All entries

If you build with MCPs, this one is worth reading. (bookmark it) The paper covers five recurring MCP server patterns across fifteen independently developed servers. That taxonomy is useful because I s

In a new interview with the Washington Post's @ben_guggenheim, ControlAI's US Director Connor Leahy explains why nobody really understands how AI works, the race to uncontrollable superintelligence, a

inference reliability has historically been a tax on devs that only large well-funded startups could afford: reserve GPUs in advance, sign a contract, guess your peak throughput requirements. everyone

Introducing SWE-Together: a multi-turn benchmark built from real user–agent coding sessions. Coding agents are often benchmarked like exam-takers: given the full spec up front, then graded on the fina

Muon optimizer shows faster training speeds compared to traditional optimizers, but analysis reveals it sacrifices the simplicity bias that older optimizers maintain, potentially impacting model gener

it's a sad day when we stop learning. nothing quite replicates the pace and structure of college, but Independent Studies has become my version of continuing education post-grad. some of my favorite c

Sebastian Raschka announced the availability of a book through Manning Publications (with immediate shipping) and Amazon (available for preorder with delivery in a few weeks). The specific book title

It's not just the Lutnick sons cashing in on the Trump family's White House self-dealing. World Liberty Financial — the crypto venture Don Jr. & Eric launched with Steve Witkoff's sons, Zach & Alex —

It's wild how quickly Etched designed and got the chips out, all within 2 years. They went deep, hardcoding attention into silicon and getting very high MFU. This kind of hardware tailored made for LL

I've added video support to my 'shot-scraper' browser automation tool - you (or your coding agent) can now create a storyboard YAML file and use that to record a video demo of new web application feat

joined @LangChain almost three months ago and have spent a ton of time thinking about evals! i think that harbor is the future of eval frameworks so really enjoyed being able to bring it into tighter

Just hardcore engineering This required: - advanced optics solutions to be able to see vessels through an opaque layer of tissue - precision manufacturing to machine micrometer scale features in our n

This post from Swyx discusses San Francisco-specific phenomena and features commentary from the 'Orc-estrator' and @swyx, likely relating to AI/engineering topics given the hashtags #aiewf (AI Enginee

LangChain 今天连发两记，直接把 agent reliability 往前推了一步：一套统一评估栈，一个不用完整沙箱的代码执行方案。 先说评估。长运行、有状态的 agent 怎么测？Harbor + LangSmith 的组合给出一个 runner，能挂载 sandbox、接入 observability，终于不是靠单元测试糊弄了。 再看代码执行。Deep Agents 需要跑不受信代码，

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of h

This post from Swyx likely discusses loops in the context of web development, programming patterns, or a specific framework/tool. Without access to the full content, it appears to be a technical post

Love how Google continues to drive down the cost of building with their models. <4s image and 0.034 / 1K image. Wow! We have a bunch of stuff (education & research) we're building @dair_ai using Nano

Marco Rubio and Elon Musk claim that no one died from shutting down USAID. Yet the best estimates are between 8–20 million by 2030. We can debate the exact number—but it's clearly in the millions. Whe

Memory has somehow consistently been the most exciting area of agent development over the last 3 years (imo), and it's still a largely unsolved problem!! Wiki's are the biggest advancement I've seen i

This documentation page covers advanced features of Hermes Agent's web search and information extraction capabilities, explaining how users can leverage the tool to search the internet and extract rel

More time to build with Step 3.7 Flash: in partnership with @StepFun_ai, we’re extending the free usage period in Nous Portal by an additional 15 days! Media Step 3.7 Flash is now free for 30 days via

Swyx presented slides on AI engineering at an event or conference, with the presentation materials hosted on a Loopcraft subdomain. The post appears to announce or share the kickoff of an AI Engineer-

My grandfather, communism, and the tremor that never left. A story I rarely share. He was the principal of a private school; respected, steady, a man who believed in books and order. Then, one ordinar

my process for writing right now is to do some engineering work, talk to a bunch of people about it, brainstorm and research with Claude, write a post, give 1 or 2 talks on it, rewrite the post, give

// Neural procedural memory // Good paper on agent memory beyond prompt retrieval. NPM stores procedural skills as activation steering vectors distilled from contrastive historical experience. Textual

Neuralink, Elon Musk's brain-computer interface company, has progressed from its initial conception to advanced development stages, with the company working toward implantable devices that could enabl

NEW: @FreeBeacon has the receipts on Ro Khanna’s obscene, oligarchic wealth: —his 2 kids (under 10yrs old) own 3 private golf courses in Ohio (not kidding) —his wife drives a $190,000 luxury Range Rov

NEW on Hugging Face: Hardware filters 🖥️ A new Hardware filter on the Models page results to models that fit a specific GPU, CPU, or Apple Silicon chip, so you only see what will actually run on your

Notes (and a Pelican) on Claude Sonnet 5 - the new tokenizer makes it ~1.4x more expensive for English, ~1.33x more expensive for Spanish but roughly the same price for Simplified Mandarin https://sim

This post references two individuals, @charles_irl and @swyx, creating positive social energy or engaging content together on a specific occasion. Without access to the full post content, it likely do

On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and has a 57.6% pass rate (higher than Opus 4.8). Note: These rel

Swyx posted a welcome message on X (formerly Twitter), likely introducing a topic, event, or initiative. The tweet appears to be part of a broader conversation or announcement, as indicated by the URL

Ornith-1.0-35B, a 35-billion parameter model, has been made available for use through Claude Code via Hugging Face integration. This announcement indicates expanded model availability and integration

Our first summit dedicated to world models, coming to SF this September. Announcing our first summit dedicated to world models, coming to SF this September. Very excited to have some incredible resear

Our Founder and Chief Scientist @EdoLiberty just kicked off the Search & Retrieval track @aiDotEngineer. 'Agents don't need to be smarter. They need a Knowledge Layer.' We've got a big update on this

PEOPLE ARE BLAMING ELON MUSK FOR “DEATHS” FROM USAID CUTS — BUT THE DATA AND REALITY SAY OTHERWISE Opponents are loudly claiming that cutting wasteful USAID spending is killing people in poor countrie

This post documents a rapid application development challenge where participants had 45 minutes to build an app as part of a 'Hack the 7' hackathon event, a collaboration between Replit and Propaganda

【採用情報】Product Designerのポジションをオープンしました🐟 https://sakana.ai/careers/product-designer/ Sakana Chat🐟・Marlin🐬・Fugu🐡をはじめとした、プロダクトの体験をリードするProduct Designerを募集しています。 このような役割を担っていただきます。 ・コンセプト設計からUI、プロトタイプ、 ブラン

Project gallery and whitepaper: https://research.nvidia.com/labs/gear/aspire/ ASPIRE is a great collaboration between NVIDIA GEAR lab, UMich, Berkeley, and CMU. Kudos to all the coauthors who pour the

Itamar Friedman participated in or organized a drone show performance at an event associated with @aiDotEngineer. The post documents this aerial technology demonstration, likely showcasing coordinated

Qwen publishes new work on RL coding agents. (bookmark it) The idea is to continually build a verification system that co-evolves with AI agents. LLMs suffer from all sorts of reward hacking issues. T

This post links to a full interview with Aidan Gomez conducted by the Aston Martin F1 team, published on their official website under their 'Perspectives' feature section. The interview likely covers

This post likely recommends resources or reading materials for practitioners looking to deploy and scale open-source language models in production environments. DAIR.AI, a research organization focuse

This post from DAIR.AI recommends resources for developers and organizations scaling applications using open-weight language models, emphasizing the importance of planning infrastructure and deploymen

This post announces a conference session at @aiDotEngineer scheduled for 2:25pm in Room 2016, covering topics including the Galactica model and early reasoning efforts in Llama models, with additional

Row-Bot's approach to memory is hybrid. We have taken the best of both worlds. A knowledge graph for the agent + bi-directionaly synced Wiki for human readability/audit. With in-app graph visualizatio