Google Ads API v26 begins a twice-monthly update cadence. Minor releases remain additive and sunset with their major version, so developers need a faster discovery workflow rather than twice as many breaking migrations.
A restricted private-preview detector changes the compliance workflow, but Claude watermarking still cannot prove authorship or reliably detect short or lightly edited passages.
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.
The two August 28 changes move a common production-agent problem out of bespoke application code: builders can derive memory boundaries from authenticated JWT claims, enforce them with Cedar policy, and organize the stored memory using runtime tenant dimensions.
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.
Google’s Search generative AI setting separates AI-answer visibility from ordinary Search indexing and model-training preferences, with inherited settings and lost AI referrals to consider.
The JavaScript micro-app platform is winding down after four years. Billing has stopped, official migration guides are available, and open-sourcing is planned for February.
DeepSeek now charges for Search/Fetch calls made both directly and via DeepSeek Harness, Claude Code and Codex. Only successful nonempty 200 responses are billable.
GLiNER2.5-Decide attacks the same bounded-decision layer as Jev and CLM from a much smaller encoder architecture. Its strongest benchmark claims are vendor-produced, but CPU deployment and constrained joint decoding make it a materially different option for software-facing AI decisions.
GLM-5.3-Flash combines open weights, multimodal coding/agent capability and an 18B-active sparse architecture with a large anonymous pre-launch trial. Z.ai has already issued a chat-template correction for early downloads, showing that day-one self-hosted deployments need artifact-level validation as well as model benchmarking.
Jev, CLM and GLiNER2.5-Decide made bounded software decisions look like a distinct model category. OpenAI is now validating the same architectural split with a Luna-powered API designed to answer finite questions rather than generate open-ended prose.
The staged release is complete: GLM-5.3’s public weights and serving artifacts are now available. That makes Z.ai’s coding and cyber-capability claims independently testable while turning the earlier safety delay into a concrete self-hosting and audit decision.
The study moves the AI-search traffic debate beyond observational correlations: participants were randomly assigned to current Google Search, a version with AI features hidden, or AI Mode-only search during ordinary browsing. It is still a preprint and does not establish effects for every query or publisher.
OpenShell v0.1.8 hardens agent egress and filesystem policies, changes credential and OCSF audit schemas, and fixes gateway leaks. Existing integrations may need migration.
Shopify partners are now represented by platform-verified project history rather than customer reviews. That changes discovery and credibility signals, particularly for smaller agencies.
The premium Claude tier gets cheaper and faster, but the practical decision is when it beats Opus 5.5 on cost per successful task—and whether an integration can accept its API and data-retention requirements.
The interesting change is architectural rather than another storage feature: migration becomes a server-to-server transfer initiated through an S3-compatible PutObject or UploadPart call, with range and multipart support for large objects.
The 10GB Hobby storage cap has not changed, but the consequence of crossing it has. Vercel has removed the previous 30-day grace period for non-exempt deployments, shrinking the rollback and preview history free-plan builders can assume will remain available.
PyTorch 2.15 is now generally available. FP8 and faster MoE decoding improve some Mac AI workloads, while the vendor/contributor speed claims remain configuration-specific rather than universal.