Find published research by company, product, platform or technology.
Showing 221–240 of 336 dossiers
Woodpecker's agent labels were self-reported and unsuitable for authorization. Version 3.19 adds server-held filters and patches a clone-step environment-variable leak; administrators should verify their worker policies.
This is not one headline vulnerability fix. Gemini CLI 0.60 is a coordinated hardening pass across the plumbing that lets extensions, sandboxes, filesystem paths and MCP authentication influence an agent’s execution environment.
The important signal is the infection path. A trusted maintainer can unknowingly become the supply-chain carrier when malware modifies project and build files before a normal package publish, so publisher identity alone does not prove the artifact matches the maintainer’s intent.
Hydrogen 2026-10 is generally available as a JavaScript commerce library with React Router and Next.js starters and examples for other frameworks. Existing Hydrogen storefronts still work; migration is optional.
CLM-8B targets the same narrow decision layer as Jev, but with open weights, local deployment and a contrastive architecture that separates state and action representations. The headline speed and coding results are researcher-produced and need careful interpretation.
Cloudflare Computer 0.7 makes agent code resumable and interruptible. The important catch: recovery replays code, and unrecorded external actions can be repeated even if they already succeeded.
Branch previews are common for frontend code, but Worker Previews extends the boundary to the runtime itself. Each branch can have independent bindings, state and logs, making parallel human and agent work safer while preserving a production-like execution path.
WooCommerce 11.3 removes /wp-json/woocommerce/mcp, REST-key MCP authentication and REST-derived abilities. Migrate clients to the WordPress MCP Adapter plugin, application passwords and explicit ability metadata before upgrading.
Ghostty 1.4 addresses malicious Kitty graphics, tmux output crashes, OSC 52 and macOS links. Update terminal installations and verify shell integration.
A six-month real-world comparison shows AI code-review agents and specialised fuzzers find substantially different V8 vulnerabilities. Replacing fuzzing with agents would leave gaps, and cost per bug remains unknown.
gopls 0.24.0 and VS Code Go 0.56.0 ship interactive refactorings for struct tags and interface implementations; the broader Language Server Protocol extension is still a proposal, with cross-file moves in preview.
PostgreSQL operators gain per-statement and per-transaction estimated-cost limits across versions 14–18, useful for runaway reports and ORMs. The guard is disabled by default and can be bypassed by users allowed to change planner cost parameters.
The third-party pgx-bm25 1.0 extension gives PostgreSQL 17 and 18 native-index BM25 ranked retrieval with ordered scans and no external engine, but it is not built into PostgreSQL core and has important planner and RLS caveats.
Rashomon's experimental local recorder can expose discrepancies between a coding agent's closing claims and its tool execution. It is an observability aid, not a sandbox or tamper-proof security product.
Laravel now has a framework-native approval flow for AI tools: approvable tools can pause an agent, surface arguments and reasons, then resume the same persisted conversation after a human decision.
A previously preparatory compliance field is now an operative delivery gate. Builders automating Toll-Free onboarding need to collect, validate and submit policy URLs as part of registration rather than treating them as optional metadata.
Gemini 3.8 Flash keeps 3.7 Flash’s promotional per-token rate and Flash-tier latency, but early independent analysis suggests harder reasoning can increase tokens consumed per task. A separate 3.8 Flash Cyber model is available only through Google’s Fairwind defensive-security program.
Microsoft Advertising is taking Max CPC out of new standalone automated campaigns from October 1. Existing capped campaigns and portfolio strategies retain the control for now, but advertisers creating new campaigns will need to rely more heavily on conversion targets, budgets and portfolio bidding.
Developers can now train and evaluate adapters through custom code while Together runs the GPU-heavy operations. The flexibility comes with B200-only support, a $100 credit threshold and ongoing charges for idle ready resources.
Buttondown’s 'Great Pruning' is a small-SaaS operations story about deleting architecture rather than adding it. The company removed duplicated or over-retained request and email-event data after changing how those workloads were processed.