All News

Cursor has just rolled out auto-review mode, aiming to reduce approval prompts while keeping agent tool calls safer. A new classifier subagent reviews unsandboxed or non-allowlisted actions, deciding whether to proceed, reroute, or ask you first.

xAI has just rolled out Grok Build 0.2.7, adding /usage and /login commands, shared terminals across subagents, and improved image understanding. Early reactions range from workflow optimism to skepticism over time savings, rate limits, and version confusion.

Anthropic has just rolled out a Claude Code research preview called dynamic workflows, letting Claude generate an orchestration script and coordinate fleets of subagents. It targets big jobs like migrations and bug hunts, but can burn tokens quickly. Available on Max, Team, Enterprise, and APIs.

Anthropic has just rolled out Claude Opus 4.8, touting sharper judgment, more honesty, and longer independent work. A new “Fast mode” promises roughly 2.5x speed and lower cost, while Claude Code gets deeper agentic workflows for long-running tasks.

OpenAI is set to sunset GPT-5.2 and GPT-5.3-Codex in Codex on June 2 for users signed in with a ChatGPT account. GPT-5.5 will become the default frontier model on free plans, while older options remain available via the API.