Knowledge catalogue
arXiv:2602.07195v2 Announce Type: replace-cross Abstract: Interactive computational notebooks (e.g., Jupyter notebooks) are widely used in machine learning engineering (MLE) to program and share end-t
It's a drop-in. One program_id field and it plugs into your existing engine configs such as KV offloading + speculative decoding. Format-agnostic by design, with OpenAI chat completions supported toda
arXiv:2607.25090v1 Announce Type: new Abstract: Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feed
Model + harness. We have barely begun to understand the best ways to do harness engineering. A huge amount of untapped potential even without models getting better (but models are getting better) Turn
The root cause: request-level engines never see that a series of LLM calls belongs to one longer workflow. ThunderAgent adds that missing view. It treats each agent workflow as a schedulable program,
We’re giving scientists, mathematicians, and engineers free access to our frontier models—starting with 10,000 researchers and expanding to 100,000 through 2027. ChatGPT for Academic Researchers is bu
arXiv:2607.22569v1 Announce Type: new Abstract: Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, an
arXiv:2607.23365v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education.
On FrontierCode 1.1 Extended, our benchmark for real-world engineering tasks that grades mergeability and quality, Kimi K3 scores 58.2% with a 63.6% pass rate. Within Devin, it excels on reproducing b
The knowledge that makes AI useful is diffused. It lives with scientists, engineers, clinicians, firms. For AI to benefit from distributed knowledge, it must itself be distributed. Agree with Jensen t
I don’t believe reality is a simulation, but you genuinely couldn’t script this timeline: • Two weeks ago: At @swyx’s AI Engineer World’s Fair in SF, I decide at the last minute to introduce my friend
NVIDIA TensorRT’s IProgressMonitor API lets developers track and cancel long‑running engine builds in both Python and C++. By overriding `phase_start`, `step_complete`, and `phase_finish`, the monitor
Multiplayer mode with AI is incredibly underrated and underutilized. Cat Wu shared that 65% of Anthropic’s product engineering team PRs are closed via Claude Tag sitting inside of Slack, and not singl
Sydney Runkle inquires whether anyone is exploring graph engineering that aligns with Claude’s dynamic workflows, specifically whether an agent could author its own state machine. The suggested approa
arXiv:2607.14076v1 Announce Type: new Abstract: Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligen
Rebecca Bellan / TechCrunch: Anthropic, Blackstone, and Hellman & Friedman's $1.5B AI implementation company, announced in May, launches with the name Ode with Anthropic and 100 engineers — AI models
Gary Marcus argues that the engineering and infrastructure surrounding large language models are more critical to their practical success than the models themselves. This reflects his broader perspect
arXiv:2607.08043v1 Announce Type: cross Abstract: Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A decision surfaced in a Slack thread, refined in a
Anyone know if ChatGPT Codex (in the new ChatGPT desktop app) is a strict superset of ChatGPT Work? Liked if you're a software engineer who isn't intimidated by Git features is there any reason you'd
Megan Morrone / Axios: Apple alleges that a former Apple engineer kept a work-issued Apple laptop and exploited a bug to access Apple's cloud file storage while employed by OpenAI — Apple is suing Ope
Mark Gurman / Bloomberg: Apple claims OpenAI recruited 400+ ex-Apple employees, including an iPhone engineer who allegedly downloaded confidential hardware files before joining OpenAI — Apple Sues Ope
arXiv:2607.07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents. Most public agentic coding benchmarks fo
Here is a visualization of the AI Picbreeder engine in action. (From our blog: https://pub.sakana.ai/picbreeder-vlm/) To recreate a collaborative human ecosystem, we run 10 VLM “breeder” agents in par
Just yesterday an engineer posted 'open swe is my favorite productivity tool at the moment' in slack Open source wins! Sierra isn't the first to build this - Ramp, Stripe, CoinBase also have If you wa
Jarred Sumner / bun.com: Bun's creator says he rewrote Bun from Zig to Rust using a Claude Fable 5 prerelease version in 11 days, noting it would've taken three engineers “about a year” — Disclosure:
【採用情報】Data Engineer (Product) のポジションをオープンしました🐟 https://sakana.ai/careers/data-engineer-product/ プロダクトチーム初のデータエンジニアとして、AIが自律的にデータ分析を行うためのデータ基盤をゼロから構築していただくポジションです。 ・データパイプラインの構築・運用 ・プロダクトおよび ビジネス指標のデータ
arXiv:2603.21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon t
arXiv:2607.07459v1 Announce Type: cross Abstract: We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence. Sim-ready 3D asset g
Sergiu Gatlan / BleepingComputer: Interpol and law enforcement agencies arrest 5,811 suspects and seize 293M in an operation combating social engineering scams and fraud across 97 countries — Law enfo
Calling all exceptional civil and electrical engineers! The SpaceX Cape Starship team needs help building and scaling the worlds most advanced launch pads. If you want to join the greatest team on Ear
arXiv:2607.06224v1 Announce Type: new Abstract: Designing microbial strains that produce high-value chemicals at commercially viable titers remains a central challenge in metabolic engineering. Existi
I used Codex to port Command & Conquer: Red Alert to Mac and Android. No emulation. The original engine now compiles natively to ARM64, with macOS and Android platform layers. Codex wrote the code, bu
Introducing: Granular job tracking and cost attribution in LlamaParse 🦙 Parsing thousands of pages a day is a lot to manage. Engineering teams need to have a pulse on what's running, who ran it, and w
“Model orchestration is in many ways the natural outgrowth of agentic engineering” Huge thanks to @AndrewYNg and @DeepLearningAI for the deep dive into Sakana AI’s Fugu and Fugu-Ultra. The article hig
arXiv:2607.06074v1 Announce Type: cross Abstract: Prompt engineering has emerged as a critical yet undertaught skill for software developers, one that traditional learning approaches are ill-equipped
this should be a huge update in your model of software engineering: rewrites can be good, cheap and fast of course most apps are not as testable and verifiable as Bun, but the models will continue to
arXiv:2508.16181v2 Announce Type: replace-cross Abstract: Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across inde
Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. M
The AI labs desperately need non-engineer Peters, Borises, and Thariqs. Most demos for 'business users' are about replying to emails or to Slack. And yes, that's helpful to manage the cacophonous hell
We're hosting the LA Agentic AI Meetup this Thursday, July 9, 5 to 7pm at Gulp in Playa Vista. Come talk to engineers, founders, and builders working across RAG, agentic workflows, and the broader AI
LangSmith Engine uses a two-stage agent architecture for trace investigation, routing queries through dedicated screener and verifier sub-agents rather than handling requests directly. This approach l
loved AI Engineer summits in NY both times, Singapore last month was great, and then ofc this was the one i couldn’t make. huge thanks @swyx and everyone who made the stream https://axinbox.com/d/01KW
introducing tinyrouter i reverse engineered the routing architecture behind Skana AI's Fugu and built replication for open frontier models. it's a tiny ~10K parameter LLM router that learns which mode
# Summary This post likely critiques the trend of 'loop engineering' as an example of superficial, trend-chasing content popular among tech influencers on LinkedIn, questioning whether it represents g
Multimodal prompting is clearly the future. I love experimenting with new ways to interact with agents. As a researcher and engineer, I've found that the richer the inputs to the agent and the richer
None of it was an accident. A team that gave up recharge week, and a partnership @GeoffBibby built with @swyx + the AI Engineer crew that turned a year-old idea into the biggest stage in AI eng. Thank
We analyzed GLM 5.2 vs Sonnet 5 for software engineering tasks using DeepSWE. GLM 5.2 gets you ~80% of Sonnet 5's capability at ~20% of the price. More insights in the thread! Deepdive: Sonnet 5 and G
This article discusses 'skill engineering' as an approach to AI system design that emphasizes iterative development and refinement of AI capabilities, arguing against the 'one-shot' design philosophy
Special episode with @bentannyhill on the Max Agency podcast. A month ago, his team shipped LangSmith Engine, our agent that hunts through your agent's failures, prioritizes issues, and drafts the fix
arXiv:2607.00990v1 Announce Type: cross Abstract: Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue re
arXiv:2607.00053v1 Announce Type: cross Abstract: Large language models (LLMs) embedded in multi-turn agentic harnesses are reshaping software engineering (SWE), but routing every task to a frontier m
Today at the AI Engineer World's Fair in San Francisco: the 'software factory' vision met resistance from speakers defending human understanding and control. https://www.latent.space/p/aiewf-daily-dis
Imagine if, as an engineer, your working memory of a codebase was wiped every time you started a new ticket Sounds ridiculous, but this is functionally what happens to agents whenever we start a new t
Interrupt 2026 is coming to New York City and London this fall. → Hear from engineers + teams shipping agents in production → Keynotes from @hwchase17 + industry leaders on what's next for agents → Ha
Max A. Cherney / Reuters: Oxmiq, which aims to combine GPUs, CPUs, and a tensor engine into a single block of IP that it can license, raised 35M led by Samsung Catalyst Fund and Fudomo — Artificial in
Russell Brandom / TechCrunch: AWS launches an internal organization for AI-focused forward-deployed engineers, backed by $1B in resources, following OpenAI and others in launching FDE teams — As compa
arXiv:2606.29014v1 Announce Type: new Abstract: Recent advancements in generative artificial intelligence (AI) and large language models (LLMs) have shown significant promise in automating complex rea
Doors are open at Agent Open, right next door to AI Engineer Two courts, blue sky, no fog (a San Francisco miracle) 🌤️ This is the perfect walk-over window, we are just 3 minutes from Moscone. Don't m
Giving a talk on agent-to-agent and AI network effects at @swyx 's AI Engineer World Fair today at 1:30p in Room 2010. Come say hi! I think this talk will be a good one if I may say so myself. https:/
This post appears to be a casual social media share from Swyx about an item or experience from an AI Engineer World Fair event, likely featuring a photo or humorous take on something encountered at th