Find published research by company, product, platform or technology.
Showing 61–80 of 118 dossiers
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.
Adobe Commerce and Magento merchants should treat CVE-2026-71362 as an urgent patch: independent security telemetry reports exploitation attempts even though Adobe’s bulletin still says it has not observed exploitation in the wild.
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.
A November 6 tinyjs patch repairs Windows builds broken by 0.71.0. Because affected apps cannot launch their updater, operators must rebuild and redistribute them.
A safer default can surprise an incident-response runbook: pgBackRest 2.60 aborts restores with invalid page checksums and refuses certain backup expirations. Here's what operators should test.
A 15-CVE pgAdmin update also changes how server-mode password commands are migrated, with a potentially irreversible first-start consequence.
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.
MLflow CrewAI autologging silently logged API keys; 3.17.0 patches it, but previously exported traces and keys still need remediation.
Neon now includes 100 separate free Postgres projects with 1GB each, 100 compute-unit hours per project and branching. It is a meaningful per-project allowance increase, not an unrestricted production database tier.
The release consolidates several recurring cluster-management jobs into core APIs and controllers. HPA scale-to-zero is now default-on Beta, storage-version migration and Pod Certificates are Stable, DRA can satisfy existing extended-resource requests, and large etcd reads gain a streaming path that reduces peak memory pressure.
Coolify 4.7.0–4.7.3 adds automatic cancellation of old queued webhook deployments, tighter API/SSH security and vulnerability scanning, with follow-up access fixes.
Google has turned its Ads API helper into a reusable agent plugin rather than a standalone project. For developers maintaining ad-tech integrations, the material change is that agent workflows can now ground themselves in current Protobuf schemas and execute validated reporting against real Google Ads accounts instead of relying only on model memory.
The non-Plus checkout migration is now an active compatibility boundary rather than an approaching deadline. Orders can continue while old post-purchase scripts, pixels or widgets stop working, making end-to-end conversion and app-behavior checks important after the cutover.
GitHub Agentic Workflows 1.2.x previews durable handoffs, hardened egress and queue recovery after GA; teams must distinguish pre-releases from stable deployment guarantees.
LiteLLM 1.107.0 remains a known compromised release. Its October 30 security review now sets out why signing failed to protect users and which fixes are complete versus only promised.
Cloudflare discloses cross-tenant GLM-5.3 Workers AI responses caused by a KV-cache rejection bug; SGLang v0.5.22 is recommended for disaggregated inference operators.
Beam makes a large agent-focused model commercially reusable without a bespoke licence, but the open weights are not a small local download.
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.
Muse Spark 1.3 is more than a routine model refresh: Meta is pairing stronger agent behavior with lower vendor-reported tool/token use at the same published unit price. Independent testing supports a capability gain, but max reasoning can consume substantially more reasoning tokens.
Supabase has implemented MCP Enterprise-Managed Authorization using identity-provider assertions, short-lived tokens and existing Supabase role boundaries. It gives organizations a central on/off switch for approved AI clients while keeping access scoped to the individual employee rather than sharing a powerful organization token.