#Tutorial/How-to

AIDSPy's official account highlighted a recorded office hours session showcasing Jev use cases and explainers. The quoted context says the session covered DSPy's Jev/System One implementation, the ReAnchor optimizer, and design patterns for selective compaction, tool approvals, and subagent delegation.

AIArtist 852 Hakoniwa made YUI, described as the first animated short created with Comfy Agent, which the ComfyUI team says took three days of focused work by one person at about 200,000 yen in total cost, excluding labor. The source says the film was made mostly with Seedance 2.5 and the making-of video with MiniMax H3, with Comfy Agent used to regenerate shots and compare video models.

AIIn a business risk monitoring test by @edwardirby, the Jev judge matched the report quality of an ordinary LLM judge while missing no investigations, versus the LLM missing 5 of 11. The LLM's threat scores also flip-flopped from 0.35 to 0.68 to 0.50 on the same threat, while Jev was 250x cheaper and 3-6x faster.

AIPerplexity's developer account says pplx-decider-v1-27b can triage customer support tickets, with escalations routed to the Agent API. The cookbook example uses the Decisions API for the initial decision and the Agent API for escalated requests.

AIAnthropic's ClaudeDevs account says its team used mods to build features in Claude Code, including the /diff command and AGENTS.md support. The post links to a blog article on Claude Code mods and invites developers to try them.

AIAnthropic is adding pre-built sample mods to the Claude Code Playground repo for developers to adapt. The post points readers to a getting started guide on creating Claude Code mods.

AIAnthropic's ClaudeDevs advises keeping Claude Code mods private or submitting useful ones to the Claude directory. Mods run with the same machine access as Claude Code itself, so users should install only mods from trusted sources.

AIHarrison Chase says model routing is a provocative term that lacks a clear definition, but offers a practical approach. His four steps are to understand tasks, understand the models, build the router inside the harness, and track outcomes, aiming to lower costs without a performance hit.

AIGoogle Workspace says Sheets canvas can turn static spreadsheet data into interactive tools such as Kanban boards, dashboards, and visual workflows from a simple prompt. Derek Snyder, Director of Product Marketing for Google Workspace, demonstrates the feature in the latest AI Boost Bite video.

AIExtropic post-trained Qwen3.6-35B-A3B with Prime Intellect for thermodynamic ML research, nearly tripling its held-out eval results in about 100 GRPO steps. The team built a custom RL environment with verifiers and trained on Hosted Training, Prime Sandboxes, and Prime Inference. This let Extropic avoid managing multi-node GPU infrastructure and focus on research.

AIZyphra published a paper and blog explaining how local mixing encodes relative position in global NoPE attention models. The work, titled "How Local Mixing Encodes Relative Position in Global NoPE Attention," is available on arXiv and on Zyphra's website.

AIHugging Face shows that training LFM2.5-2.6B with RL inside the agent harnesses themselves lifted held-out task success from 42% to 54% across four harnesses. Before training, the model solved 62% of tasks in Mini-SWE-Agent but only 33% in Claude Code, so the same model behaved very differently per harness. The approach uses an OpenEnv capture proxy to record tokens and logprobs, Harbor for tasks and sandboxes, and TRL's async GRPO trainer, with 31% fewer tool calls on already-solved tasks; training in OpenCode alone mostly improved OpenCode.

AINVIDIA announces that developers can build visual AI agents from a prompt using NVIDIA Cosmos and VSS 3.3. The post is a broadcast announcement that links to a live stream and provides no further technical details.

AICloudflare released Clef and Clef-flash, two decision models hosted on Workers AI and open-sourced on Hugging Face under Apache 2.0, and launched a reinforcement learning fine-tuning service. In Cloudflare's tests, Clef classified a domain in 2.2s versus 4.7s for gpt-oss-120b, and the models are Jev-API compatible. The company is offering fine-tuning first through a forward-deployed engineering team, with a self-serve platform planned later.

AIHamel Husain advises against building automated evaluators for every failure mode discovered during AI development. He argues that teams should weigh the costs of different evaluator types, such as code-based checks versus LLM judges, before building an eval.

AIHugging Face's Merve Noyan promoted a four-chapter YouTube series teaching viewers how to train AI agents using only open-source tools. The post links to the series' first video and is a brief call to learn agentic training.

AIPhysicist Matthew Schwartz describes building BootLoops, an open-source harness for exact quantitative calculations, after choosing problems suited to Claude's strengths. He reports that Claude solved long-standing integrals and found connections across ecology, population genetics, economics, and linguistics, with domain experts steering results toward questions those fields care about. The post states that the approach required constant human oversight, since Claude often overstated results and misjudged time.

Why it matters: The guest post explains why scientists often find current AI tools frustrating and offers a method for finding problems where AI and researchers match, backed by concrete projects.

AIManus 2.0 introduces Video Editor, which lets users refine videos Manus generates, including changes to music, captions, and cut timing, without regenerating the entire video. The article describes Manus creating explainers, launch films, and animations from a single prompt, drawing on web search, video models such as Seedance 2.5, and code for motion graphics.

AILangChain built a model router inside its open source coding agent Open SWE that picks one of three models for each thread. In an A/B test against always using GPT-6 Astra, the median cost per thread fell 64% with no measurable change in merged PR rate. The router runs on the thread's first message, using a base prompt, per-tier criteria, and a classifier model, and the post lists next steps including subagent routing and mid-thread re-routing.

AIHamel Husain has published a longer review of a new Claude Auto Eval plugin after many users asked about it. He invites readers to share their experiences using the plugin and how it went for them. The plugin is part of Claude's ability to help build evaluations and hillclimb on them, as described by @ClaudeDevs.

AIGoogle Flow publishes a guide to creative prompting with Gemini Omni Flash, covering video generation for films, marketing, and visual assets. The guide recommends high-level constraints, first and last frame visual anchors, tagged image, video, and storyboard ingredients, and granular mid-scene pacing edits. It also suggests transferring style and motion from reference images and videos.

AIFireworks AI has made GLM 5.3 Flash available for training through its Serverless Training API, open to all users. The model supports both vision and text inputs. Fireworks says it performs well on its benchmarks for agentic coding, document analysis, and tool use while remaining cost-efficient to serve.

AITerminal test runs miss multi-turn agent regressions, so Agent Clinic Episode 3 builds an automated eval suite for a LangGraph agent in 60 minutes. The post presents a four-step framework for moving from informal checks to benchmarking AI agents, with a link to the full guide.

AICursor's Eric Zakariasson shared a game-builder skill he has been using to build games with new models. The skill can be installed with the command npx skills add ericzakariasson/skills --skill game-builder.

AINVIDIA says a single prompt can build and deploy a visual AI agent for a manufacturing line in under 30 minutes, with alerts, video search, and incident reports. The method uses the new Build Vision AI skill in NVIDIA VSS Blueprint 3.3, and a tutorial is available for readers who want to build one.

AIAnt Ling can convert plain-language prompts into standalone, interactive Three.js pages covering topics such as an internal combustion engine, an optical-disc reader, paramecium organelles, and vector-field divergence. The output is runnable code rather than just an explanation.

AIAnt Ling reports that its Ling-3.1-flash model completed a roughly 20-hour Rust port of a C image library. After a performance regression caused by busy-waiting workers and a parallelism adjustment, the model recovered and reached an 8.015× speedup. All 30 correctness checks passed.

AINVIDIA and Nous Research published a hands-on walkthrough of NVIDIA NeMo Relay for collecting traces from Hermes Agent. The guide runs two example scenarios and shows the agent's calls and retries in Arize Phoenix. It also covers how Nous used traces and task results to evaluate fixes across repeated runs.

AIAgentic data science has AI agents explore datasets, choose modeling approaches, run analyses, and explain findings while data scientists frame questions and verify evidence. In an experiment, Claude Opus 5.0 given the vague prompt "Build me a model to detect fraudulent nodes" on a modified Elliptic Bitcoin dataset reported F1 0.87 and ROC AUC 0.99 using a random split that leaked a planted label proxy.

AIGoogle Gemini now offers skills, which are saved sets of instructions for specific tasks you repeat often. The post describes them as shortcuts that let users skip repetitive prompting and go straight to results.

AIIdeogram 4.5 turns a single room photo into a design canvas where furnishings, finishes, and palettes can be swapped one edit at a time. The room's architecture stays unchanged throughout the edits.

AIIdeogram recommends restoring an old photo in stages: first remove scratches and damage, then add color, then enhance. The post says trying to fix everything in a single prompt rarely works, so multi-turn editing lets each edit be refined separately.

AIGoogle Cloud introduced GKE Agent Substrate, an open-source execution runtime it says can run millions of sandboxes with 10x higher density than standard container runtimes. It also made GKE Agent Sandbox optimized for reinforcement learning generally available, alongside an orchestration SDK and native RL gym integrations. Google said GKE Pod snapshots can reduce AI inference start-up by as much as 89%, based on internal tests.

AINVIDIA announced a new approach to building edge AI through agentic development on NVIDIA Jetson, presented in a broadcast. The post provides no further technical details, figures, or availability information.

AILocal and desktop agents such as Claude Code and Codex are powerful largely because they can use the shell, which connects them to the whole CLI ecosystem. The post lists tools including git, ffmpeg, curl, pandoc, gh, cron, and ssh as examples. It also says the video itself was produced by an agent operating the shell.

AIKarl's AI Watts asks whether a menu-bar tool can switch models while preserving the existing conversation, so users avoid re-explaining their project each time. The post frames this as the reason they want to keep the menu bar tool, which the quoted post describes as magpie, a menu-bar switcher for 20+ agents including Claude Code and Codex that also offers a local gateway.

AIHamel Husain reviewed Anthropic's new build_eval and hill-climb commands in the claude-api plugin for Claude Code, finding it useful for discovering issues like human handoff, formatting, and voice agent problems. He criticized it for pushing evaluator creation before data review, asking for label validation in Markdown files, and bundling four failure checks into one broad call-transfer evaluator. Husain says he would hold off on using it for now.

AIKling AI says Kling 4.0 will support native video generation from 3 to 30 seconds, with up to 10 keyframes for timing control. The full model is scheduled for October 2026, with early access to the new creation page rolling out from September 28.

AIGoogle Developers Blog describes how Sparse VideoGen (SVG) routes video diffusion attention heads into spatial or temporal sparse masks and implements them as custom JAX and Pallas Splash Attention kernels on TPU v6e. In isolated single-chip tests with 75.6K tokens and 10 heads, the sparse variants retain about 38.87% of query-key pairs. The article argues that theoretical sparsity must be converted into hardware tile skipping to yield real speedups.

AIJulien Chaumond, who owns Hugging Face, recommends a DGX Spark guide written by @0xSero and published on the Hugging Face blog. The post itself gives no further technical details about the handbook's contents.