AI Briefing#agentic-coding
The latest AI and developer news about #agentic-coding, with the original source and a short summary.
The latest AI and developer news about #agentic-coding, with the original source and a short summary.
Qwen3.6 has been released with enhanced frontend workflows and repo-level reasoning.
Claude Opus 4.7 has been added to Bedrock, strengthening coding, agent, and document work.
Qwen released a MoE model with 35B total parameters and 3B active parameters under Apache 2.0.
Running MiniMax M2.7 AWQ on 2 GX10s to complete a local agentic coding stack.
Prompted by the Mythos analysis, security has become a token-consumption race.
Steve Yegge's criticism of Google's AI adoption was directly rebutted by people inside Google.
Connected an LLM to Hack Chinese to cut character review speed from 30 seconds to under 1 second.
xAI is preparing credit-based billing with monthly allocations and additional purchases for Grok Build.
Claude Opus 4.6 has launched with enhanced coding, long-context, and safety capabilities.
When an agent read papers and forks before writing code, llama.cpp optimizations improved significantly.
Z.ai's GLM 5.1 is now available on Vercel AI Gateway.
Alibaba's Qwen 3.6 Plus is now available in Vercel AI Gateway.
A summary of how running Claude Code as a multi-day autonomous agent can be used to implement scientific computing code.
MyRealTrip's PE organization has adopted a development approach that leverages AI coding tools, delegating code writing to AI while humans focus on design and verification.
OpenAI has released GPT-5.3-Codex, an agentic coding model that combines reasoning ability with coding performance.
OpenAI has unveiled GPT-5.2-Codex, an agentic coding model optimized for software engineering and cybersecurity.
OpenAI has released GPT-5.2-Codex, an agentic coding model optimized for professional software engineering and cybersecurity.
OpenAI has released the safety report for GPT-5.2-Codex, an agentic coding model optimized for complex software engineering.
Introduces an Agentic Coding guidebook along with a cheat sheet for AI collaboration and a standard ruleset sharing system.
OpenAI has significantly enhanced Codex's capabilities by unveiling GPT-5-Codex, optimized for agentic coding.
xAI has released Grok Code Fast 1, a fast and low-cost reasoning model optimized for agentic coding workflows.
The 480B MoE Qwen3-Coder aims for SOTA in coding, browser use, and tool use.