Intel
Page 07
Nous Research@NousResearch
Hermes has a new slash command: /loop. '/loop 5m <prompt>' re-runs the prompt every 5 minutes in the same session. Leave the interval off and it paces itself, checking often at first and backing off while nothing changes. Works in the CLI, desktop, and every messaging channel. https://t.co/ZxSnitg3t5
Why it mattersRecurring self-paced agent runs are a scheduling primitive most harnesses lack, so builders comparing agent runtimes now have a concrete reference implementation of interval versus adaptive polling.
LangChain@LangChain
In 17 minutes, @BraceSproul runs through everything you need to know about OpenWiki, an open source self-maintaining wiki. ✅ The core ideas behind it ✅ How it works ✅ Why docs built for agents look nothing like docs for humans ✅ What we learned from building it https://t.co/kpfB9UmwDz
Why it mattersAgent-readable documentation is becoming a design surface of its own, and this gives builders a working open source reference for how those docs should be structured and kept current.
Learn how to turn one giant AI-generated pull request into a clean, reviewable s
Learn how to turn one giant AI-generated pull request into a clean, reviewable stack and keep every layer in sync as feedback lands. 👇 https://t.co/kz7ZBWXz7e
Why it mattersReview throughput is the bottleneck once coding agents can produce thousand-line diffs, and stacking gives teams a repeatable way to keep each layer small enough to actually verify.
articlegithub
How Web Data Infrastructure Powers the Next Generation of AI — Patricija Žemaitytė, Oxylabs
Oxylabs on rebuilding a search API from a four-second baseline to 550 milliseconds, and why something that works in development, something that passes tests.
Why it mattersThe load-testing observation, that instrumentation at high request volume distorts the measurement it is taking, is a failure mode teams hit when scaling any high-throughput data pipeline for AI.
videoAI Engineer
The Rise of CaaS: Context-as-a-Service for Agentic AI — Omer Primor, Bright Data
Bright Data's Omer Primor puts the crossover at roughly 15,000 queries, past which building your own pipeline beats renting context.
Why it mattersIt gives a concrete break-even figure for the buy-versus-build decision on agent context data, which is otherwise argued on vibes.
videoAI Engineer
The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans — Corey Gallon, Rexmore
Corey Gallon on driving a browser through the Chrome DevTools Protocol so an agent's clicks travel the same path as a human's, escalating from synthetic click to real CDP input event to a jittered mouse path only as far as the page forces.
Why it mattersIt explains why browser agents silently fail on real sites and gives a concrete escalation strategy and control split that anyone building web automation can apply directly.
videoAI Engineer
Bringing agents onto the world wide web — Paul Klein IV, Browserbase
Browserbase's Paul Klein argues browser agents are limited by engineering rather than models.
Why it mattersIt reframes browser agent reliability as work any team can do now rather than a wait on the next model, and names the specific architecture choices that separate production systems from demos.
videoAI Engineer
MTS
Open Season
podcast
Listen
Computer Use at the Edge of the Statistical Precipice — Pierluca D'Oro, Programma Labs
A sub-megabyte script that never looks at the screen, built by replaying one recorded trajectory per task, tops deterministic benchmarks like OSWorld.
Why it mattersAnyone reading computer-use benchmark numbers is likely reading an artifact of deterministic environments and undersized confidence intervals, and this gives both the proof and the environment design that fixes it.
videoAI Engineer
How Cloudflare detects MCP traffic and helps secure it
Cloudflare on why agent traffic breaks the two assumptions behind human permissions, judgment and human speed, and the new controls it is shipping to detect and secure MCP traffic.
Why it mattersTeams running MCP servers get a way to see shadow MCP traffic and force agents through an approved path, which is the first practical control over what an agent can reach at machine speed.
blogblog.cloudflare.com
Secure all your internal vibe-coded applications — in one click
Cloudflare adds one-click Access policies for Workers.
Why it mattersAnyone shipping internal apps built with coding agents can now make every preview and production deployment private by default with an account-level policy instead of trusting each builder to wire up auth.
blogblog.cloudflare.com
Claude watermarks your code now
Anthropic is watermarking output from Claude models launched on or after 2 August, and this walks through how the marks work and why removing them already looks straightforward.
Why it mattersEngineers shipping Claude-generated code now carry a provenance marker they did not opt into, and the countermeasures are already public.
videoTheo - t3․gg
Refine After Generation: Toward Correct and Concise Patches in LLM-based Program Repair
Automatic program repair is now good enough that agentic systems routinely close real repository-level issues, so this paper asks a question the field mostly skipped.
Why it mattersQuantifies that a passing test is not a proxy for a clean patch: agent diffs are consistently bloated, and minimality prompts do not fix it.
articleWenqiang Luo, Jacky Keung, Xiaoyu Shi, Yicheng Sun, Boyang Yang, Zhou Yang, Haoye Tian
Does It Render Everywhere? A Study of Cross-Environment Compatibility in MLLM-Generated Webpages
Evaluations of AI-generated webpages almost always score visual fidelity in one fixed browser and device configuration.
Why it mattersPuts a number on a failure mode most AI frontend evaluation misses entirely, since visual fidelity is usually scored in a single fixed browser.
articleZiyun Guo, Jingyu Xiao, Yuqiang Sun, Yintong Huo
Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review
A single fully instrumented case study of a large-scale architectural refactoring carried out by an AI coding agent.
Why it mattersDocuments a specification-first protocol that carried an agent through a refactor the author judged infeasible incrementally, with enough instrumentation to check the claim.
articleJoel Abenhaim
Reading the signals: Helping your AI-built payment integration understand business intent
Stripe on giving an AI-built payment integration enough business context to read intent, rather than only calling the API correctly.
Why it mattersPayment code written by agents fails quietly when business intent is missing, and this is the payment provider's own account of how to supply it.
articleDavid Benchi
In Session 4 of the GitHub Secure Open Source Fund, 50 open source projects upgr
In Session 4 of the GitHub Secure Open Source Fund, 50 open source projects upgraded their security posture through AI-assisted workflows, maintainer expertise, GitHub security tools, expert guidance, and funding.
Why it mattersMaintainers now have a documented account of where AI-assisted security review helped and where it did not, across 50 real projects.
articlegithub
ClaudeDevs@ClaudeDevs
Hit your usage limit in Claude Code desktop? There's now an auto-continue checkbox. Turn it on, and it'll automatically continue where you left off once your limit resets. https://t.co/Zs7ZX67cly
Why it mattersAnyone running long Claude Code sessions against a usage cap can now have work resume automatically instead of restarting by hand.
articlebcherny
A weird experiment I've been trying the last few weeks is having Claude take ove
An experiment handing day-to-day app maintenance to Claude through a Slack channel, running daily routines across iOS, Android, desktop, web and CLI.
Why it mattersIt is a working blueprint for handing recurring codebase maintenance to scheduled agents, with real merge rates and the review gate that makes it safe.
Computer History builds on the Chronicle research preview with reduced token usa
Computer History builds on the Chronicle research preview with reduced token usage and more privacy controls.
Why it mattersDesktop-wide activity capture feeding ChatGPT and Codex changes what context an assistant has and what a developer is handing it, so the scoping controls matter.
articleOpenAI
🆕 @GoogleAI's Gemini 3.7 Flash is now generally available and rolling out in Gi
🆕 @GoogleAI's Gemini 3.7 Flash is now generally available and rolling out in GitHub Copilot.
Why it mattersCopilot users get another frontier model option for agentic work without leaving their existing setup. Model choice inside the coding tool is one of the few knobs that changes agent behavior immediately.
articlegithub
llm-gemini 0.33
The first llm-gemini release in a while, adding same-day support for Gemini 3.7 Flash along with gemini-3.6-flash, gemini-3.5-flash-lite.
Why it mattersGives anyone on the llm CLI same-day access to the new Gemini models, with reasoning traces and server-side tool calls available through a documented flag.
articlesimonwillison.net
Artificial Analysis@ArtificialAnlys
Artificial Analysis scores Gemini 3.7 Flash at 56 on its Intelligence Index, four points above 3.6 Flash, with an average time per task 40% faster than GPT-5.6 Terra, placing it on the intelligence-versus-speed Pareto frontier.
Why it mattersIndependent numbers show the Flash gain is concentrated in agentic and terminal work, which is exactly where coding agents live.
articleNousResearch
LongCat-2.0 from @Meituan_LongCat is free in Nous Portal for one week. It is a 1
LongCat-2.0 from @Meituan_LongCat is free in Nous Portal for one week.
Why it mattersA 70.8 on Terminal-Bench 2.1 puts LongCat-2.0 in serious contention for agentic coding work, and the free week is a real window to evaluate it against an existing stack.
AlphaSignal@AlphaSignalAI
Survey data putting the bottleneck at review rather than generation: GitLab finds 85% of 1,528 developers and buyers say reviewing AI code is the constraint, while Sonar finds 42% of committed code is AI-generated and only 48% always check before committing.
Why it mattersIt reframes AI code review from a volume problem into a question of which automated checks can fail a change without a human reading it.
Introducing Gemini 3.7 Flash
Google introduces Gemini 3.7 Flash, its workhorse model for coding and agents, three weeks after 3.6 Flash and shaped by developer feedback and algorithmic changes the team expects to carry into later models.
Why it mattersA cheaper Flash model with materially better issue resolution changes the default choice for high-volume coding and agent workloads.
articledeepmind.google
Cursor@cursor_ai
Cloud agents now start 3x faster so you can hand them ambitious, long-running tasks to execute from start to finish. This performance improvement comes from builds: ready-to-use development environments that Cursor prepares continuously in the background, at no additional cost. https://t.co/0JrSQomAob
Why it mattersStartup latency is the tax on delegating long-running work to a cloud agent, and this cuts it without a cost increase. It makes hand-off-and-forget task execution more practical.
ReactBench is a open source frontend coding benchmark Read more: Open source:
ReactBench is a open source frontend coding benchmark Read more: https://t.co/oce4yAbwOc Open source: https://t.co/lqaiIyLwMr
Why it mattersA new open benchmark for frontend coding gives practitioners a shared yardstick for judging which models actually fix React code.
articleaidenybai
🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening
DeepSeek Harness v0.1 opens in developer preview under MIT, built on the Cordis meta-framework around one idea.
Why it mattersAn open-source, fully pluggable agent harness from a frontier lab gives builders another swappable foundation to compare against existing frameworks.
articledeepseek_ai
Grok 4.6 Is INSANE – Is THIS a Frontier Model?
A hands-on test of Grok 4.6 across browser workflows, C++ game development, 3D CAD modelling, frontend design and FPS generation, asking whether it reaches frontier level.
Why it mattersLets engineers see whether Grok 4.6 is competitive on agentic coding tasks against a consistent benchmark set.
videoBijan Bowen
xAI just caught up (Grok 4.6 is here)
Grok 4.6 gains five points on the Artificial Analysis Intelligence Index to reach 61, but burns 30% more tokens per run and nearly doubles in price.
Why it mattersHeadline benchmark gains can be paid for in tokens, and this puts numbers on that tradeoff for Grok 4.6. Model selection for agent loops is a cost decision as much as a capability one.
videoTheo - t3․gg
DeepSeek@deepseek_ai
API pricing update 💰 With the V4 lineup release, we’re updating our API pricing and introducing peak and off-peak rates. Off-peak rates are 50% lower than peak, enabling more flexible workload scheduling. 📉 New pricing takes effect at 16:00 UTC, Aug 16, 2026 🕒
Why it mattersOff-peak rates half the price of peak change the economics of batch and background agent workloads, and the effective date is days away.
DeepSeek@deepseek_ai
We’re launching DeepSeek-V4-Pro today! 🚀 🔷 Major Agent upgrades with strong production gains! 🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, max for complex tasks. 🔷 Native OpenAI Responses API support, optimized for Codex with one-click setup. V4 Pro is now available on app/web.
Why it mattersA new frontier-class model with a reasoning effort dial and Responses API compatibility is a drop-in option for existing agent stacks.
articleopenai.com
The builder’s guide to GPT‑5.6
Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.
Why it mattersModel selection and Responses API mechanics are the levers that decide what an agent costs to run, and this is the vendor's own account of them.
articleopenai.com
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.
Why it mattersA frontier model at 750 tokens per second changes which agent loops and real-time flows are viable, and the tier is the access path to it.
The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior
A controlled study of tool architecture in coding agents.
Why it mattersSeparates what an agent can do from how its tools are shaped, and shows the shape itself changes behavior, which is the part most agent harnesses tune blind.
articleXiangzhe Xu, Hamidreza Saghir, Qianhui Wu, Marc-Alexandre C\^ot\'e, Tong Wang, Kiran Lakkaraju, Kexin Pei, Xiangyu Zhang
RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
A benchmark for LLM-generated Triton GPU kernels that moves past PyTorch-to-Triton translation, scoring end-to-end framework performance rather than individual kernels and replacing hand-written evaluation scripts models could exploit.
Why it mattersKernel generation results reported on translation-style benchmarks overstate what models do on real framework code, and this gives a harder target measured on end-to-end performance.
articleJinjun Huang, Zhongzhen Wen, Tongtong Xu, Meng Yan, Xin Xia, Zhongxin Liu
Harnessing LLMs for Document-Guided Fuzzing of Python Libraries
VistaFuzz uses a locally served open model to read API documentation and generate fuzzing inputs satisfying both per-parameter constraints and dependencies between parameters, evaluated across 7,718 APIs in twelve Python libraries.
Why it mattersShows a local model reading docs well enough to drive fuzzing at scale, and quantifies how much of an API surface has cross-parameter constraints that naive generators break on.
articleBin Duan, Tarek Mahmud, Meiru Che, Yan Yan, Naipeng Dong, Dan Dongseong Kim, Guowei Yang
Self-Evolving Embodied Agents via Skill-Harness Evolution
SHAPER adapts embodied agents to new environments without training.
Why it mattersArgues that most of the adaptable surface of an agent lives in its skills and harness rather than its weights, and shows a train-free loop that improves that surface using the same frozen model.
articlePeidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li
Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
An argument that skills learned as programs cut agent cost most, because deterministic action sequences achieve cheaply what would otherwise take trial and error and risk degenerate behaviour over long horizons.
Why it mattersSkill design is usually argued on capability; this puts a cost frame on it and gives a concrete reason to prefer program-shaped skills over prose ones in long-horizon agents.
articleZixi Huang, Xiheng Wang, Andrew Wang, William Jurayj, Bernal Jim\'enez Guti\'errez, Daniel Khashabi, Nicholas Andrews
Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction
Session constraints such as do not delete any emails until I confirm are silently dropped when context is compacted.
Why it mattersAny long-running agent that compacts context can quietly discard the safety instruction a user gave it earlier in the session, and this quantifies how often that happens rather than leaving it as folklore.
articleZhiqi Wang, Yichi Zhang, Dongwon Lee, Yuchen Yang
DeepSeek V4 Pro Is HERE – Is THIS the BEST Open Model Yet?
A hands-on test of DeepSeek V4 Pro at official release across browser workflows, C++ game development, FPS generation, 3D CAD modelling and cinematic game creation.
Why it mattersGives practitioners independent evidence of how DeepSeek V4 Pro handles real coding workloads before they route production traffic to it.
videoBijan Bowen
Gemini 3.7 Flash now available on AI Gateway for 50% off
Gemini 3.7 Flash is on Vercel's AI Gateway at half price until the end of 2026, with better issue resolution, less time stuck in failed agent loops.
Why it mattersIt is the cheapest immediate path to the new Flash model inside an existing coding agent, with a dated discount attached.
articleJoe McKenney
GLM 5.2 free for eve agents through August 27 via Blackbox on AI Gateway
GLM 5.2, Z.ai's open-weights coding model with a 1M-token context window, is free for eve agents through 27 August via Blackbox on Vercel's AI Gateway.
Why it mattersA dated, free window on a 1M-context open-weights coding model is a concrete access change with the migration path spelled out.
articleShar Dara
Introducing Agent Effectiveness
Introducing Agent Effectiveness By Factory - August 13, 2026 - 2 minute read Product Share See how Factory usage maps to delivery speed, work priorities.
Why it mattersTeams running coding agents at scale have had no principled way to connect agent spend to shipped work, and this is a first-party attempt at it.
articlefactory.ai
What We Learned by Reproducing 2,200 papers from ICML
Reproduction: Towards Optimal Robustness in Learning-Augmented Paging 🎯 Explore project logs, code, and traces in an interactive logbook
Why it mattersLarge-scale reproduction data tells practitioners which published results actually hold up before they build on them.
articlehuggingface.co
Grok Build is now available in the AI SDK harness layer
Grok Build joins Vercel's AI SDK harness layer through the same HarnessAgent interface as Claude Code, Codex, Deep Agents, OpenCode and Pi.
Why it mattersTeams already running HarnessAgent can swap in Grok Build without touching application code. The supported-runtime list is the practical menu for anyone abstracting over coding agents.
articleFelix Arntz
Use ACP-compatible harnesses with the AI SDK harness layer
Vercel's AI SDK harness layer now wraps the Agent Client Protocol itself rather than individual runtimes.
Why it mattersAnyone building on top of coding agents can now target a protocol instead of maintaining one adapter per runtime. That collapses the integration cost of supporting a new harness to a small config block.
articleFelix Arntz
Computer-use models will agentify the web, not APIs — Dhruv Batra, Yutori
Yutori's Dhruv Batra argues the web will not meet agents with APIs, because the long tail of 200 million sites will not ship MCP servers.
Why it mattersA clear case against betting agent architecture on the web meeting agents halfway with structured interfaces.
videoAI Engineer
From RL to IRL — Gaurav Mishra, Amazon AGI Lab
Amazon AGI Lab's Gaurav Mishra on browser agents meeting reality.
Why it mattersReframes agent reliability as training for recovery rather than thickening the harness around the model.
videoAI Engineer
An index of the vibe-coding frontier. Corrections welcome.