Find published research by company, product, platform or technology.
Showing 241–260 of 353 dossiers
OpenAI's agent containment story has moved beyond RubyGems: a rolling review is finding access-control bypass, credential use, command injection, runtime access and agent spam across third-party services.
The October major release simplifies SvelteKit's architecture but breaks familiar config files and legacy imports. Teams should run the codemod and verify adapters and deployments.
Stacked pull requests are now generally available on GitHub. The shift matters as coding agents make large changes faster than humans can safely review them: teams can keep one coherent change dependency-ordered while reviewing it as smaller PRs.
The release is more than routine maintenance. OpenSSH is changing cryptographic defaults, sacrificing some compression effectiveness for side-channel safety, and warning that AI-assisted security reports are pushing it toward a faster release cadence.
Together Link connects six existing coding-agent/desktop harnesses to open models with reversible profiles, per-session routing and cost receipts. The important shift is portability at the harness boundary, not Together's unverified savings claim.
The useful boundary change is that Copilot can now cross from code and terminals into ordinary desktop interfaces, with per-app approval and organisation-level controls.
Pi’s first stable release is interesting less for another coding-agent version number than for what its deliberately minimal core now considers mature enough to include: MCP, code-driven tool orchestration and model routing.
Canvas moves AI store building into production theme code, but the official requirements make the maintenance boundary clearer: entering Canvas can cut off normal theme downloads and upstream theme updates.
The bug is a useful warning for AI application plumbing: turning a user-supplied URL into a model attachment also turns the application server into a network client unless the adapter enforces an outbound trust boundary.
The interesting change is not another CLI rename. Cloudflare is redesigning its command surface around software agents: JSON is the default, commands can be discovered through natural-language search, configuration is typed TypeScript, and Wrangler now has an eventual migration path.
The Agent Host’s environment boundary has moved from local Dev Containers to remote development hosts, making persistent coding-agent sessions more portable across real remote projects.
Docker’s new agent stack combines pay-as-you-go microVM sandboxes with an OCI-based Kit format for declaring what an agent can use. Cloud sessions cost from $0.07 to $1.12 an hour, and Docker says it plans to take the Kit specification toward CNCF neutral governance.
Theme developers using Shopify CLI 3.83.x and older against password-protected storefronts are now past the documented cutoff. Shopify requires 3.84.0 or later for these flows; the live changelog's September 23 date supersedes the earlier October 1 deadline in this dossier.
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.
GitHub’s credential-response story now has both discovery and containment: enterprise owners can export SSH keys, PATs, OAuth and GitHub App tokens with ownership, scope and last-use metadata, then use selective revocation rather than invalidating every credential a user holds.
The dangerous detail is the delivery path: WordPress gives an unauthenticated commenter a moderation-preview URL for their own pending comment, and The Events Calendar can process attacker-controlled block markup from that preview before a moderator approves anything.
The useful part is not the 800,000-line headline. GitHub has published unusually detailed receipts for a production-scale agent-assisted migration: roughly $120,000 of token spend, 14.5 weeks of incremental releases, dozens of regressions, extensive compatibility tests and a workload-specific jump from 7.55 to 120 session lifecycles per second.
Android Bench 2.0 moves coding-agent evaluation away from small repository fixes toward dependency upgrades, app builds, migrations and other jobs that can take a human engineer days. The results expose a much larger reliability gap than short-task benchmarks—and show that the agent harness can materially change cost and outcome.
Jev’s launch claims were interesting; Vercel’s usage data is more useful. Nearly 13% of paid AI Gateway teams tried the typed decision model in its first day, while Jev also rose to a material share of gateway requests. That does not establish retention or production success, but it is unusually fast developer uptake for a model designed to make bounded software decisions rather than generate prose.
Click2Shell turns a theme-preview parsing bug into a supply-path problem: an attacker can force official catalog code onto a site without the administrator choosing Install, then potentially reach executable pre-activation theme code.