Find published research by company, product, platform or technology.
Showing 141–160 of 315 dossiers
The post-release evidence sharpens the original story. Qwen3.8-27B can retain useful agentic-coding performance at practical 4-bit sizes, but local model quality is not a property of the checkpoint alone: quantization, reasoning effort, context handling and the agent harness can materially change the result.
GitHub Copilot can now turn Slack or Teams threads into collaborative cloud-agent sessions. Teammates can add context and steer the work in public, while repository permissions, agent budgets and optional extra PR approvals remain the main control boundaries.
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.
GitHub OAuth apps can now use eight-hour access tokens with rotating refresh tokens, register up to 10 callback URLs, and explicitly control wildcard callback matching. New apps default to expiring tokens, while existing single-callback apps should review a legacy wildcard setting GitHub has now made visible.
The May Antigravity agent ID is retired. Managed Agents now require the September preview ID and default to Gemini 3.8 Flash, alongside hooks, token budgets and scheduled sandboxes.
SvelteKit 3's Vite and #lib migration remains the main upgrade boundary; 3.1.1 now also fixes security-sensitive server-only module and cross-origin path handling, so deploy a patched 3.x build.
The workflow shift is continuity rather than another model upgrade: one Kiro agent session can outlive the laptop that started it. Cloud configuration can also carry agent setup across environments, although enterprise governance is not identical between local and web/cloud surfaces.
The October 28 security release is more than an upgrade-window RCE fix. WordPress has now documented affected blocks, note access and root certificate changes; no confirmed active exploitation is established by the announcement.
GitHub moved its September 25 deadline to September 29 and has begun full version enforcement for self-hosted runners in Enterprise Cloud. Old pinned images and disabled auto-updates can still stop workflows.
With no planned installation banner, apps should identify affected merchants and handle the migration proactively; Shopify's alternative theme app embeds still require activation on the published theme.
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.
CVE-2026-119741 affects rsync through 3.5.1. The 3.5.2 fix bounds checksum work; a hostile receiver can otherwise drive CPU exhaustion on senders, including through repeated daemon connections.
Developers can submit tool integrations to Google Search and Gemini using MCP, but access is phased, users must connect apps, and Google reviews submissions.
WebMCP is no longer a Chrome-only browser experiment: Microsoft Edge now has its own active origin trial, while ChatGPT’s built-in browser and WordPress Playground show agent-client and platform implementation paths.
PIE 1.5.5 and 1.4.12 fix a low-severity temporary-file issue in the PHP extension installer that could expose long failed-build logs to other local users.
Quattro’s unified programmable shell is a real architecture change rather than a theme refresh. Omarchy 4.0.2 now hardens package, installer, SSH and input paths, while current user reports of Quickshell crashes and a runaway-memory event illustrate the new central shell’s blast radius.
PHPUnit's October 16 fixes extend output integrity from terminal text into XML logs, which could previously be malformed by test-controlled strings.
The platform now offers an objective-oriented /goal interface as well as Custom Flows; availability depends on GitLab 19.3+, Duo CLI 9.17+ and eligible tiers.
AI image and social-app developers face clearer moderation and review obligations; hiding features can threaten an entire developer account.
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.