Updated
Updated
AIVercel has added Jev to the AI SDK for Python, and the team tested it in two experiments: detecting whether typed text is Python or English, and writing Python one decision at a time. The main post is a short endorsement praising a writeup about Jev and Python.
AIAnthropic's Lydia Hallie explains that mods are plugins with special functions that let custom code run inside Claude Code, working like middleware. She notes users can simply ask Claude to write them.
AIThe vLLM team integrated Helion, a PyTorch-native kernel DSL, into vLLM's linear backend, using per-shape autotuning to select among Standard GEMM, Split-K, and Swap-AB variants. On NVIDIA Hopper GPUs, the Helion backend outperformed the default CUTLASS and DeepGEMM backends across the evaluated models, with more than 10% throughput gains for some workloads. The work focuses on FP8 and INT8 quantized GEMM.
AINVIDIA reports that fine-tuning Nemotron 3.5 ASR reduced word error rate on Najdi and Hijazi Saudi Arabic from 55% to 30%. The post says a new tutorial shows how to adapt the model for other dialects and languages.
AITogether AI's CPO and product team outlined how they use AI to make the whole team more productive, not just individuals. The approach includes a shared context repo readable by any AI harness, cutting half a day of research to about 5 minutes, and evals that test their product the way agents actually use it.
AIGoogle Cloud's DevEx program sprint tested agent governance on Gemini Enterprise using standard external accounts and no internal shortcuts. The goal was to identify and fix developer friction in building enterprise AI.
AIHamel Husain recommends binary pass/fail labels over 1-5 Likert ratings when evaluating AI systems. He argues that binary labels force clearer thinking, produce more consistent labeling, and are significantly less complex to operationalize.
AIAirbnb CTO Ahmad Al-Dahle, who joined from Meta in January, says 60% of the company's code is now AI-authored and pull-request throughput per engineer is up about 1.6x. Roughly half of Airbnb's support tickets are now resolved purely by AI, which the company tested with synthetic data before production. Airbnb's internal context graph Everest helped speed up the grocery delivery and airport pickup services, which took eight to nine months and about six weeks to build, respectively.
AIThe team at @thesystms built a creative agent in 48 hours, and @ingi_erlingsson documented how he reads a moodboard, starting with feeling, then color, tone, and camera. @armandgw turned that process into a Krea Agent skill.
AIArchitectural Decision Records (ADRs) give coding agents durable project context, helping them distinguish intentional decisions from implementation details. Agents can over-apply accepted but obsolete ADRs, so the author recommends explicit AGENTS.md instructions treating accepted ADRs as binding, prompting agents to flag conflicts, and keeping each ADR current rather than recording amendment logs.
AIUsing an AI agent, the author rewrote a desk hardware pixel clock in Rust and linked it to the working status of both Claude and Codex agents. The device also monitors quota resets in real time and shows the day's token consumption. The quoted post notes the project ties into Claude Code's session state with parallel-session support, and says Claude's visual design was far stronger than Codex's.
AIFollowing @karpathy's advice, write ASD-STE100 into the system prompt.
AIServiceNow CoreAI introduced AutoSynthData, which uses a target model's failures and a stronger teacher's successes to generate and validate new agent training tasks. In EnterpriseOps Gym experiments, the Hybrid domain produced 2,000 samples and raised Gemma-4-26B-A4B-it mean Pass@1 by 7.2 percentage points, while the ITSM domain produced 1,994 samples and raised it from 18.77% to 27.18%.
Why it matters: The post shows how failure analysis, teacher demonstrations, and verifier checks combine into a repeatable pipeline for generating targeted agent training data.
AIEvery's senior editor describes moving from single-thread chatbot prompting to delegating complex projects to teams of coordinating subagents, using skills, orchestrator threads, context packets, MCPs, and computer use. He says a subagent workflow verified employee equity costs across multiple grants, strike prices, and vesting schedules, and returned a draft Slack message for approval. The shift was prompted by a June tweet in which Codex placed a colleague at Level 5 of the "Eight Levels of AI Adoption" framework.
AICreative director Johnson Sheng tested Kling 4.0 for commercial video production, focusing on stability during fast camera moves and dynamic action. He reports stable motion in whip pan and handheld push-in shots, a 30-second single-take fight scene, and consistent props and characters across scene changes. The post also covers performance and emotion control through prompt adjustments and multilingual generation. Kling states Kling 4.0 is in closed beta with an official launch planned for October, supporting up to 4K resolution and 10-bit HDR output.
AIClaude Code can now be modded to change how it behaves, customize its UI, and add custom features. Mods are written in a few lines of TypeScript or generated by Claude, and ship inside plugins installed with /plugin in the CLI or desktop app.
AIAndrej Karpathy says people will spend more time understanding language model outputs and suggests better formats than plain text. He recommends asking for ASD-STE100 controlled-language explanations, diagrams, interactive HTML pages, or custom explainer videos, and he is most bullish on the video format.
AIThe article compares LangChain/LangGraph and CrewAI workflow orchestration with OpenRouter's native model and provider routing. It says OpenRouter's models parameter provides an ordered, error-driven fallback list, while LangGraph and CrewAI handle state, memory, and delegation. Frameworks can also run on OpenRouter as the model layer underneath.
AIA post from TypeSafe AI promotes Jev, a tool it says gives AI bots a way to listen. The quoted post from @SoCalJayF describes using Jev as a semantic VAD in a real-time voice AI, combining the live transcript and recent conversation to judge whether a user has finished speaking, including through hesitations and pauses. The integration was built with Agora ConvoAI.
AIFireworks reports that numerical mismatch between training and rollout engines can destabilize reinforcement learning, with a GLM 5.2 experiment showing collapsing reward without alignment and stable reward with it over 25 steps. The post notes that MoE models add further alignment challenges, as Qwen3.5-MoE differences in expert output combination caused disagreement even when one implementation used higher precision. Fireworks says it co-develops its trainer and rollout engine to keep frontier RL training aligned across numerics, kernels, and MoEs.
AI@MicrosoftAI @MicrosoftAI STT plugin guide here:
AIReplit says users can ask its AI to analyze signup funnel data and identify where to increase activation, then follow up by requesting a dashboard. The post frames this as a way to reach a first win without knowing the final output in advance.
AIAnthropic's Thariq describes Claude Code mods, which can read conversation scope such as turn count and token usage. Mods run in process, so they can spawn subagents, parse their results with structured output, and modify the UI, which hooks cannot do. Mods ship inside plugins and are installed with /plugin in the CLI or desktop app.
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話 Hakoniwa made YUI, the first animated short film created with Comfy Agent, in three days of focused work for about 200,000 yen excluding labor. She used the Agent to regenerate shots, compare video models such as Wan, MiniMax H3 and Seedance, and check outputs against her character sheet. The main film was made mostly with Seedance 2.5, and the making-of video with MiniMax H3.
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'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.
AIExtropic designed the tasks and reward, while Prime Intellect supplied the RL infrastructure, including verifiers for environment construction, Hosted Training for the RL loop, and Prime Sandboxes for executing model code. Prime Inference serves the LLM judge and frontier baselines in the same workflow.
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.
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 says the company already offers four video series on YouTube for viewers who want to learn how to do it. She links to one playlist in the post, but the post does not specify which topic the series cover.
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.
AII used AI to further develop this pixel clock at home, directly linking it to all the status of Claude Code on my computer, with support for parallel sessions. To be honest, when it comes to aesthetics, Claude is still far too strong. The results Codex produced were genuinely ugly, I'm in tears...
AIAllie K. Miller argues that people can change how they use AI within one weekend by abandoning three habits: prompting, typing, and relying on a computer screen. The post offers no specific tools, products, or steps beyond these three directives.
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.
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.
AILatent.Space shares a podcast episode in which OpenAI's AriX and Nikunj Handa discuss OpenAI's new agent stack. The episode covers Computer Use, Dots cloud computers for agents, and the Decisions API, which the speakers say went from idea to product in weeks.
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.