Knowledge catalogue
We just got back from our team offsite in Hawaii - and wow, did we need it. 🏝️☀️ Our team has been heads down driving some serious growth, and this trip was the perfect reset. We spent the time doing
Google AI's Gemma 4, released on April 2, 2026, is Google DeepMind's most capable open model family to date, purpose-built for advanced reasoning and agentic workflows . The models are available ...
We pit LlamaParse against frontier models (Opus 4.6, Gemini 3.1 Pro, GPT-5.4) in a live OCR arena. ICYMI: the full workshop is on Youtube! Frontier VLMs are getting quite good at visual understanding,
We worked with @RWSGroup to fine-tune our Command translation model, which improved language and cultural expertise. Now, that model is the “brain” that powers RWS’ Language Weaver AI translation solu
Week 3 winner of the Agent 4 Content Challenge: Magomed Kurbaitaev 🎉 Built: https://help-dagestan.replit.app/ A real-time disaster coordination platform that connects flood victims with verified local
Welcome to the singularity 😎 hermes agent from @NousResearch is the fastest growing agent of all time. @OpenClaw went from 0 → 40K stars in 61 days. hermes did it in 45 days. in the past 7 days alone,
what a week! @swyx and team built the room, the builders filled it. never been a better time to be a builder in Europe And that's a wrap! AI Engineer Europe 2026 has concluded. Our video crew did incr
What does it actually take to make agents better over time? A system that starts with a trace. You capture traces of agent behavior, enrich them with evaluations and human feedback, identify what’s fa
what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned from the Claude code leak” bros 👀 orchestration patterns, tool d
What if a model became the computer itself? NEW paper from Meta. (bookmark this one) What if the model wasn't just using the computer, but became the computer? New research from Meta AI and KAUST make
why not? what in the current harnesses are not bitter lesson-pilled? off top of head: will go away: - planning tools - compaction (or at least will matter less) not going away: - sub agents - skills -
On April 10, 2026, Anthropic posted their Wordle 1,756 result on X (Twitter), completing the puzzle in 5 out of 6 guesses. The answer to that day's puzzle was **CAROM** — a noun and verb meaning, ...
wow. GenAI is definitely not living up to the hype, for most people. 🦔A global survey of 3,750 executives and employees found that 54% of workers bypassed their company's AI tools in the past 30 days
Wrapped up the 3-day AI Engineer conference in London. Key takeaways: Planning & verification > implementation. Humans define what to build and validate it works. AI handles the coding. The harness ma
Yeah It's incredible the extent to which the social sanctioning engine has simply seized up. Hit pieces that would have been 5-alarm fires 5 years ago now come and go with no notice. Nobody cares, it'
Yet another illustration of why LLMs aren’t even close to being AGI. The world’s best LLMs are still terrible at poker. We put each model into a 200bb heads-up NLHE match against GTO Wizard AI. The be
A tweet by @luebken captures a moment from the AI Engineer (aiDotEngineer) London event in April 2026, noting that swyx (Shawn Wang) — co-founder and organizer of AI Engineer — was personally handi...
Yup These dumb policymakers now want to force Grok to their lunatic woke ideological views!! For Grok this affects the entire world and how AI is used!! This ain't just Colorado BS - it goes global an
1️⃣✅❌ 2️⃣✅❌ 3️⃣✅❌ One of the benefits of Deep Agents deploy is model optionality Choose from models from @OpenAI @GeminiApp @AnthropicAI @FireworksAI_HQ @baseten @OpenRouter @ollama @nvidia and many o
(1/5) FP4 hardware is here, but 4-bit attention still kills model quality, blocking true end-to-end FP4 serving. To fix that, we propose Attn-QAT, the first systematic study of quantization-aware trai
Anthropic's new hosted service for long-running AI agents, designed to solve the challenge of creating systems that support 'programs as yet unthought of.' It abstracts infrastructure management to en
@3blue1brown https://x.com/verncrawford/status/2042344703077859402?s=46 @NousResearch 2 prompts guys. 2 prompts!!! The second prompt was “go from 6 camera moves to 3.” (Hermes Agent, Codex5.4, Manim V
>8 out of 8 [cheap oss] models detected Mythos's flagship FreeBSD exploit Completely disingenuous They gave it just ~20 lines of code to read. They baked in custom, relevant context pertinent to the e
92% of COBOL developers are expected to retire in the next four years, and 68% of enterprise COBOL modernizations are failing. Agents can help – we wrote up how: https://cognition.ai/blog/how-devin-is
A bit over a decade ago, we got fuzzers. A fuzzer is an automated vulnerability-finder that repeatedly runs a target program with semi-random inputs. One particular fuzzer, American Fuzzy Lop, was not
Fardis Makraduli ([@f_makraduli](https://x.com/f_makraduli)) shared a post about attending the AI Engineer ([@aiDotEngineer](https://x.com/aiDotEngineer)) event, noting shared themes and networking...
A different sense of the word “bubble” @GaryMarcus It's actually kinda hilarious that @OpenAI thinks that buying a niche tech podcast followed mostly by Bay Area insiders is going to solve their colos
I was unable to retrieve the specific tweet at the URL provided (status ID 2042072653658460260). This appears to be a future-dated or non-existent post — the status ID is beyond what currently exis...
a useful mental model on how teams can think about good data design to improve their models/agents: Evals ~= Training Data ~= Environments - in Classical Deep Learning, we learn from each training exa
Accurate In 19 days, a jury in Oakland is going to decide whether the entire legal foundation of the AI industry is built on fraud. Everyone thinks the Musk vs Altman lawsuit is a billionaire grudge m
The Electronic Frontier Foundation (EFF) announced on April 9, 2026, that it was leaving X (formerly Twitter) after nearly 20 years on the platform, citing a dramatic collapse in reach: an X post ...
After playing with it a bit, Meta's Muse Spark Thinking is fine so far, but really doesn't match the current Big Three models. It also is a bit... weird. Like some strange language & tone, a little lo
Agents like @openclaw are incredibly powerful, as long as the information they receive is clean and structured🦞 When it comes to PDFs and other unstructured documents, most agents struggle. The tools
AI Engineer after hours @altryne @steveruizok @maximelabonne As tradition, the AI Engineer speaker dinner is a great kick off before the first day of talks tomorrow! If you're ever debated submitting
AI is jagged, but I think sometimes it is easy to overly focus on that. The generalness is a surprise too! LLMs may be optimized for verifiable fields like coding, but AI is also not bad at corporate
AIE Europe 2026 - Session Day 1 in the books! So much energy & enthusiasm here -- we had such a blast! Thanks to all of our speakers for anchoring this event -- and to our sponsors for making the even
The specific tweet from Gary Marcus (X post ID 2042361570253217968) is not publicly accessible without authentication, and the search results do not surface its specific content. Based on available...
All users can link their accounts, access the portfolio page, and ask Perplexity about their finances. Computer tasks are exclusive to Pro and Max subscribers. Read more: https://www.perplexity.ai/hub
Also not a sign of someone who has any clue about the realities of current neuroscience. Sam Altman has admitted he is on a waitlist for a procedure that would digitize his brain. The procedure would
And all the evidence is is that is that models are getting better all this other stuff at the same time as they are improving in coding. More recent models are more creative, for example. Still plenty
And that is what Thoth uses for its agents in the backend. Thanks for your contributions to oss @LangChain @hwchase17 https://github.com/siddsachar/Thoth AI that doesn't just work for you, it knows yo
Announcing the @LangChain podcast -- Max Agency. Deep context to give you the edge while building and iterating on agents. Watch the full episode on: - Youtube: https://www.youtube.com/watch?v=Xyh1Eqc
Another banger paper from Microsoft. Why it's a big deal: It teaches reasoning models to compress their own chain-of-thought mid-generation. The most interesting finding isn't the 2-3x memory savings
A post from X (formerly Twitter) by user Yuchenj_UW, shared or referenced by Swyx, humorously contrasts Anthropic's AI capabilities with the persistence of TurboTax, the widely criticized tax preparat
Anyhow, its not bad. Just not the vibe level that the benchmarks might indicate. And, for a first re-entry into the frontier model space, given the engineering efficiencies they achieved, it feels lik
At 15:10 today, I’ll be speaking about our SWE-rebench leaderboard at AI Engineer Europe. I'll cover how we build evals and how models cheat! Come listen and let's chat! So far, this is the coolest ap
Automating Loan Income Verification with AI agents 💸☑️ Loan processors spend a huge portion of time verifying the borrower’s documents (tax forms, pay stubs, bank deposits), and cross-checking them fo
I was unable to retrieve the specific content of the X/Twitter post at the URL provided (https://x.com/elonmusk/status/2042071672686293001). The post ID `2042071672686293001` appears to be a future...
calling all of my fellow podcast nerds! 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeoffs, evals,
On April 9, 2026, Elon Musk posted 'Canada is cooked' on X (formerly Twitter) in response to a viral clip of Canadian MP Leah Gazan using the government acronym 'MMIWG2SLGBTQQIA+' during a parliame...
Can’t get enough of Harrison and his AI takes? Lucky for you, we’re announcing Max Agency where you can hear him & other industry experts talk agents, harnesses, models, evals, and more!! 🎙️Introducin
Can’t trust WhatsApp 🚨 WhatsApp’s “end-to-end encrypted” privacy is a total lie. New class-action lawsuit just dropped: Meta secretly let employees, contractors like Accenture, and third parties read,
Checkout our new Max Agency podcast - the first episode is already out! 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architect
Claude Agent SDK tracing in LangSmith just got an upgrade. Now you can trace: → Subagents → Child runs inside MCP tools → Cost tracking + more Update to the latest Python SDK to try it out. Docs: http
Claude Cowork, now generally available! We released Claude Cowork as a research preview 12 weeks ago. Since then, millions of people have made it part of how they work - and hundreds of thousands more
Cognition is live in Japan! 🇯🇵 We launched today with Tokyo Merge - a standing room only event with industry leaders across the country. We’re hiring, partnering, and building in Japan. If you’re buil
Ryan Lopopolo, a Member of Technical Staff at OpenAI, posted this tweet inviting people to discuss harness engineering with him in-person at Westminster — referencing his broader work on the topic....
Computer now connects with Plaid to link bank accounts, credit cards, and loans. Track spending in detail, build custom budget tools, and visualize your net worth alongside your investment portfolio.
Cursor cloud agents now run in isolated virtual machines where they can build, test, and verify their own code — then automatically attach artifacts such as videos, screenshots, and logs to the pul...
On April 9, 2026, Elon Musk posted 'Cybertruck is so awesome 😎' on X (formerly Twitter), reposting content originally shared by the account 'HustleBitch.' The post accumulated over 26.1 million vie...