All entries

Communism through (my) ages: 1) When I was 15, a teacher told me 'It isn't as bad as they say, and makes a lot of sense.' 2) At about 19, college friends, 'Socialism isn't communism.' 3) At 20, on mee

Fireworks AI announced the release of an open source GLM model that offers significant improvements in speed, cost efficiency, and output quality compared to existing alternatives. The post suggests t

Cost per iteration is the unlock. GLM-5.2 on Together AI can generate polished web apps for a few cents. At that price, developers can explore more directions, compare more versions, and keep the best

Crazy how many times people have told me over the last five years that a solution to hallucinations was right around the corner — and yet here we still are. This study tests how often LLMs invent answ

deployment cookbook for langchain agents! Agents are easy to demo locally. The hard part is shipping them inside a real app. We published a deployment cookbook for @LangChain agents: full-stack exampl

Disagree with @mcuban’s opening sentence – I do think some people genuinely hate the noise, blight, impact on electric prices, etc—but he is quite right that data centers have become a proxy for hate

excited to be speaking at @aiDotEngineer World Fair next week on Improving Agents, Continual Learning, and why we think a large part of it is...Data Mining! Trace Mining is how we understand agent beh

Replit's integrations catalog allows developers to browse and discover third-party tools, services, and extensions that can be connected to their Replit projects to enhance functionality and streamlin

focusing on a single user story in your marketing can be challenging because you feel like that one story might not resonate with all of your target customers but when done well (like this), it’s emot

Getting used to being liked likely means you are overfit to RLHF. The problem with overfitting is that the pain overwhelms the limbic system once you try to sample trajectories outside the known distr

Grifters and many other salesman are like LLMs. They say things that aren’t always true with absolutely certainty. Bitcoin has won. Global consensus is that $BTC is digital capital. The four-year cycl

Grok Imagine Video has achieved significant adoption on Vercel's AI Gateway, accounting for approximately 50% of all videos generated by developers using the platform. This milestone indicates Grok Im

Grok may not be the AGI that Elon promised, but it appears that the man has found his use case. xAI is betting big on AI video and image generation — but the biggest driver of Grok Imagine may not be

Yohei Nakajima questions the legitimacy of token-saving solutions in the AI space, noting anecdotal reports from peers that some of these tools may actually increase token consumption rather than redu

Honestly at this point I'm a bit frustrated I didn't get my USAID-sponsored RPG Naming it USAID was brilliant honestly because most people are too dumb to even ask what it really does It’s like naming

How do you construct, compact, and query a full-text search index when all your durable data lives in object storage? And where every GET costs 50–100ms? @ankush_gola11 + team on how we built and run

This post likely presents a before-and-after comparison of some aspect of Tesla, SpaceX, X (formerly Twitter), or another Musk-led enterprise, showing the contrast between the company's initial state

How many more children before we admit the experiment failed? This time it’s two Iraqi brothers, 18 and 20, on trial in Essen, Germany, for allegedly raping a 7 year old girl on two separate occasions

This post likely describes how to integrate voice communication capabilities with Hermes agents, enabling two-way spoken interaction rather than text-only exchanges. It probably covers implementation

OpenAI discusses how AI agents are reshaping workplace productivity and operations, likely covering applications of autonomous AI systems in automating tasks, enhancing decision-making, and transformi

This post expresses enthusiasm about attending an AI-focused engineering conference organized by Swyx, noting the impressive scale of the event. The tweet suggests this was the poster's first attendan

I know this is a common thing to mention in some corners of X, but there is still so much focus on future model development & innovation bringing transformation that people are really overlooking the

I love using GLM 5.2 for web app iteration. My workflow: generate 6 variations, then pick the best one and continue iterating on it. I built Recast to make this even easier. Give it a prompt, get 6 va

I spend 10 minutes a day trying a new app. http://matrix.build is my favorite app today. You can tell from a product whether the team's thinking is clear. The thing I love about matrix is it helps you

I think part of what makes this account’s work so satisfying is they are doing a form of pattern recognition that is computerlike in many ways but actually requires a soul to pull off. Proof humans ar

I think this means you can collect ~10k hours just from open source datasets, which means basically anyone should be able to build a decent robot foundation model: 500 from the new BitRobot dataset 50

If it was just military implications, that would be one thing, but if this is about info security at scale (as Five Eyes suggests), publicly understanding risks and mitigations is incredibly important

if you get 1% better every day then you're 37x better in a year (from @JamesClear's atomic habits book) my theory is you can do this for agents if you build a good continual learning loop which is wha

I'll be talking more about Claude Tag with @petergyang and at AIE with @_catwu. Let me know if there's anything you'd like us to dive into more! Claude Tag is the next evolution of agents. It's a proa

Imagine if i had a business that gave you 20 bills for 10 bills. As word spread, my customer base would grow. My revenue (how many $10 bills I collected) would grow. And I would continue to lose money

In a joint Fireworks and @Faros_AI evaluation of 211 real engineering tasks, Claude Code + GLM-5.2 beat both Claude Code + Opus 4.8 and Codex + GPT-5.5: - Judge score: 0.568 vs. 0.521 and 0.466 - Time

🚨 In a surprise to NOBODY, a study shows that generative AI use raises homework scores, but substantially reduces learning. My takeaways for AI ethicists and educators: The study analyzed data from 26

In HF GGUF section of models, we are emphasizing MTP heads with its own sign 𝗠𝗧𝗣 llama.cpp adds MTP for the Qwen3.6 family This is a significant milestone for the local AI ecosystem. The performance j

In the end, will Elon be best known for his efforts to mainstream electric cars, for his rockets, …. or for his efforts to mainstream AI-generated porn? xAI is betting big on AI video and image genera

In this episode, @OpenAI Chief Research Officer @markchen90 joins @allenpark to flambé shrimp, cook Korean stew, and chat about being at the frontier of AI research: why scaling laws and pre-training

Independent analyses estimate that your actions to dismantle USAID and drastically reduce lifesaving foreign aid have already killed 700,000 people. Here are some of those people. 🧵https://x.com/elonm

It is amazing to me how little the X-verse cares about the rise of authoritarianism in the United States. Is that because most of the “people” here are actually Russian bots? 🤔 More Soviet-style decep

It would be very useful to understand more about the government safety concerns associated with frontier AI releases so we could (a) know what risks everyone will face if/when open source reaches Myth

It’s time for everyone to realize that the fight against data centers has nothing to do with data centers. They have become a proxy for the hate towards AI and the concentration and accumulation of we

Just had a great discussion on dynamic workflows. Rough notes: - applies to a very small set of use cases - think of it as a new paradigm of (test-time compute) TTC - strong for hill-climbing research

LIVE TOMORROW: Replit now has 450+ integrations, and we've made them easier to find and put to work! ⚡ Stripe, Google Docs, Gmail, Figma, Slack, Notion, Airtbable and more! We're going to talk to Jaco

LLMs are getting better at writing GPU kernels. Multi-GPU kernels are the harder test. At @aiDotEngineer World's Fair, @simran_s_arora will share ParallelKernelBench, an open-source benchmark built fr

Looks like OpenAI’s IPO will be delayed until 2027. • might be a sign that their finances don’t look compelling yet. • gives Anthropic time to go first If they can bump up the valuation by $999.3 bill

Loops, one of the most symbolic tools ever invented, are rescuing generative AI. Neurosymbolic AI is completely dominating. Anthropic engineers just showed how to build agents that can run for days wi

lots of folks prepping talks next week (congrats!). Some thoughts from RLing on thousands of hours of engineer- and researcher- focused talks: - AI generated svgs > AI generated imgs. MAXIMUM 4 ai slo

love that one of my readers made her own, explicit set of public predictions. 🙏 I want to post my predictions for 2ish years horizon. AI stock bubble collapses due to fundamentals not working out with