Follow the AI industry.

DeepSeek’s Super-agent research prototype tries to reduce the reminders and handoffs around software work. Individuals can try it, but someone must deploy and supervise it first.

The $200 monthly plan keeps a weekly allowance, while verification determines whether a temporary session cap remains.

Google plans a staged rollout of its next frontier model, with introductory token prices and wider availability still to come.

The hosted upgrade adds a faster option, while full model weights remain scheduled for release by November 4.

The downloadable model arrives after its hosted launch, with a custom license and a deployment footprint that depends on the serving setup.

The new route combines Google Cloud access and billing with an API operated by Anthropic, creating a separate organization for each project.

The collaboration turns selected crash tests into machine-checked claims about compiled binaries, with a smaller public proof set than the full reported experiment.

The proactive assistant runs on its own cloud computer, but its background checks and tasks consume the same allowance as other Claude work.

Anthropic’s new background assistant shares your Claude allowance and still needs your judgment. The useful question is which work it can take off your mind.

Four supported PHP branches have security updates. The coordinated disclosure also shows how AI findings still depend on maintainers and infrastructure providers to become protection.

The open source backend supports familiar PyTorch execution on Trainium2 and Trainium3, with compatibility and compilation limits that still matter for migration.

Anthropic’s security research has a concrete outcome in a widely used server. For teams trying AI audits, the useful question is whether a proposed change closes an unnecessary path while preserving the work the software must do.

DeepInfer gives developers a closer look at how DeepSeek serves its models. The decision to operate it depends on hardware, the missing service components and the workload that has to pay for them.

TorchNeuron gives PyTorch developers a familiar route onto Amazon’s AI chips. Library support, compilation waits and the cost of a complete job decide whether that route is worth taking.

The biotech workflow platform and its team will join Rosalind, extending OpenAI’s life sciences work beyond scientific analysis.

The cloud platform is testing a way to keep AI agents from waiting on the computers that execute their commands. Better hardware still has to become a better service for customers.

The Ohio training cluster already supports Muse models; its planned final scale and next hardware generation remain ahead.

The formal release reaches the API, M Plan and MiniMax Code, while subscription migration carries separate conditions.

Stockholder approval is still required, and any increase in the new fund's stake would be at the board's discretion.

Anthropic says it revoked Claude API keys believed to be affected; OpenCode distinguishes its hosted Console from the coding app.