All entries

This post compares the outputs of three AI models—GLM-5.2, Fugu Ultra, and Fable 5—using an identical one-shot prompt to evaluate their performance, with the author expressing a preference for Fable 5

Wiki!!! One unexpected outcome of this is that I'm now using the wiki as the ONLY place I run Claude Code I use it as a master controller for all of my repos, kicking off cross-repo tasks and using To

This post announces the release of an open source tool or example demonstrating how to implement wikis for memory management, following up on a previous discussion about this trending approach. The re

Will the AI bubble pop is the wrong question. We partnered with Damon Cassidy, a video essayist with ~300k subscribers: even if it pops, the race to uncontrollable superintelligence doesn't go away. P

This entry documents a Wordle puzzle solution (puzzle #1,837) shared by Anthropic on X/Twitter, showing the complete sequence of guesses and letter feedback that led to solving the word on the sixth a

This appears to be a Wordle game result shared by Anthropic on X (formerly Twitter), showing the solution was found in 4 attempts with a specific pattern of correct (green), present but misplaced (yel

Wow and soon after that @mitsuhiko came by and also expressed interest in analysis of token usage in reviews, a perfect use case for context-lens! I didn’t wake up thinking I’d show my work to @simonw

Yes! Pre-classifying routers are going to result in a lot of bad work because routing is hard and tend to underestimate the value of intelligence on many problems. OpenAI learned this with GPT-5, now

Fable's re-release was recently announced, and Thariq (Twitter handle @trq212) provided commentary or insights on the news in a follow-up discussion. The post appears to be from Swyx sharing reactions

you can now build RLMs with Deep Agents! the more context agents accumulate, the worse they perform, a phenomenon called context rot. RLMs, proposed by @a1zhang from MIT, help: instead of working mode

Recursive Language Model (RLM) workflows are now available as a feature in Deep Agents, allowing AI systems to iteratively call language models within multi-step processes. This capability enables mor

You can start building with GLM 5.2 in minutes: 1️⃣ Download dcode 2️⃣ Select your model (GLM 5.2) 3️⃣ Enter your API key …and you're ready to go with frontier performance on open weights. Great demo

You really need to benchmark models for your use case. As soon as judgements & decisions stack on top of each other, the differences between models amplifies, and no standard benchmark will tell you t

1/ Today, more than 140 companies, most of which compete fiercely with one another, agreed to back the same stablecoin. The vehicle is @openstandard, a new and deliberately independent company launchi

This post captures excitement about an upcoming presentation by Swyx at an AI Engineer conference, noting the unexpectedly large attendance at the event's world fair component. The message was posted

A candid hallway track interview with the man himself - @swyx Mini Podcast if you will, he's told me about a huge milestone tomorrow, things that have surprised him about @aiDotEngineer and ... a few

This post describes a common architectural pattern for integrating memory components into AI systems, illustrated through examples like DeepWiki and AutoWiki that automatically generate and maintain k

A conversation is all it takes to launch powerful ComfyUI workflows. This showcase demonstrates how Comfy MCP can generate, refine, and iterate on creative assets using natural language. To try this w

A great read from @LangChain Best framing I've seen for agent architecture. Every non-model piece like the filesystem, sandbox, compaction, Ralph loops exists to patch a specific model limitation. htt

This post from Nous Research demonstrates a visualization tool or system that maps the accumulated knowledge, memories, and skills learned by a Hermes AI agent during its training or operation. The in

A study from @Stanford showed that 71.3% of chatgpt queries could be accurately answered by a local model. I suspect a major part of enterprise AI workloads could be run locally too for free (compared

a very cool Harbor x LangSmith flow I love to help you “look at the data”: 1. you do evals or rollouts for RL 2. all reward metrics and traces and rollouts get automatically propulates into Experiment

Added this for everyone else through the /usage command! Run `/usage` and get this breakdown wherever you use Hermes Agent :) starting today you can now see a breakdown of your context usage per sessi

After 18 months of writing, coding, and experimenting, Build a Reasoning Model (From Scratch) is finally out! My first copies just arrived! 📚 440 full-color pages. Inference scaling, reinforcement lea

Code-writing AI agents can solve complex problems more effectively than agents using other approaches, but deploying them requires executing potentially untrusted generated code within sandboxed or is

agree a lot with this - the actual storage layer for memory (eg which database you use) matters less than the process around that data (retrieval, ingestion, etc) @hwchase17 what if memory is not stor

Agree is a TypeScript library by Boris Cherny that provides a schema validation and serialization system, enabling developers to define data schemas with type safety and validate data at runtime. The

And that’s just the tip of the iceberg USAID ran a secret fake Twitter to spark revolution in Cuba. Funded Venezuelan opposition politicians directly. Got expelled from Bolivia after WikiLeaks cables

I can't provide a summary of this post without access to its actual content. The title appears to reference legal judgments involving a U.S. president, but I would need to verify the specific claims a

As open models get stronger, more workloads move into the competitive inference market. That pushes the real fight toward speed, cost, reliability, and control. Together AI is where open models become

'At this very moment China is giving its AI technology away. It's releasing open-weight AI models that are cheap, capable, and they're fast becoming the world's default.' We can overcome this. @neil_c

Being at the launch of Cybercab two years ago was magic. A decade from now there will be millions of these things rolling around the world. The war over autonomous vehicles is on, as everyone in San F

BREAKING: Philippines becomes the first country in Southeast Asia to commercially launch Starlink Direct-to-Cell through a mobile network. Globe has secured regulatory approval to offer Starlink Direc

Bridgewater, one of the worlds largest hedge funds, a Tinker customer talks through how they've carefully fine-tuned a model focused on what makes interesting financial news. Their fine-tuned model is

Building voice agents can come with tradeoffs. 💬 Better convos w/ speech to speech models Vs 🥪 More reliable harnesses w/ sandwich architecture How to build a voice research agent with both: ✅ Gemini

Can regularization based JEPA (e.g. SIGReg) scale and compete with SOTA foundation models (DINO)? Here is the answer: yes and with 10x less data. VISReg (slight variation of SIGReg) competes with DINO

The post references someone attending AIE (likely an AI or tech conference) and describes having a positive experience, with 'certified token billionaire' appearing to be either a humorous self-descri

This post discusses how the metaphor of 'factories' for AI systems presents a pessimistic framing of the future, arguing that the language and analogies we use to describe AI development shape our per

Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside the browser and terminal, you now get a first-class desktop experience with Claude Code, Claude Cowork, and chat on all

Claude Sonnet 5 is now available as a model option in the Cursor code editor. On CursorBench, Sonnet 5 achieves a 57% score compared to Sonnet 4.6's 49%, representing a meaningful performance improvem

Claude Sonnet 5 has been integrated into Devin Desktop and Devin CLI, offering advanced coding capabilities at a more competitive price point than previous models. This release represents an update to

Claude Sonnet 5 is now available for use in Perplexity, accessible to Pro and Max tier subscribers. Users can also select Claude Sonnet 5 as an orchestrator model within Perplexity's Computer feature,

Common challenge that will come up in the near future is capturing the gains of greater AI intelligence in organizations. High human capital firms need to be set up to benefit from their high-quality

Context engineering has its own track at the @aiDotEngineer World's Fair this year. 🎉 I've respected what @swyx ​and the @latentspacepod team have been building for years — and I'm pumped to be a part

Cool new paper from NVIDIA. Looks like agentic coding is moving into hardware design. HORIZON treats hardware design as repository-level code evolution. A Markdown harness becomes a project pack with

This post references a talk given by @bclavie at an AI engineer event hosted by Mixed Bread AI, featuring cute illustrations and exploring the distinction between code as a form of knowledge represent