Knowledge catalogue
Your coding agent bill doubled and nobody can tell you why. Here's the actual reason: Claude Code, Cursor, and Copilot all log activity in different formats. The second your team uses more than one (t
DSGym is a comprehensive framework designed to evaluate and train AI agents for data science tasks, providing a structured environment for benchmarking agent performance across various data science wo
1/ On Training in Imagination - Dwarkesh's episode has a segment on dreaming as one of the next training paradigms. The idea is that a model learns mostly inside its own, by imagining what would happe
ThunderAgent is an agentic inference system designed for fast and efficient execution of AI agent programs, developed by Together AI. The system appears to optimize program-aware inference by leveragi
TTT-Discover is a method that enables models to learn and discover patterns during test time rather than only during training, allowing for adaptation to new data distributions at inference. The appro
RARO (Reasoning via Demonstrations) is a method for training AI models to improve reasoning capabilities by learning from demonstrations rather than relying solely on external verifiers. The approach
This paper presents V1, a framework that unifies text generation with self-verification mechanisms to enable parallel reasoning processes in language models. The approach allows models to generate mul
Aurora is a unified training-serving system that integrates reinforcement learning with adaptive speculative training to optimize large language model inference and training efficiency. The system dyn
Untied Ulysses is a memory-efficient technique for context parallelism that processes attention heads in chunks rather than sequences, reducing memory overhead during transformer inference and trainin
Opportunistic Expert Activation (OEA) is a batch-aware expert routing technique for mixture-of-experts models that enables faster decoding without requiring model retraining. The method optimizes whic
ParallelKernelBench is a benchmarking framework designed to evaluate large language models' ability to generate optimized GPU kernels for multi-GPU computing environments. The benchmark assesses LLMs
A basic sigmoid extrapolation suggests that this measurement will be close to its performance ceiling in around a year---meaning most randomly sampled remote work projects would be highly automatable
a bit of a teaser for the upcoming talk @aiDotEngineer World's Fair 12:05 pm, Room 2003 Intelligence != Expertise Intelligence + Continual Learning = Expertise I will share some thoughts about continu
A once in a lifetime crossover between @aiDotEngineer and @FIFAWorldCup is happening in SF! 100 speakers from AIE got the golden pass to see team USA kick Bosnia's ass!! Thanks @swyx @liamcbride and T
This post by Harrison Chase, creator of LangChain, likely discusses the concept of building specialized wikis or knowledge bases tailored to specific domains using AI and language models. The idea sug
After helping build FaZe Clan from the ground up, @FaZeApex is starting fresh as a YC-backed founder with his new venture, @TryNearby_. Watch the full interview on YouTube to hear how he's bringing a
Again, 2 weeks missed. No rehab. Rib injury, which really affects ability to rotate (comfortably) and he's just raking. He's on a heater. It is kind of unfathomable that Chase DeLauter missed two week
“Agentic kernel optimization is the future of on-device inference” @xenovacom used Fable 5 to write kernels that pushed Gemma 4 to a massive 255 tok/s on WebGPU with M4. He shared the demo, so you can
'agentic map reduce' is a nice name spawning subagents programatically allows you to do these advanced agent patterns, where you want some determinism to control how agents are created/run check out d
Agentic retrieval is changing the way retrieval-augmented applications are built, especially in domains like legal and fintech, where agents need to autonomously navigate large, evolving knowledge bas
AI gave us speed. What’s missing? Experience. Wisdom. Its neural networks are an incredible compressed representation of humanity’s knowledge. But trusting their judgment is still a challenge. Can exp
ai pickleball tournament was actually so good. they executed the concept perfectly. glad @MehulKalia_ and i showed up from Notion to see some familiar faces :) @braintrust @modal @browserbase @llama_i
AI systems that are accessible or even better open-source are safer for a simple reason: more people can inspect them, test them, stress them, and report what breaks or harms to keep the builders acco
This post praises the content quality and organization of AIE (likely an AI or technology conference), suggesting it exceeded expectations and set a high standard compared to other tech conferences. T
This post discusses ongoing efforts to improve AI safety safeguards, specifically refining systems to accurately differentiate between genuine misuse and legitimate user requests while addressing edge
Apparently we didn't talk enough about w̶o̶r̶k̶f̶l̶o̶w̶s̶ loops yet! See ya there! @steipete is now joining us for Crafting Software Factories! 📅 6pm Wed evening in SF after the @aiDotEngineer World's
ARC-AGI-3 is built different, it has dumbfounded almost all regular attempts so far because it's so much harder than anything that came before. It has no rules, it's agentic and has no explicit goals,
Are there any CS profs left at Berkeley and Stanford? Might as well just merge all the PhD students into the big labs at this point Department Chair of Electrical Engineering and Computer Sciences at
As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that ad
This post humorously describes using Claude AI as a learning tool to understand Microsoft Teams functionality for first-time users, shared during an AI Engineer event discussion. The post suggests Cla
This post likely references a casual, positive experience at an event or space associated with @aiDotEngineer, highlighting a 'puppy zone' as a memorable or enjoyable feature. Without access to the fu
Build a in-browser debug mode sort of tool for @LangChain deepagents that resides a shortcut away. Helpful to debug there and then as the conversation is going on without switching tabs, like seeing a
@_catwu @simonw and I will be doing a fireside chat about 'This year in Claude' from 12:30pm-1:30pm at AIE in Expo Stage 2. We'll be covering a really wide range of topics and I think it will be reall
Claude Fable 5 has been re-enabled as an available model option within Cursor, where it achieves the highest performance scores on CursorBench among all supported models. However, it comes with the hi
Claude Fable 5 is available in Devin. You can use Fable 5 in Devin Cloud’s Ultra agent, our smartest and most capable agent, which excels at long-horizon tasks and debugging. Claude Fable 5 is also av
Claude Fable 5 has been re-enabled as an orchestrator model option within Computer, Anthropic's AI system for automated task execution. This announcement from Perplexity indicates that users can again
Claude Fable 5 will be available again globally tomorrow. After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and blo
🖲️ Codex Reset Distribution Initiated! 🚨 Loved celebrating this moment with the community. Enjoy your extra reset in the bank. Happy Codexing! Media 🖲️ We love our community! To celebrate getting toge
This X Spaces broadcast from Pinecone invites developers to join a live discussion about building applications and solutions using Pinecone's vector database platform. The session likely covers use ca
Congratulations to our friends at @togethercompute. Exciting moment for open models!! We @togethercompute believe intelligence should be abundant, not expensive. Today we announced our Series C fundin
Sparse autoencoders (SAEs) are used in Krea 2 for dataset curation and exploration, enabling more interpretable analysis of training data through learned sparse feature representations. This applicati
Creating AI voice agents has become ridiculously easy xAI’s Grok Voice Agent Builder lets you deploy a human-like voice agent in under 2 minutes - no coding required It is currently in beta, but the s
A ComfyUI creator demonstrated a morphing transition workflow using ComfyUI Cloud integrated with Seedance 2, enabling seamless frame blending and character consistency across animated transitions. Th
Cross-agent feedback loops are incredibly effective -- for a reason. Check out what @leon2mcp and team at @Bloome_im are building in this space: http://bloome.im Bloome lets you pull Claude, ChatGPT,
Day 2 in 30 seconds. Packed keynote halls, a retro arcade battle on the show floor, and Mochi doing crowd control at the expo pen. Day 3 starts now. World Cup finals, the Autoresearch keynote, Moscone
do you know what you pay for in agentic workloads? cached tokens! session with 50+ tool calls -> prompt is billed 50 times all providers give 1/5 cached discount for GLM-5.2 we at @FireworksAI_HQ drop
DOGE showed they were morons with a series of gotcha moments: - DOGE claimed to have discovered USAID was paying for condoms for Gaza which they joked was for 'gay Hamas.' It turned out the condoms we
Donald Trump made more than $2 billion last year while lying that affordability issues are a hoax and prices are going down. Never in American history has a man exploited the White House while in offi
Elon Musk explains one of the most optimistic futures imaginable: Neuralink and Optimus restoring lost human abilities through real-world cyborg technology And the first people this could help are the
I can't verify the specific claims in this post title. The source appears to be a social media post attributed to Yann LeCun discussing Elon Musk's response to criticism regarding DOGE (Department of
Enjoy the codex reset people. A user got to push the secret button and suddenly all of you got more tokens. Hope the button goes back to @thsottiaux where it belongs. (Also I think @sama has one) Medi
ENPIRE -> ASPIRE, our 2nd work in the series for Physical AutoResearch. We are building the components for robot self-improvement, one /skill at a time. Today, we give robots a /skills library that se
excited to get Fable back in your hands! We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5. We'll begin restoring access tomorrow, and wil
This post is a brief social media testimonial from someone who attended an event where Swyx delivered a keynote address. The speaker expresses enthusiasm about both Swyx's keynote performance and thei
Excited to release OpenWiki! OpenWiki is the easiest way to generate and maintain documentation in your codebase, built specifically for agents to consume Get started with a single command: `openwiki
Fable 5 back Lebron possibly to the Warriors AI eng world fair it's a good week to be in SF We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mytho
Fable 5 has been announced or is in development, marking the return of the Fable franchise. The announcement was made by Thariq on X (formerly Twitter). This likely refers to a new entry in the action
Trq212 is presenting a Field Guide to Fable at AI.Engineer World's Fair, indicating renewed interest or development in the Fable project or framework. This presentation likely covers Fable's features,
Fable is very good, and having it taken away after getting early access delayed a few things I was working on and made me defer others until it returned But in my early access I also tripped the secur
Fable, the indomitable model from Anthropic, is coming back. These last two weeks have been a great reminder that: models can be removed at any time, you should have fallback plans (including open sou