github CrewAI · 1h ago · agents

Anthropic Claude Code v1.15.6 fixes tool-use detection and dependency resolution

from English

Claude Code version 1.15.6 has been released with several bug fixes, including improved detection of Anthropic preview tool-use blocks and preservation of strict tool schema property names.

Dispatches the execution_end hook on failed crew and flow executions.
Handles async get_agent in load_agent_from_repository.
Resolves dependency resolution issues.
Includes snapshot and changelog for v1.15.5.

The update addresses stability and compatibility concerns for users relying on tool-use schemas and agent loading mechanisms.

Importance 1/3 Trust 2/3 CrewAI Cursor AI agents

Read original

media TLDR AI · 1d ago

AMD + Anthropic deal: AMD to supply MI450 chips and invest $5B

AMD and Anthropic have signed a major agreement involving tens of billions of dollars in AI servers, with Anthropic purchasing up to 2 gigawatts of AMD's Instinct MI450 chips starting in the first half of next year. Concurrently, AMD will invest up to $5 billion in Anthropic as specific deployment milestones are met, while both companies collaborate on identifying suitable data centers for the hardware.

media TLDR AI · 7d ago

Claude Code adds in-app browser; Cursor builds general agent

Anthropic has added an in-app browser to Claude Code on desktop, allowing the tool to read, click through, and interact with websites and docs similarly to local dev servers. Concurrently, reports indicate that Cursor is developing a general-purpose AI agent designed to handle emails, texts, spreadsheets, and engineering tasks.

lab Claude Code Releases · 14d ago · 1 view

Claude Code v2.1.207 enables Auto mode by default and defaults to Claude Opus 4.8

Claude Code version 2.1.207 makes Auto mode available without opt-in on Bedrock, Vertex AI, and Foundry, while changing the default model for these platforms to Claude Opus 4.8.

lab Hugging Face Blog · 31d ago · 5 views

Build Real Agentic Apps with CUGA: 24 Working Examples

CUGA introduces a lightweight harness enabling developers to build real agentic applications. It includes 24 working examples demonstrating practical implementations across various use cases.

arxiv arXiv cs.AI · 38d ago · 1 view

Oracle Signals in Agent-Authored Test Code

An empirical study of 86,156 test-file patches from 33,596 agent-authored PRs reveals that 80.2% of test patches contain weak or no explicit oracle signals. Strong-oracle test files significantly improve merge likelihood (OR = 1.28, p < 0.001) after adjusting for multiple factors, indicating test file presence alone overestimates verification strength.