The setup: ✔️40 hand-selected PRs from OpenClaw, mid-complexity (100–300 LOC excluding tests) ✔️ Thr... - 惯性聚合

推荐订阅源

Check Point Blog

CTFtime.org: upcoming CTF events

Stack Overflow Blog

Proofpoint News Feed

Microsoft Security Blog

The GitHub Blog

WordPress大学

博客园 - 【当耐特】

Cyber Security Advisories - MS-ISAC

Apple Machine Learning Research

博客园_首页

Full Disclosure

Google DeepMind News

奇客Solidot–传递最新科技情报

Help Net Security

Recorded Future

News and Events Feed by Topic

Vulnerabilities – Threatpost

Schneier on Security

aimingoo的专栏

Schneier on Security

cs.AI updates on arXiv.org

罗磊的独立博客

Privacy International News Feed

Application and Cybersecurity Blog

Hugging Face - Blog

Heimdal Security Blog

LINUX DO - 热门话题

Forbes - Security

美团技术团队

Security Latest

MIT News - Artificial intelligence

Tor Project blog

Cisco Talos Blog

宝玉的分享

Threat Research - Cisco Blogs

TaoSecurity Blog

Augment Code(@augmentcode)

Watch the full episode here: https://t.co/x5FzXbNYUL The IDE is dead. Now what? Full conversation here: https://t.co/urWTMCGqbW How do you keep up with AI? @gregorojstersek has advice for any engineering leader: The human reviews the design before any code exists. Our Code Review experts then read the full diff... A few we shipped to production like this, all on systems with thousands of active users, none of whi... Most teams point agents at small, well-scoped work. A ticket goes in, a tidy PR comes out, a human r... https://t.co/gf2G7OYoaX Claude Fable 5 has been suspended following a US government directive. Details here: https://t.co/ot... "There's never been a better time to be a software engineer", @JustinReock with the hot takes 🔥 Wa... Fable 5 is built for long-horizon work: investigations, multi-step changes, and end-to-end tasks tha... With models like Fable 5, model routing is more important than ever. We’ll be adding Fable 5 to our ... The bigger unlock is Fable 5 running in our unified agent platform, Cosmos. Pull context from your t... TL;DR: Fable 5 isn’t the right-sized model for every task, but when quality and depth matter (revie... Fable 5 brings a new level of capability to complex software engineering work. We've found it perfo... Fable 5 is now available to Augment Code users. At ~2x the cost of Opus 4.7, Fable 5 is a premium op... We're all experiencing the moving bar of "being AI native". How do we navgiate it? Watch the full e... TODAY: the first live look at Cosmos, the Unified Agents Platform. Join us at 10am PT to hear from ... Live this Friday, June 5 at 10 AM PT: the first look at Cosmos, our new Unified Agents Platform. Yo... See it live this Friday, June 5 at 10am PT. Full walkthrough of Cosmos, plus how our own team at Aug... Cosmos runs in your environment or ours, supports the models you choose, and provides the observabil... At the core is Augment's Context Engine. It helps agents understand how a codebase actually works, n... Introducing Cosmos: the Unified Agents Platform for software teams. Orchestrate a fleet of agents a... Cosmos gives your organization a single platform for running agents. Deploy our tuned agent experts... Four months ago we realized two things: 1. Individual developer productivity doesn't automatically ... Try it in Cosmos today: https://t.co/VANf6pg1nZ Opus 4.8 is now available in Cosmos. In our evals, the model demonstrates strong performance on lon... https://t.co/tWjZLYYCsF https://t.co/gEIxt9RMBF The team building Codex at @OpenAI has a front row seat to how engineering organizations are changin... The team building Codex at @OpenAI has a front row seat to how engineering organizations are changi... The demand for engineering managers is actually surging in the agentic coding era. Agents can write ... Uber's internal agent platform now generates 11% of all PRs across the company. Join a live convers... Download the survey: https://t.co/DO3YXsD91F "Excited, anxious, invigorated." That's how one engineering leader described going AI-native. We as... The engineering leaders we spoke to ranged from managers to CTOs, overseeing teams of 1 to 1,000+ en... At @augmentcode , we took a counter-intuitive bet on our AI architecture. Instead of using the prim... https://t.co/T8MuoEG48b We surveyed 219 engineering leaders in April 2026 and asked them what's actually happening inside th... Harvey built their coding agents to be collaborative by design. Engineers, PMs, and researchers all ... https://t.co/p81J9gjbvi Augment can do this because we are model agnostic. No single model wins every task, so we give our c... Prism is in the picker today: VS Code, JetBrains, CLI (/model), and web. Billing rolls up under a s... Today we're shipping Prism: a new option in the Augment model picker that efficiently routes each tu... @karpathy @jiayuan_jy @openclaw Full post by @VZhenylenko here: https://t.co/ERoEbco3ol Every runner used fewer tool calls and finished faster. The agents found what they needed in fewer ... Quality: basically unchanged for Auggie and Codex. Claude Code dropped −0.07, with more conservative... The Karpathy rules are the kind of thing you'd write at the top of a team style guide. Here is the ... We added @karpathy -inspired coding rules from @jiayuan_jy to AGENTS.md and ran 40 @openclaw PRs thr...

The setup: ✔️40 hand-selected PRs from OpenClaw, mid-complexity (100–300 LOC excluding tests) ✔️ Thr...

Augment Code · 2026-05-02 · via Augment Code(@augmentcode)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。