All AI news

AIThe vLLM blog guide explains how separating prefill and decode, and moving tokenization to a CPU-only render tier, can keep token streams from stalling under load. In a two-L40S test on Qwen2.5-7B, collocated p99 inter-token latency reached 169 ms at 0.4 req/s while disaggregated serving stayed between 25 and 52 ms. The guide notes that the gain depends on fast KV cache transfer, and it includes setup code for NIXL-based serving and the render/derender API.

AISparse attention cuts per-operation KV cache reads but does not reduce overall memory capacity, so top-k cache misses still depend on HBM. SemiAnalysis's InferenceX estimates GB200 at about $0.044 per million total tokens at 150 tokens per second, roughly 12% below MI355X running ATOM at $0.049. Neither system holds a uniform cost advantage across the tested 100, 125, and 150 tokens-per-second targets.

AIPerplexity Developers released a cookbook recipe that combines Profiles, Skills, and managed connectors to build an incident responder. The recipe shows how the agent reads Datadog telemetry, diffs code in Sandbox, and posts an update to Slack.

AIGoodfire has published a practical guide to sparse autoencoders (SAEs), linking readers to the full blog post for details. The post itself offers little beyond the title and link, so no further specifics can be confirmed from it.

AIEdy Massih, owner of Edy's Grocer in Greenpoint, Brooklyn, uses Gemini to scale family Lebanese recipes into catering batches, automate aisle-by-aisle shopping lists, and adapt menus for dietary restrictions. He says the tool handles the math and logistics, freeing him to spend less time on administrative tasks.

AIMastra's guide explains how teams can run agents under GDPR, with self-hosted deployments in any EU region or a platform environment created with --region eu. It covers PIIDetector redaction before data reaches the model, SensitiveDataFilter for trace fields, and retention and deletion handled in the team's own database. Mastra says it offers a DPA with EU Standard Contractual Clauses, a SOC 2 Type II audit, and no training on personal data.

AIKling AI's blog outlines a structured prompt method for basketball league logos, covering league identity, basketball symbol, style, colours, and composition. It provides six example prompts for professional, modern, youth, retro, minimal, and street styles, and shows how to generate concepts with Kling IMAGE 3.0 from text or reference images.

AIXiaomi MiMo reports that tool-call repetition in MiMo-V2.6 reached over 0.05% of responses across agent harnesses, causing stalled agents and wasted context. The team traced the cause to an RL flooding penalty set at 32 calls per turn, which missed smaller excess behavior, and replaced the approach with a specialized teacher distilled via MOPD. Repetition rates for both Pro and Flash dropped substantially, at roughly $90,000 versus an estimated $2.31 million for the alternative fix.

Why it matters: The post traces an agent failure to a reward blind spot and compares the costs of two fixes, offering a transferable debugging method for RL-trained tool-calling models.

AIHiggsfield AI published an open-source breakdown of its "Passport Rush" project, including every prompt and asset used. The post links to the project page on higgsfield.ai for readers to explore the materials.

AICanvases in the GitHub Copilot app are customizable interfaces that you and the agent share, such as kanban boards, dashboards, or checklists. You create one by running /create-canvas and describing the workflow, what you can do in the interface, and what the agent can do. Changes made by either you or the agent appear immediately in the shared canvas, and completed canvases can be saved as reusable extensions.

AIGoogle Cloud has launched a managed reinforcement learning fine-tuning service (RLFT) that lets customers adapt Gemini models using a reward function they define instead of labeled answers. Users supply prompts and a reward function, while Google handles the RL infrastructure and proprietary model internals. The guide advises exhausting prompting and supervised fine-tuning first, and notes that RLFT suits tasks that are easy to score but hard to demonstrate.

AIUsing the Neuron Kernel Interface, Reactor and Amazon's Neuron Science team built a kernel-centric path to real-time autoregressive diffusion video generation on Trainium. They addressed dynamic shapes, memory access patterns, and cache management, which are hard for generic compilers, and developed techniques intended to generalize across models.

AIMicrosoft's Foundry Agent Service preview lets developers attach a named, ordered egress policy to a hosted agent, allowing only approved destination hostnames. The walkthrough uses an invoice agent, an Audit-mode RAI policy with a Deny default, and Allow rules for two finance and vendor hosts, configured outside the agent code. Network egress controls are preview features, not GA, with no preview SLA, and are not intended for production use.

AILovable describes how its Chats feature lets a workspace-level chat agent hand work to project builder agents and receive progress back. The design records each agent's history as an append-only, forkable trajectory, and passes messages through durable inboxes that activations wake. Agents can suspend at iteration boundaries and resume on freshly deployed nodes without killing long-running runs.

Why it matters: The post details how trajectories, inboxes, and activations let agents share work and resume after deploys, useful for designing comparable agent systems.

AIKling AI's blog identifies six limitations of current AI video generation, including temporal consistency, character consistency across shots, unrealistic physics, long-form generation, fine details and text, and prompt control. It recommends workarounds such as reference images, shorter single-action clips, storyboards, and adding text or logos in post. The article says Kling VIDEO 3.0 and VIDEO 3.0 Omni offer reference-based subject consistency to help reduce these problems.

AIThis guide compares six watermark removal tools, including Kling AI, HitPaw Watermark Remover, Picsart, Adobe Photoshop, Fotor, and Cleanup.pictures, based on mark type and editing control. Kling AI's IMAGE 3.0 uses natural-language prompts and annotated images to rebuild marked areas in context, while IMAGE 3.0 Omni adds refinement with native 2K/4K output.

AIOpenClaw lets users send files to a paired computer where their agent works, then return finished files in chat. Memory and supported Skills can also be stored on that paired computer. Setup requires host configuration, permissions, and matching OpenClaw versions.

AIAfter a restart, OpenClaw can return unfinished conversations with their saved history, progress, and tool results. The agent checks earlier actions before continuing interrupted helpers, while chats the user stopped remain stopped.

AISimon Willison had a voice conversation with his blog's Datasette backup through datasette-mcp, which is now accessible from the ChatGPT iPhone app. The quoted post says ChatGPT Voice can now use plugins and run on GPT-6 Astra, Sol and Luna in ChatGPT Work on web and mobile.

AIClaude builds a model of a program's most complex parts, such as state machines or race-prone code, and searches that model for counterexamples that signal suspected bugs. It then reproduces those bugs and fixes them in the code. The post clarifies that the whole codebase is not formally verified, only the riskiest sections are modeled and checked.

AIAnthropic says it made claude.ai 3x faster in two weeks, and the same speedup applies to the Desktop app. A linked blog post explains how the team used Claude to measure, debug, and improve performance, and includes prompts and methods.

AICursor's Eric Zakariasson shared a prompt for improving an LLM agent harness to lower token cost per completed task without losing quality. The prompt covers the system prompt, tool definitions, cache layout, tool results, compaction, and subagents, and reports that one team's round of these changes cut overall token cost about 7%.

Why it matters: The prompt gives a concrete checklist for cutting agent token cost per completed task, with tested figures on cache layout, tool offloading, and compaction.

AIAnthropic published a write-up on how it made the Claude frontend faster using agentic optimization techniques. The post coincides with Max Woolf's separate blog post showing that prompting agents can make code faster than current state-of-the-art libraries, with prompts and benchmark results included.

AIInferact says vLLM maintainers used megakernel optimization to reach 700 tokens per second per user on TPUv7 running Kimi K3. SemiAnalysis, which shared the work, reports this is 56% better performance than Nvidia's GB200 NVL72. Inferact links a full technical breakdown of the TPU megakernel work on its blog.

AIGitHub rebuilt the pull request view in the GitHub Copilot app to keep review fast on very large diffs, testing it on an open source pull request with 2,200 files, over a million changed lines, and more than 400 inline review comments. The core difficulty is that review comment heights can only be measured at render time, which breaks the fixed-geometry virtualization used for code-only diffs. GitHub split the document height into a deterministic code domain and a separately measured domain for comment blocks.