All entries

wild. Google reportedly limited Meta’s use of Gemini due to a shortage of compute resources. — FT Google is in a position where it can’t sell Gemini to Meta as freely as it might want to. Compute rema

This post documents a Wordle game result where the player solved the puzzle in 4 attempts using a strategy that progressively narrowed down letter positions. The final answer was a five-letter word wi

you may have heard that glm-5.2 at 392 token/s is cool, how about 446 except… it’s all noise. Artificial Analysis picks median among 8 points/day so first point of the day can be way off looking at 3

2 year old girl raped and murdered by a migrant This is the moderate response 🚨NEWS: An African migrant has been charged with rape and murder after the body of a 2 year old girl was found at property

🧑‍🏫3hr Long Deep Agents Course Great course from a member of the community on Deep Agents Covers task planning, file systems for context management, subagent-spawning, and long-term memory https://www

A thing I am noticing is the number of folks who believe AI is “real” is larger, but now there is a growing division between people who know that we are on an exponential & those whose mental model is

AI Engineer After Dark is the official side event of World's Fair. Presented by @vercel, @merge_api, and @FactoryAI. July 1 at SFMOMA. A founder panel, lightning talks, DJ, drinks, and the builders yo

Swyx shared that they recently implemented a new 'canvas view' for what appears to be a conference or event schedule (AI Engineer World's Fair), noting that the implementation uses vibecoding techniqu

America is about to lose the AI race, and it will not happen at the frontier. It will happen at the floor. Everyone is watching who ships the smartest model. The actual war is over the 80% of tokens n

An interesting way to take Noam at his word in regards to always keeping a constant inference budget for any eval reporting - is that open models have a lot more dollar per token mileage than closed m

And the idea that frontier open weights models will continue to be released was fragile even before the current de facto licensing regime. https://x.com/emollick/status/2067669551685218638?s=20 Is the

Ethan Mollick notes that OpenAI has not released a GDP value metric for GPT 5.6, which he identifies as one of the most useful measures for quantifying the economic value generated by AI systems. This

> Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. We do this for you in Deep Agents - see

🚨 BREAKING: Anthropic and US Govt insiders expect the administration's limits on Fable 5 could be lifted as soon as this coming week, per Axios. The Pentagon and National Security Agency still have to

btw we crossed our 6k attendee mark a while ago. will probably call sold out when we hit 7k this weekend. do get tix now, this is the epicenter of ai next week. if you are a student or between jobs, h

“Capitalism is not a profit system, it is a profit and loss system, and the losses are more important than the profits.” —Milton Friedman But the US education system runs on the exact opposite princip

'Come and take it' is a historical phrase and motto associated with resistance to government authority, most famously used during the Texas Revolution (1835-1836) and later adopted in American politic

DSpark from @deepseek_ai ingeniously integrates many speculative decoding ideas to achieve 1.5x to 5x higher throughput in a real production system Let's understand it with 10 ideas, starting from the

Every enterprise will have its own model-harness-sandbox-eval flywheel with token value per watt optimization. This is the future. Simple reason: tacit knowledge about the domain and customers and the

Everyone tells me that Elon Musk is a fascist because he could 'solve world hunger' for a mere 3 billion dollars, but MacKenzie Bezos has burned through 26 billion dollars of her ex husband's money an

For half a century, the 7.6 million pounds of thrust from the Saturn V was the absolute ceiling of human engineering SpaceX is now treating that as a baseline “Starship V3 is more than double the thru

From playing around with /goal It feels like there's less and less of a need to build any type of workflow manually (whether through code, drag and drop, or a prompt). Instead, specify the goal, let t

Sakana AI's Fugu-Ultra model is now available through Vercel's AI Gateway, expanding access to this language model through Vercel's infrastructure. This integration allows developers to use Fugu-Ultra

I can't verify this specific post or its details from the URL provided. To create an accurate knowledge base entry, I would need to confirm the actual content of the tweet, the doctor being referenced

Gary’s analysis is pretty much spot on as ever. This is such a worrying development People are not getting how significant this news – The White House delaying GPT 5.6 – is. Here’s the context and a s

How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. Better Defaults (not Usage Caps) – Engineers can choose

Elon Musk shared commentary on a post contrasting 'maker' versus 'taker' dynamics, likely referencing an observation about productive versus extractive behaviors or individuals made 14 years prior. Th

I put together a new article on setting up local coding agents with open-weight models. Everything runs 100% locally. I thought it might be useful putting this together because many people asked me ab

If you use LLM-as-judge, this one is worth reading. (bookmark it) It's actually one of the most effective ways to use LLM-as-a-Judge for evals. Holistic judge scores hide both their reasoning and thei

I’m speaking at AIE SF World’s Fair on July 1st in the Sandbox & Platform Engineering track. My talk is called 'From fork() to Fleet: Designing an Agent Sandbox Cloud'. I’ll cover the OS and Infrastru

Swyx conducted an impromptu live tour and Q&A session on the AI Engineer conference show floor, likely showcasing booths, demos, and networking opportunities while answering audience questions about A

It has now reached the point where I truly believe that public officials and politicians who continue to knowingly import third world savages into our communities should be prosecuted. It is that reck

It is entirely possible that the steady-state people will prove to be right in the future, but there's no sign of a slowdown yet. And if greater intelligence brings greater value at an exponential pac

It really isn't an exaggeration! LiteParse clocks in at an average of 3ms per page for a reason: it skips the heavy AI processing and cloud overhead entirely. Here is exactly how it pulls off that kin

Ladies and gentlemen, I am pleased to announce that staplers & pencil erasers will once again be available for sale to some companies, as well as a few close personal friends and important donors. Thi

langchain is one of the few teams that actually explains the engineering behind agent concepts instead of just naming them. loop engineering, managed agents, memory systems. every time a new concept d

langgraph <3 New category drop on the Arena: ✨AI agent frameworks✨ Agent Experience (AX) update as of 06/26: 1/ @LangChain LangGraph 2/ @vercel AI SDK 3/ @crewAIInc 4/ @mastra For context: we evaluate

This article explores the implementation and use of local coding agents—AI systems designed to autonomously write, test, and debug code on local machines without relying on external APIs. The piece li

LiteParse is unreasonably good for document parsing ✅ It is the fastest document parsing tool out there - average parse time per page is 3ms ⚡️⚡️ ✅ Now that we support markdown, it tops opendataloader

Loop engineering refers to an iterative approach to AI system design that combines prompt engineering with robust system architecture, emphasizing that effective AI applications depend equally on how

Lots of advances coming from the open source harness movement (including Moltbook, RAG approaches back in the day, etc.) but they depend on the intelligence of the models created by a small handful of

Madness IT'S REAL BAD. The British government just came with a new bill that could throw parents 5 years in jail if they try to stop their child from wanting to change gender. I had a look at what the

Swyx is promoting membership opportunities for both companies and creative individuals, with applications available through an Airtable form. The initiative appears to be community-focused, inviting i

minor milestone in the growth of swyx inc: we took over my new media lab today it will be the new home for engineer-creatives in san francisco; a third place to make; a finishing school for technical

Model management is the real SDLC scaling bottleneck. @FactoryAI standardized on Fireworks to solve it: → 2–3x open-model growth → 5–15x more work per dollar → day-0 access to every new open-weight mo

Ornith is a model available through the Ollama library, a platform for running large language models locally. The specific capabilities and parameters of this model can be found on its dedicated model