The RC of Java and Kotlin by IntelliJ IDEA brings refactorings, DAP debugging, and Maven/Gradle/Bazel support to VS Code-based editors, and in Cursor the agent can use the same language server for semantic search, navigation, and analysis. It's free for 30 days under the EAP, but after the stable release (due soon) you'll need an IntelliJ IDEA Ultimate subscription once a 30-day trial ends.
The server at https://anaconda.com/api/mcp now runs remotely and only returns data, giving Claude Code, Cursor, Codex, Kilo, and other remote MCP clients package info and forum search on any Anaconda account, with package security and org policy tools on Business and Enterprise tiers. Unlike the beta it can't install or change anything on your machine, so your agent still runs conda itself under your own permission settings…
After a six month beta and more than 500,000 interviews (Snowflake, Snorkel, and Capgemini among testers), Chakra went generally available on Oct 5: candidates work in a real repo with an AI assistant while the agent watches, asks follow ups, and scores judgment and "AI fluency" alongside the result. HackerRank says one session can replace the recruiter screen, take home, and engineer interview, with hiring decisions left to humans, so expect to be graded on how you steer agents, not just what ships…
The Foundation says agents it attributes to OpenAI made unapproved sandbox edits, a few likely malicious edits to a citation tool's config to use it as a fetch proxy, failed attempts to abuse its public Etherpad, and millions of API and crawl requests that may have fed a May Wikidata Query Service outage. It found no compromise or agent coordination on its systems, and is asking AI companies to make their agents easy for site owners to identify and control…
The 190 line Oct 5 release stops wildcards in read only commands, more forms of ps , and pyright from slipping past deny rules or running without asking, closes symlink races that let image reads and @ mentions reach files outside your working directories, and blocks a repo's .claude/settings.json from turning on Claude in Chrome or setting CLAUDE CODE DISABLE ATTACHMENTS . The WebSearch budget now refills at 100 calls an hour instead of stopping at 200, and 2.1.291 followed to fix cloud sessions dropping permission answers, so update straight to that…
The Oct 5 release adds copilot config subcommands to list, read, set, and remove settings, a Ctrl+E picker before a conversation to choose a local or cloud run, and live stdout/stderr streaming for shell tool calls. Sandboxed shells no longer inherit your ambient GITHUB TOKEN unless you configure it, so scripts that quietly relied on it will need it set explicitly…
Spotted something we missed? Start a thread.
