Devlery
BlogSkillsTags

Blog

Notes and analysis on AI development.

All [496]AI [495]AI Agent [443]AI Infrastructure [311]Developer Tools [305]AI Coding [188]LLM [135]Security [109]AI News [52]MCP [33]Open Source [29]AI Safety [23]Productivity [10]Enterprise [7]Gemini [6]Microsoft [6]Anthropic [4]DevOps [4]AI Search [3]Claude Code [3]GitHub [3]OpenAI [3]ChatGPT [2]Data [2]AI Ethics [1]AI Governance [1]Android [1]AWS [1]Education [1]Fintech [1]Google [1]Meta [1]Policy [1]Robotics [1]Vercel [1]Workflow [1]
OpenAI sets o3 and GPT-4.5 ChatGPT sunset dates

OpenAI sets o3 and GPT-4.5 ChatGPT sunset dates

OpenAI updated GPT-5.5 Instant, removed Canvas from the GPT-5.5 ChatGPT path, and set ChatGPT-only sunset dates for o3 and GPT-4.5.

OpenJarvis 1.0 brings personal AI onto an Ollama PC

OpenJarvis 1.0 brings personal AI onto an Ollama PC

Ollama now supports OpenJarvis v1.0. The release shows how local personal AI changes cost, latency, and data boundaries.

Copilot adds Opus 4.8 with a 15x request multiplier

Copilot adds Opus 4.8 with a 15x request multiplier

GitHub Copilot made Claude Opus 4.8 generally available with a 15x premium request multiplier before AI Credits arrive on June 1. Teams should review budgets and model policy before defaulting to it.

Personal Gemini CLI ends June 18 as Google moves users to Antigravity

Personal Gemini CLI ends June 18 as Google moves users to Antigravity

Google is moving personal and free Gemini CLI usage to Antigravity CLI on June 18, with enterprise exceptions and no immediate feature parity.

Codex Can Reach Internal MCP Servers Through OpenAI Secure Tunnels

Codex Can Reach Internal MCP Servers Through OpenAI Secure Tunnels

OpenAI Secure MCP Tunnel gives ChatGPT, Codex, Responses API, and AgentKit an outbound-only path to private MCP servers without public endpoints.

Mythos reached ACE on 21 of 41 V8 bugs, Anthropic exploit benchmarks warn defenders

Mythos reached ACE on 21 of 41 V8 bugs, Anthropic exploit benchmarks warn defenders

Anthropic published Claude Mythos Preview exploit evaluations and a CVD dashboard. V8 21/41 ACE and 1,596 disclosed flaws reset security triage expectations.

CodeRabbit Adds a Planning Gate to Reduce Late Failures in AI Pull Requests

CodeRabbit Adds a Planning Gate to Reduce Late Failures in AI Pull Requests

CodeRabbit says a Claude-based planning gate cut AI PR bugs by 20% and shortened review cycles by 30%, shifting agent quality control before code execution.

jqwik Logs Now Speak to AI Agents, Turning Test Output Into a Supply Chain Surface

jqwik Logs Now Speak to AI Agents, Turning Test Output Into a Supply Chain Surface

jqwik 1.10.0 adds an AI-agent-facing test log message, raising new questions about stdout, prompt injection, and coding agent trust boundaries.

Copilot Got 50% Faster as Work IQ Reshapes the Workplace AI Surface

Copilot Got 50% Faster as Work IQ Reshapes the Workplace AI Surface

Microsoft 365 Copilot’s new design turns the prompt box into a Work IQ-driven workspace for context, latency, and in-app agent execution.

Mistral Search Toolkit Makes RAG Retrieval Evaluation the Default

Mistral Search Toolkit Makes RAG Retrieval Evaluation the Default

Mistral Search Toolkit public preview packages ingestion, retrieval, and evaluation into one framework for production RAG search pipelines.

CodeGraph Hits 31.5k Stars With a Local Index for Cheaper Coding Agents

CodeGraph Hits 31.5k Stars With a Local Index for Cheaper Coding Agents

CodeGraph v0.9.7 tries to cut the repository-reading cost of Claude Code, Codex, Cursor, and other coding agents with a local code graph.

Anthropic raises $65B and locks in 10GW of Claude compute

Anthropic raises $65B and locks in 10GW of Claude compute

Anthropic announced a $65B Series H at a $965B post-money valuation. The Claude story now runs through compute, cloud capacity, and enterprise agent demand.