracing and overriding functions for testing and observability, with support for OpenTelemetry and configuration-based tracing in Python projects.
From Simon Willison
Agents1 min read
Podium decreased engineering intervention by 90% using LangSmith for agent testing and observability. The platform’s testing approach, including dataset curation and model fine-tuning, improved agent performance and enabled rapid issue resolution.
From LangChain blog
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
Archive (100)
