Wordle 1,780 3/6 🟨⬛⬛🟨🟨 ⬛🟩⬛⬛⬛ 🟩🟩🟩🟩🟩
This entry documents a Wordle game result where Anthropic solved puzzle #1,780 in three attempts, using emoji indicators to show letter positions (yellow for correct letters in wrong positions, green
Knowledge catalogue
This entry documents a Wordle game result where Anthropic solved puzzle #1,780 in three attempts, using emoji indicators to show letter positions (yellow for correct letters in wrong positions, green
Gary Marcus reported that Greg Brockman, OpenAI's President, had a $10 million side deal with Sam Altman during OpenAI's early nonprofit period that was not disclosed to Elon Musk or documented in non
You can build a full pitch deck in Replit without touching a single slide. Just describe what you want, iterate in chat, edit visually, then export to PPTX, Google Slides, or PDF (or publish a live UR
A case study in suicidal empathy. Read @GadSaad ‘s upcoming book on the subject. The kicker: none of this will change her political views. She’ll still promote the same policies and vote by the same w
Sam Altman's post argues that the Agents SDK 2.0 is underappreciated or overlooked despite its capabilities and potential value. The post likely discusses features, improvements, or use cases of the A
agreed The core argument of my latest article 'There is no AI race' was that the 'AI race' between the US and China is a manufactured narrative concocted by US tech companies to serve their corporate
AI will create more jobs than any other technology in history. The doomers' fundamental error isn't just the lump of labor fallacy. It's deeper than that. They assume a finite problem space. This is t
Altman’s bait-and-switch: So, my problem with this is, Altman basically admits he's been running a confidence game for years about this singularity stuff, then pivots when it becomes inconvenient, and
Brian Moore's interactive clock comparison tool demonstrates the significant performance gaps and inconsistencies across different AI systems when performing the seemingly simple task of displaying ti
Ancient cultures were extremely violent, not “peace-loving ecologists” at all! David Reich on how much ancient DNA evidence has overturned so much consensus thinking how ancient cultures spread. 'It w
Clem Delangue announced the birth of a child named Johnny Cash, sharing the news on X with a playful reference to 'Alpha' and 'ReachyMini.' The post appears to be a personal announcement celebrating a
Another day, another product idea from @swyx Introducing the Locker extension: - Attach any files from your locker to an upload box - Generate files or use @tldraw to create on the fly - Still 100% Op
This post draws a comparison between how parents measure their babies' development and relationship milestones, noting that both shift from month-based to year-based metrics around the 18-24 month mar
Sebastian Raschka maintains a comprehensive gallery of LLM architecture diagrams and visualizations on his website, with higher-resolution versions available at sebastianraschka.com/llm-architecture-g
Demis Hassabis says he plays chess with Gemini to trace the model's chain-of-thought. As a former chess prodigy, he can tell when the model starts reasoning itself into trouble. Sometimes it sees a bl
SpaceX confirmed the successful deployment of the CAS500-2 satellite, according to an announcement by Elon Musk on X (formerly Twitter). The CAS500-2 is a commercial communications satellite that was
efficiency is back on the menu again boys https://x.com/jbhuang0604/status/2050686882653065496?s=46 Keep getting rate-limited by Claude, so I tried out DeepSeek V4 for the first time. After 10M+ token
Elon keeps warning about birth rates because this is not a spreadsheet problem South Korea near 0.7 fertility US hitting record lows Most rich countries far below replacement Were more focused and get
Every American should demand fair, secure elections. Without them, we don’t have a country. For years, the left has been playing a dangerous game, trying to redefine voting, reshape representation, an
Everyone interested in getting the most out of Hermes Agent should definitely consider joining the Nous Research discord - We have a forum channel for plugins skills and skins and another for communit
SpaceX's Falcon 9 rocket successfully launched the CAS500-2 mission from a California spaceport, deploying 45 payloads into orbit. This mission demonstrates SpaceX's capability to conduct rideshare la
SpaceX's Falcon 9 first stage successfully completed a landing at Landing Zone 4, demonstrating the company's reusable rocket technology. This achievement is part of SpaceX's ongoing efforts to reduce
Features - Multi-agent: each task runs on a specialized profile, with its own tools, skills, and personality. - Linked tasks: parent → child dependencies. Fan out work, gather results, continue. - Sha
For those who are trying to scam X Ads, use fraudulent credit cards etc. Better make sure your opsec is flawless because we are coming for you. I already got a few IPs, and we are drafting up subpoena
Sam Altman posted a message referencing @gao_zibo with a statement about future developments or features coming to OpenAI's products or services. The specific details of what is 'coming' are not evide
Grok, Elon Musk's AI chatbot developed by xAI, is experiencing increased popularity and user engagement on the X platform. The post indicates notable trending activity around Grok, likely reflecting g
Ha love to see this port of flue to python Harness engineering is a fun time! Need more people exploring! 🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Sch
This post documents a second wave of large language model and AI architecture releases from April, featuring updates from multiple organizations including Ant Ling 2.6 1T, Minimax M2.7, Xiaomi MiMo V2
This tutorial provides guidance on using Kanban board features within the Hermes Agent platform by Nous Research, covering how to organize and manage tasks or workflows using the Kanban methodology. T
Hermes Agent now has multi-agent via the Kanban, new in v0.12.0. Agents claim tasks from a board, work in parallel, and hand off when blocked. You watch progress and unblock from one easy view instead
http://infinitybuilds.gg The best Diablo 4 website. One community. We aim to support every language the game supports. Translations powered by Grok — built to understand the universe. No better AI for
i actually don't want this 'but you don't review compiler output either' meme to die. it's the perfect signal for being immediately able to ignore someone in this space. Interesting article on treatin
I am not sure I would agree with all of this, but the relationship between Anthropic and Claude is quite different than the relationship between other labs and their models. And that shows up in lots
I have an utter respect for Richard Dawkins, for his brilliance, sheer intelligence, and his works. But @GaryMarcus has a valid critique [1]. [1] https://garymarcus.substack.com/p/richard-dawkins-and-
I hear this take (usually from the model labs), but that will just mean more people turn to open source models, no? They’re already cheaper, if they have similar performance (because they’re less coup
Elon Musk expressed enthusiasm for large-scale machinery in a post on X (formerly Twitter). The statement likely reflects his interest in heavy equipment or industrial machines relevant to his compani
if even coding doesn’t make serious RoI for users, the jig is probably up. Economics of AI coding tools are crumbling. Cost per developer has doubled because cost of Claude code and microsoft copilot
This post is a humorous thought experiment comparing how GitHub's features, policies, and design would differ if the platform were developed in various countries and regions, each reflecting their dis
I'm obsessed with running local LLMs. Been working with an engineer to build product(s) that are 100% local. A new model that came out recently instantly improved the quality of our product. We live i
Sam Altman expressed that Greg (likely referring to Greg Brockman, OpenAI's President) was instrumental to OpenAI's success, stating it would have been impossible for the company to achieve its accomp
“In summary, there is very little evidence for LLMs benefiting patients or doctors for health outcomes” - Dr. @EricTopol Read his full review here: https://open.substack.com/pub/erictopol/p/the-parado
🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott @FredKSchott CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings prog
it has been a real pleasure to work with Greg over the past decade. i feel very lucky. this post held up pretty well, but not did not sufficiently highlight his technical brilliance and sheer determin
it's always funny to me when these bot posts say we *just* launched deepagents... like nah man we've been carving this stone for close to a year now! Long-running agents almost always fail because the
It’s been almost six weeks since Jensen Huang claimed we had achieved AGI. Why don’t I feel any different? https://www.forbes.com/sites/antoniopequenoiv/2026/03/23/nvidias-jensen-huang-says-he-thinks-
Its getting hard to benchmark frontier agent performance on longer tasks. Repeated measurement is very expensive and there are differences between using models in harnesses versus via APIs. I suspect
It’s hard to understand what the other 39% are thinking. Once you drive a Tesla, it’s like driving an all-seeing sensor with a super computer behind the scenes doing all the decision making, driving a
Jessica Winter has been raising her children to detest A.I. Then her daughter’s public middle school began receiving Google Chromebooks, which came pre-installed with an all-ages version of Gemini, a
Joseph Gordon-Levitt argues that most AI systems are fundamentally built on 'mass theft,' contending that companies deploying large language models without proper authorization or compensation for tra
JP Morgan's investment research team just shared exactly how they built their multi-agent system 'Ask David', and it's the same architecture pattern showing up everywhere: - supervisor agent orchestra
A Kardashev Type II civilization would require enormous energy production capabilities, potentially necessitating large-scale manufacturing and resource extraction from the Moon to support such advanc
Many people (incorrectly) think Native American tribes lived in peace and harmony. The noble savage myth is merely a myth. Ancient cultures were extremely violent, not “peace-loving ecologists” at all
Men have become one point more conservative - women have become 23 points more liberal. That's an interesting chart. Young men have stayed similarly conservative for over 25 years, while young women h
Meta bootstrapped China, reaped the positive PR for being “open”, and then went back to being closed. Meta abandons open-source Llama for proprietary Muse Spark https://thenewstack.io/meta-abandons-ll
Much respect to @tokengobbler who shutdown Vibe-kanban live onstage at AIE Europe - still with 30,000 MAU, and still living on as an open source project. 'Everyone who is making money is doing 2 thing
Of course Pynchon would call this correctly 40 years ago: “It will be amazing and unpredictable, and even the biggest of brass, let us devoutly hope, are going to be caught flat-footed.“ He and Dougla
Swyx shared a personal milestone about completing his second short story after a three-year gap since his first one, addressing fellow users @deepfates and @mada299. The post reflects on the extended
Old days: “Bigshot chief scientist of major corporation can’t handle criticism of the work he hypes” New days: “Same bigshot no longer hypes LLMs; can’t handle the fact that someone else noticed flaws
This post likely discusses open source AI and language models, potentially covering developments in model accessibility, licensing, or comparisons between proprietary and open source approaches. Given
our docs are a great place to get started! we try to make all conceptual guides applicable to a wide range of experience levels. if you need a more structured learning format, check out langchain acad