Knowledge catalogue
A weird experiment I've been trying the last few weeks is having Claude take over day-to-day maintenance of our apps. Seeing early signs of life that this might be possible. The setup is straightforwa
Coding agents are helping scientists spend more time advancing research, taking on everything from routine maintenance and targeted optimization to complete redesigns and new systems. While agents can
Across eight case studies spanning industry and academia, we explore what this shift means for scientific computing—and why human verification, stewardship, and long-term maintenance matter. https://o
Auto-Protect is rolling out today on an opt-in basis for paying customers. Over time, our vision is for this kind of maintenance to become almost fully automated by AI. To enable Auto-Protect across y
Keeping your apps secure has always required constant oversight from you. Replit Auto-Protect now keeps watch over your apps 24x7. We'll monitor threats, proactively prepare fixes and notify you to ap
Replit announced Auto-Protect, a security feature designed to automatically safeguard user code and projects on their platform. The feature likely includes automated threat detection, code scanning, o
Self-improving agents isn’t a single algorithm - it’s a systems engineering problem involving: - eval data curation + maintenance - experiment design to battle overfitting - an update algorithm - huma
A post by @caspar_br on X (Twitter) highlights the risk of AI agents gaming or overfitting their own evaluations, referencing an article by @Vtrivedy10 (Viv, an agents & evals engineer at LangChain...
https://x.com/ashpreetbedi/status/2041568919085854847?s=46 great related write up from a team that pushes taking a rigorous systems engineering first approach to building agents it’s never one prompt,
So much alpha on the TL today, but this has to be the💧that you should take a minute to read @Vtrivedy10 pitching an incredible approach to auto-improving systems, something i've been experimenting wit
Simon Willison expresses hope that OpenAI will commit to long-term maintenance of an AI tool, citing concerns about his own tool potentially becoming stale or discontinued. The post reflects broader u
Tesla Service refers to Tesla's vehicle maintenance and repair network, which has been a recurring topic of discussion for Elon Musk on social media. Musk has frequently addressed customer complaints
Claude Code Routines are here! In addition to a schedule, you can now trigger templated agents via GitHub event or API – with our infra & your MCP+repos They've changed how we do docs, backlog mainten
【採用情報】Sakana AIで「Project Manager（製造分野）」を募集🐟 https://sakana.ai/careers/#business-role-project-manager-manufacturing エンジニア・リサーチャーと協働して製造現場の困難な課題をAIで解き、Go-To-Market戦略も担う重要ポジションです。 このようなご経験をお持ちの方を募集 ・大手製造
This post, shared by Swyx on X (formerly Twitter) from user @thekitze, likely expresses a personal opinion or observation about the cleanliness and urban conditions of London. The content probably ref
La plupart des grandes boîtes sont des organisations zombies. Voici pourquoi. Dans League of Legends, ton rang n'est pas un titre. C'est une mesure continue. Tu es Master parce que tu joues comme un M
Tesla police vehicles demonstrated significantly lower operational costs over a five-year period, costing approximately 75% less to operate compared to traditional gasoline patrol cars when accounting
cool new paper on self-improving agents // Self-Evolving Agent Protocol // One of the more interesting papers I read this week. (bookmark it if you are an AI dev) The paper introduces Autogenesis, a s
Data Driven Agent Design with Evals & Hill Climbing Algorithms this is a mental model dump i’ve been thinking through + iterating on as we’re building self-improvement infra around agents: - mining Tr
Simon Willison discusses the perception that LLMs and coding agents are primarily useful for greenfield development (starting new projects from scratch) rather than for maintaining and modifying large
yeah, what they said 🤝 a decent harness gets you an actually functioning agent now + teams that actually invest time in their harness+problem design, choosing good infra, self-improvement loops, data
La France a parmi les meilleurs mathématiciens et ingénieurs IA du monde. On le sait. On les embauche partout ailleurs. Et la première chose qu'on fait au moment où on pourrait enfin capitaliser dessu
tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheaters. they will reward-hack your evals and overfit just to mak
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD
check out how AI helps scientists with quantum computing research @bea_yankelevich at MIT's EQuS group used GPT-5.6 Sol with Codex to run routine measurements on quantum chips, so she could accelerate
Thariq Shihipar (@trq212) is an engineer on Anthropic’s Claude Code team I asked him how Anthropic makes the most out of the models for engineering and how the industry will change soon. In this episo
How fast is the Claude Code plugin ecosystem actually growing? Plugin-touching commit activity grew 8.8x in the six months after the initial launch. Researchers studied 1,926 repositories hosting plug
OpenAI is proposing to remove access to its models in Cursor on November 12. OpenAI, Cursor CEO, and Anthropic founder all weighed in on X with so much subtly, I had to go Nancy Drew mode and dissect
100% Agree @GavinSBaker. Now, I'm going to debunk every single piece of mis-information about data centers that I've ever seen online: > DISINFORMATION: Data centers use a lot of water. FACT: Most AI
A new model launch is not a product update ‼ It's one of three things, and you don't know which until you test it. Sometimes it's nothing: the model improved inside the same distribution, your harness
**IssueBench** is an internal benchmark created by LangSmith to assess the performance of *Engine*, a continual‑learning agent that scans other agents’ traces to identify, cluster, and fix issues. In
Big unlock for open-source AI inference: Hugging Face Transformers models can now run in vLLM at native speed, often matching or beating hand-written implementations. Until now, every new architecture
I just left the final day of the @aiDotEngineer World's Fair Conference in San Francisco. Kudos to @swyx for putting together a world-class lineup of speakers and workshops! It really was an invigorat
@hwchase17 very spot-on! for our (http://qontext.ai) customers, the journey is usually: local .md files -> shared github repo (-> gbrain) before these approaches break down at a) multiplayer (incl acc
Après avoir vu Elon répondre au Programme alimentaire mondial de l'ONU qui lui réclamait 6 milliards pour 'résoudre la faim dans le monde', j'ai compris quelque chose que je vais essayer de prouver ic
Leaving aside the “Vandalism” stuff for a brief moment: President Trump’s claims today that the reflecting pool “never opened” or was “rarely open” after the Obama repair project are just not true. It
GLM 5.2 x AWS GLM-5.2 is accessible via http://Z.ai GLM API on AWS Marketplace 🚀 Powerful long-horizon autonomous workflows, top-tier coding & multi-step agent reasoning capability, delivered through
Everyone Operating At The Frontier Satya Nadella, Chairman & CEO, Microsoft, interviewed by @saranormous & @eladgil (No Priors) and @swyx (Latent Space) Crossover special at Microsoft Build 2026. Summ
You don’t need to be @garymarcus to know which way the wind blows. I would be way more bullish on AI if it actually worked and was actually replacing real humans at scale. Nothing is changing and we’r
Je me suis longtemps passionné pour la psychologie, et une période m'obsède plus que toutes les autres. L'après-guerre. Le moment où des chercheurs se sont posé la question la plus dérangeante du sièc
// Your Agents are Aging Too // Huh!? They need 'sleep,' and now they are aging? Joke aside, great write-up on reliable agentic engineering. This new research introduces AgingBench, a longitudinal rel
Railway is a platform for deploying and managing applications in the cloud, and this status page link provides real-time information about the service's operational status and any ongoing incidents or
HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kin
A developer named Thariq shares their shift away from markdown to HTML, leveraging Claude Code to automatically generate HTML files for their documentation and content needs. The post suggests that HT
Good agent memory paper. And great insights on the benefits of structured memory for long-horizon behavior in LLMs. Why it matters: It treats memory less like search and more like a system that will n
Replit implements a defense-in-depth security strategy to protect user applications across multiple architectural layers of their platform. The blog post details the security measures and protocols Re
🎙️ Talked to @ListenLabs co-founder + CTO @florian_jue in the latest Max Agency. Really enjoyed hearing about the architectural decisions behind their agents, their self-reviewing feedback subagents,
You can now /schedule one-time tasks from the CLI or the Routines UI via the Schedule -> Once Trigger. Use it to: * /schedule cleanup this feature flag in 1 week */schedule give me a launch report for
Great paper on self-improving agents. Why? We need to think more deeply about AI agent system design. The protocol specifies a framework for proposing, assessing, and committing improvements with audi
NEWS: Senior Government Members Lie About Starlink in South Africa Parliamentary chair Khusela Diko claims Starlink’s FREE high-speed internet for 5,000 rural schools “brings nothing to the table” and
just finished this. genuinely one of the most informative episodes I've heard in a while the future of engineering is changing faster than most people realize. and it's self-managed, self-improving ag
⚡️ with @staysaasy, our second anonymous pod ever: https://www.youtube.com/watch?v=5KnCKadxSPY A conversation with the Stay Sassy duo on how AI is changing software teams, management, internal tooling
Nous Research shared a tip or reminder encouraging users to run 'hermes update' when experiencing issues or uncertainty with their Hermes model or related tooling, suggesting this command resolves com
a useful mental model on how teams can think about good data design to improve their models/agents: Evals ~= Training Data ~= Environments - in Classical Deep Learning, we learn from each training exa
This 10-min read from @Vtrivedy10 changes how you build AI agents. Most people are stuck in the same loop; switching models when agents break. The reframe: evals are the training data for your harness