Search: “engineering”

Harrison Chase discusses the tradeoff between speed and focus when building a core product using a frontier model versus developing more customized solutions. Using a frontier model with a standard ha

Auto-generated synthesis of 142 entries about swyx--x

Developer advocate **Nick Taylor** (@nickytonline) posted a thank-you message on X praising the **AI Engineer Europe** conference organized by @swyx (Shawn Wang) and the AI Engineer team. Taylor ex...

AI Engineer Europe is a technical conference series held in London (April 8–10, 2026) organized under the @aiDotEngineer brand, bringing together the global AI engineering community for talks, work...

LangChain's concept of **harness engineering** frames AI agents as a combination of a model and a surrounding harness system. An agent equals a model plus a harness — harness engineering is how sy...

The tweet by @TomasMann1878 is a social media post from an attendee of the AI Engineer (@aiDotEngineer) conference, calling out for meetups at a 'giant lobster' landmark and praising the event orga...

arXiv:2305.06177v1 Announce Type: cross Abstract: We present a thermodynamic analysis of a quantum engine that uses a single quantum particle as its working fluid, inspired by Szilard's classical sing

arXiv:2509.21079v2 Announce Type: replace Abstract: Foundation models have shown remarkable capabilities in various domains, but their performance on complex, multimodal engineering problems remains l

arXiv:2607.27167v1 Announce Type: cross Abstract: LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fund

arXiv:2607.24792v1 Announce Type: cross Abstract: Energy utilities still run engineering work management, engineering procurement, and inventory processes on long-lived enterprise asset management pla

OpenAI’s Codex, an AI‑powered coding engine, has surged beyond the developer community to reach over 10 million users—combining Codex with its new “ChatGPT Work” platform that turns the model into a g

here’s a video on my approach at applying this to agents w @activegraphai: 🆕 ActiveGraph: The Log is the Agent my talk from AI Engineer is live!!! 😆 https://www.youtube.com/watch?v=khVX_BUnEwU it's ab

Cuda and Vulkan Benchmark: TensorSharp vs. llama.cpp I would like to share my latest open source local Unsloth (GGUF) LLM inference engine and applications. It supports many models from Unsloth, like

The automotive industry is moving from building hardware-centric platforms toward building their own sophisticated Software-Defined Vehicle (SDV) architectures. For OEMs, a vehicle is no longer just a

How should your security team manage shadow AI? Workloads deployed by developers without formal registration can often evade traditional security scanners, because organizations are reluctant to slow

arXiv:2607.03525v1 Announce Type: cross Abstract: Game engines provide real-time simulation, rendering, physics, interaction, networking, and asset pipelines, making them valuable not only for games b

in case you needed more evidence that tokenmaxxing was a stupid idea Meta burns 2.65B a year on AI tokens. at 300K for a Meta engineer, that's enough to pay ~9,000 engineers for a full year. now ask y

This is a Twitter Spaces broadcast hosted by Swyx discussing an AIE (AI Engineering) workshop day, likely covering practical applications, techniques, or discussions related to AI engineering practice

Swyx announced an upcoming AI Engineer event with tickets and information available at ai.engineer/wf, promoting it as significantly larger than all previous AI Engineer conferences combined. The post

arXiv:2605.29986v1 Announce Type: new Abstract: To guarantee that an LLM's outputs conform to a specified structure, context-free grammar (CFG) decoding engines force the selection of next tokens that

Starship’s Super Heavy booster produces roughly the same thrust as ~80 Boeing 747s all firing at once The scale of that power is almost incomprehensible Its Raptor 3 engines are true marvels of engine

arXiv:2605.17448v1 Announce Type: cross Abstract: Computer-aided design (CAD) is the backbone of modern industrial design, yet learned CAD generators still fall short of real engineering pipelines: th

Accessing enterprise data is shifting from static reports to dynamic use by autonomous systems. To keep up, organizations must route fragmented data from SaaS, IoT, and legacy sources into secure, sca

🧵 Slime: The Most Elegant & Comfortable RL Training Framework Ever A deep dive into why Slime redefines LLM RL training with clean architecture & production-grade engineering ✨ Insights from Zhihu con

Elon Musk shared a post about Starship's static fire test, which is a ground-based engine test where the vehicle's engines are ignited while the rocket remains secured to the launch pad. This test is

Editor’s note: Want to keep up with the latest from Google Cloud? Check back here for a monthly recap of our latest updates, announcements, resources, events, learning opportunities, and more. We host

Sakana AI Labs is offering free API credits for developers to test their Fugu orchestration models in real workflows. The offer was announced by David Ha on X, with additional details available on the

arXiv:2604.21599v1 Announce Type: cross Abstract: Machine Learning (ML) Engineering is a growing field that necessitates an increase in the rigor of ML development. It draws many ideas from software e

David Ha shared an enthusiastic post about receiving a Sakana AI branded mug, expressing joy with fish emoji decorations. The post appears to be a personal social media update celebrating Sakana AI me

The Never Ending Lore of Harness w/@Vtrivedy10⚡️ Viv brought some amazing perspective around harness design, evals, file systems, RL Envs and so much. 0:00:00 - INTRO 0:03:30 - PhD at Temple Universit

AIサイエンティストが示すような自律的な科学的発見の未来を実現し、現在の課題を乗り越えていくためには、最先端のML研究とプロダクトを繋ぐ強力なエンジニアリングが不可欠です。 https://sakana.ai/careers/#software-engineer-research-and-development 現在Sakana AIでは、研究開発を加速させるSoftware Engineer (

Tencent HY-World 2.0 is an open-source AI world model that generates real 3D scenes directly usable in game engines like Unreal Engine and Unity; unlike previous versions which produced video-based wo

Today, we're thrilled to announce that BigQuery Graph is now available in preview. With BigQuery Graph, we’ve built an easy-to-use, highly scalable graph analytics solution for data engineers, data an

Auto-generated index of all people mentioned across the wiki.

"**AI Engineer Europe (London) — Conference Recap**

Swyx or a developer in the AI engineering community is sharing work-in-progress progress on a Model Context Protocol (MCP) application built using 'vibe coding' (AI-assisted development). The project,

arXiv:2608.10941v1 Announce Type: new Abstract: Industrial time-series signals, such as turbine temperature and rotational speed in aero-engines, are essential for monitoring the health and operationa

In a fast-paced digital economy, data is your most critical engine. Yet, many enterprises find themselves trapped in a costly paradox, spending over 100 hours a week building and fixing fragile, in-ho

I'm the author, so discount the enthusiasm accordingly. This is an unaffiliated community port, not endorsed by the vLLM project, which it uses to verify its correctness. What started it: I love vLLM,

I'm hoping that one of you guys has been working on an inference engine or has somehow found improvements to running DSV4F on RDNA4 multi-GPU setups. I am currently building a custom inference engine

arXiv:2607.27251v1 Announce Type: new Abstract: Transformer-based surrogate models are increasingly used to replace expensive first-principles simulation in engineering design. But conventional transf

The Test Bench Setup I tested running a massive 1.56TB Mixture-of-Experts (MoE) checkpoint (96 shards, 93 layers, 896 experts/layer, ~4.46 bits/param MXFP4) on a budget gaming laptop. Laptop: HP Victu

I've been building a C99 inference engine from scratch (no Python, no BLAS, just gcc and make) that runs BitNet's ternary models on CPU. A few weeks ago I got obsessed with the matmul kernel - wrote a

arXiv:2607.13035v1 Announce Type: cross Abstract: Cloud services experience frequent incidents that require rapid diagnosis and resolution. Troubleshooting guides help engineers respond consistently,

[SYCL] Flash Attention with XMX engine via oneDNN (#25222) [SYCL] F16 (default) Flash Attention with XMX engine via oneDNN graph API; Qwen3.6-27b-Q8_0 prefill speed up x1.21 at p=512 and x4.26 at p=80

B9862 is a continuous build-tagged release from llama.cpp , the open-source C/C++ LLM inference engine. Llama.cpp is the inference engine that powers most of the local-AI ecosystem, including tools li