dotrandomcode @dotrandomcode

x.com/i/article/2064…

HTML plans are so good. Thank you @trq212 for putting me on. Mythos is so good at them. Provided nothing but the request to explain monetization plans in HTML, and got this incredible breakdown with a diagram in the middle of it.

A new study has reconstructed 1,000 years of earthquake activity along Southern California’s San Andreas and San Jacinto fault systems and found that tectonic stress in the region has reached levels not seen in the past millennium. Using a physics-based 4D earthquake cycle model, researchers combined paleoseismic data (from geological evidence, radiocarbon dating, tree-ring anomalies, and historical records) with simulations of stress accumulation and release. The results show that current stress on key fault segments, particularly around the Cajon Pass junction northeast of Los Angeles, equals or exceeds the highest values observed over the entire 1,000-year period. Cajon Pass functions as an “earthquake gate”, a critical junction where ruptures on one fault can sometimes propagate to the other under the right stress conditions, potentially triggering much larger, multi-fault events. Historical patterns indicate that joint ruptures across both fault systems have occurred when stress levels on the adjacent segments (such as the Mojave South section of the San Andreas and the San Jacinto Bernardino section) become similarly high and aligned. Today, those segments are modeled at approximately 2.8 MPa and 3.6 MPa, respectively, placing the system in a configuration historically associated with through-going ruptures. This has significant implications for the densely populated greater Los Angeles region, including San Bernardino, Riverside, and critical infrastructure corridors through Cajon Pass. However, the study does not predict the timing of the next major earthquake—such events cannot currently be forecasted precisely. Instead, it provides a physics-based assessment of accumulated stress and the range of plausible rupture scenarios that could occur. [Burkhard, L. M. L., Smith-Konter, B. R., Scharer, K. M., & Sandwell, D. T. (2026). Cajon Pass and the Southern San Andreas Fault System: Earthquake Cycle Stress Accumulation and Present-Day Loading. Journal of Geophysical Research: Solid Earth, 131(6), e2025JB033213. DOI: 10.1029/2025JB033213]

What actually turns a chatbot into an AI agent? The “harness” around the AI model (the large language model, or LLM). In this video I break down what a harness is: a large language model at the core, plus memory, tools, and the engineering systems that make it all work at scale. One piece I didn't get to in the video: the thing that ties it all together is the loop. An agent doesn't just answer once and stop. It runs in a cycle; the model decides what to do, takes an action (call a tool, check memory), looks at what came back, and picks its next move. Again and again, working several steps toward a goal. The loop is foundational to what makes agents work. A key part of that loop is knowing when to stop - recognizing the task is actually done instead of spinning forever or quitting too early. "Knowing when to terminate" is its own small piece of engineering. Model = the brain. Harness = everything that lets it actually get work done. Questions? Please leave them below, and follow along - more on agents (and open-source models like DeepSeek) coming.

This @TEDTalks, How to Build a Career You Actually Love, by @bgurley is awesome both in content and delivery. The big takeaway: it's all about continuous and obsessive learning, which is generally the product of fascination. ted.com/talks/bill_gur…

BREAKING: Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world. We've been testing it internally @every for the last week or so across coding, writing, marketing, editing, and more—here's our vibe check: - It broke our benchmarks. Fable scored a 91/100 on our Senior Engineer benchmark—this is human senior engineer level. The previous high score was Opus 4.8 at 63. GPT-5.5 is a 62. - It's a one-shot wonder. You can set it and forget for hours or overnight on huge coding tasks, and come back to completed work. It cleared entire production bug backlogs, built a playable 3D, and even made a 2-minute animated film—all one-shot. - Taste and attention to detail. In coding and knowledge work tasks, it has much better taste and attention to detail than we've ever seen. It gets subtle things right, adds little features you might not have thought of, and generally understands the assignment in ways that surprised us. - Great use of context. We set it loose analyzing customer feedback surveys and our website data and it came back with a crisp, clean report that identified a. our biggest problem and b. a concrete testable solution—and then we sent it off to build that. - It's best for power users. If you're already used to orchestrating multiple agents in your work, this model can do things that you've never seen before. If you're a knowledge worker or vibe coder with a more basic setup, you're not going to notice a huge difference—in fact, it probably isn't the right model for you. - It's very slow, token-hungry. Using this thing for regular knowledge work is like squashing an ant with a rocket launcher. It also routinely uses 500k to 1M tokens on tasks. That's why it's best for your heaviest jobs—but not as good for tasks like collaborative writing. - It's expensive. It's about twice as expensive as Opus, and it's also incredibly token hungry—so expect it to be something you'll use sparingly unless your company pays for it. Overall, I think of it like a warp drive for coding: It can get you across the galaxy in a few hours, when it used to take months or years. But it's not appropriate for getting around town—you need something faster, cheaper, and more maneuverable. The ceiling is extraordinarily high on this model though. Even our most advanced testers like @kieranklaassen felt like they were only scratching the surface of it. Want our full vibe check with all of our testing and benchmarks? Read it on @every: every.to/vibe-check/ant…

Whatever AI sceptics say, LLMs really can reason. They're not just doing an imitation that looks like reasoning, it's the real deal. But even though they are able to reason, sometimes they won't! If you ask an LLM a question it can't answer, sometimes it will just try to imitate reasoning without doing it. The chain of thought looks basically indistinguishable from actual reasoning. But under the hood something very different is going on. @TrentonBricken talked with me about what work on circuits inside LLMs has revealed:

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time. I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

Claude @claudeai

2 days ago

Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision. The longer and more complex the task, the larger Fable 5’s lead over our other models.

499 2K 15K 5.3M 2K

Recon agenda have been published cfp.recon.cx/recon-2026/sch…. Email have been sent to all training attendees, general email for conference attendees should get sent in the next 48 hours. See you all next week in Montreal!

We’ve spent the last few months reimagining @NotebookLM. It might look similar on the surface but we’re actually rolling out a completely new chat experience today that runs on @antigravity attached to a cloud VM. blog.google/innovation-and…

x.com/i/article/2064…

Also, the new @NotebookLM research agent has the full context of the project you're working on—current sources, chat history, etc—so you can do nuanced research prompts like: "given everything we've reviewed so far, what topics are we missing? Find me sources on those topics."

Josh Woodward @joshwoodward

3 days ago

The new killer NotebookLM feature: easily being able to expand your search beyond your own source files Then, with today's update, you can also make new output formats: PDFs, DOCX, XLSX, PPTX, charts, etc. We want NotebookLM to keep helping you do better research

76 106 1K 176K 218

imagine loops with Mythos...

Matthew Berman @MatthewBerman

3 days ago

wtf is a loop?

68 112 2K 243K 2K

Fantastic new NotebookLM agentic capabilities! It’s always one of my favorite AI apps!

NotebookLM @NotebookLM

3 days ago

Introducing a more powerful NotebookLM 🚀 Massive upgrades deliver agentic capabilities in chat, more advanced reasoning, and a suite of new output formats. Tackling complex, multi-step research problems has never been easier. Rolling out now to Google AI Ultra subscribers.

208 534 4K 842K 2K

I made an angel investment in @tomas_hk two years ago, believing model routing would become a massive business. Now companies are spending $500m per month on tokens. Increased quality and decreased cost are not mutually exclusive. Here's Tomas' essay about how Model Routing Will Control the Future of Economic Value briefing.forwardfuture.ai/p/model-routin…

People are confused about what "loop" means in the context of LLMs. Stop babysitting the model. Build a non-interactive AI application instead. Loops can be simple (ralph, autoresearch) or complex (fabro.sh). Your task: "build the thing that builds the thing."

How anyone can start a $ making business with AI in 15 minutes: > Brain dump everything about yourself into GPT 5.5 > Ask for the top challenges you can solve > Give a challenge to Codex. Ask for solutions you can build > Get the prototype built > Get a design from Claude Design. Hand it back to Codex > Point your project to Hermes who can autonomously work on it > Host it on Vercel > Put it on a Convex database > Create the waitlist > Tweet about it over and over > Make $ It's not rocket science. You find challenges you are uniquely positioned to solve, then solve them with AI You promote through your distribution on X You make money Been doing this for 5 years now and now have a multi million dollar business You can do this too Get to it.

Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.

Great post by @0xkato - How LLMs Actually Work - 0xkato.xyz/how-llms-actua…

Better memory = Shorter prompts = More utility per token

OpenAI @OpenAI

a week ago

We’ve been researching new ways for ChatGPT memory to carry context across conversations and keep it useful over time. Today, that work is rolling out as a more capable memory system in ChatGPT. openai.com/index/chatgpt-…

740 1K 10K 2.6M 3K