Shandong University researchers held models fixed and ran Claude Code, OpenCode, and the ~100-line mini-SWE-agent on 492 SWE-bench Verified tasks, finding statistically equivalent success rates but up to 3x differences in cost per task. On the 45 hardest tasks, switching harnesses flipped results about as often as simply rerunning the same setup (13%), so small single-run benchmark gaps say little.
GA as of Oct 23, version 1.2 bundles dependency based builds, ZCodeScan static analysis on the CLI, unit and functional testing, and Wazi Deploy into governed pipelines for z/OS apps. It's sold as a peer to IBM Bob Premium Package for Z, which supplies the AI assisted coding at each stage (product page)…
Now GA as of Oct 23, the Copilot coding agent investigates a CodeQL alert, writes a fix, reruns CodeQL to confirm it, and opens a draft PR, with up to 25 alerts batchable into one PR. It only covers alerts on the default branch and needs GitHub Code Security or Advanced Security on Enterprise Cloud, an admin enabled policy, and a Copilot billing method…
GitHub Advanced Security for Azure DevOps now uses the Copilot coding agent to propose pull request fixes for dependency vulnerabilities and third party scanning findings, following repo instructions and skills in .github or .agents . It also adds EPSS exploit likelihood percentiles and dev versus runtime dependency labels to triage, and you still review and merge every fix yourself…
Announced Oct 23, geelark cli (install with npm install g geelark cli@latest ) manages cloud phones, browser profiles, proxies, and billing from the terminal, and geelark cli mcp exposes the same commands as tools for Codex, Claude, and Cursor. It authenticates with a bearer token from the GeeLark client, so the agent gets whatever that token can do (repo)…
Shipped Oct 23, the new submit feedback tool lets an agent send bug reports, friction reports, and feature requests to the Vercel team with structured context like the tool, task, expected and actual behavior. It requires sign in and only sends when you ask your agent to share feedback…
Spotted something we missed? Start a thread.
