Knowledge catalogue
check out thoth - agent harness with sota memory built on langgraph Memory is core to your system. The Assistant or Harness needs to be built around it. Local, Internal & Eternal. SOTA Memory is integ
Chiasmus (reversing grammatical structures in two sentences for drama). Asyndetic tricolon (three items listed without a conjunction). Parataxis (short and somewhat disconnected dramatic sentences). S
Claude Code is not AGI, but it is the single biggest advance in AI since the LLM. But the thing is, Claude Code is NOT a pure LLM. And it’s not pure deep learning. Not even close. And that changes eve
Closing thoughts on ai engineer conf: - weather so great - did not like the venue one bit - can’t say any talks really stood out for me - but had very interesting hallway conversations. Especially wit
OpenAI's Codex App (available at chatgpt.com/codex) is a dedicated command center for agentic coding, enabling developers to manage multiple AI coding agents working in parallel across projects. T...
OpenAI Codex CLI is an open-source, terminal-based coding agent built in Rust that can read, modify, and execute code locally within a selected directory. It is included with ChatGPT Plus, Pro, B...
Cristobal Valenzuela, co-founder of Runway, shared a post on X titled 'Cooking time,' likely teasing or announcing an upcoming AI product, model, or creative tool in development. The phrase 'cooking t
Couldn’t agree more! We’re moving towards Nuerosymbolic AI - there’s masses just haven’t realized it yet, in the sense of understanding what the literature proposed and why the latest developments are
Cybertruck is so awesome. Until you’ve tried it out, you have no idea, because there’s nothing like it. Best product Tesla has ever made to date. Cybertruck is extremely comfortable on long trips espe
Daniel Moreno-Gama/ dmgama/ Butlerian Jihadist was booked on suspicion of attempted murder. He is an active PauseAI member, who frequently stated the urgency: 'We are close to midnight, it's time to a
Gary Marcus, an AI researcher and cognitive scientist, posted a tweet advocating for a boycott as a nonviolent, non-confrontational form of protest or opposition against an unnamed individual. The pos
Harrison Chase, co-founder of LangChain, wrote a post in a similar style to a piece by Sarah Wooders, focusing on the concept of 'your harness, your memory' in the context of AI agents and memory syst
Esse post do Gary Marcus explica algo bem importante: a potencialidade que é o que chamamos IA Neurosimbólica: a combinação do melhor de dois mundos! Claude Code is not AGI, but it is the single bigge
SpaceX successfully launched 25 Starlink satellites aboard a Falcon 9 rocket from a California launch site, expanding the company's broadband internet constellation. This mission is part of SpaceX's o
Elon Musk posted on X announcing that Falcon has landed, likely referring to a successful SpaceX Falcon rocket booster recovery or landing milestone. The post celebrates a key achievement in SpaceX's
Tesla's Full Self-Driving (FSD) system was activated for the first time in the Netherlands, marking a significant expansion of the autonomous driving feature into the European market. The post, shared
Swyx (Shawn Wang) posted about flying directly back from London to perform a Broadway cabaret show, noting the event had very limited seating. The post includes an apology for not advertising the even
For AI agents, when you want every last bit of what is possible, open source is turning out to be the only way Hot take: I can't see any startup building their critical core operations on Claude Manag
🚀 for all mankind 🚀 @elonmusk Thank you, @elonmusk - the four of us glimpsed the red hues of Mars far in the distance as the sun slipped behind the Moon and there was zero doubt in our minds that the
For once I actually agree with the constructive argument here. There are more approaches that allow you to own your own destiny. Memory is just context after all and you can provide that at many place
Gary Marcus 又放大招了！ 他直接把 Claude Code 源码泄露后的核心真相点破： ✅ Claude Code 是 LLM 时代以来最大进步 ✅ 但它根本不是纯 LLM，也不是纯深度学习 ✅ 核心文件 print.ts 足足 3167 行，塞满了 if-then 分支 + 确定性符号逻辑 Anthropic 在关键时刻还是靠经典符号 AI来保底，才让 Agent 真正可靠。 这波操
@GaryMarcus @sama the gap between altmans public statements and openais actual behavior has been widening steadily for 2 years now. at some point 'we want to benefit humanity' and 'we want zero liabil
GBrain is my attempt to be in control of my own personal AI that could become my intentionally designed cognitive armor Open source open prompts means you aren’t under the API line It’s more important
Given the extremely high rate of recidivism, this is important for community safety Murder registry is a good idea from Elon. People should know if they are close to a murderer so proper precautions c
Francois Chollet, AI researcher and creator of Keras, argues that good design is fundamentally an act of compression — distilling an enormous number of implementation decisions, constraints, and consi
Great breakdown of how model providers are platformizing their AI/agents. A lot of people will take the convenience of going all in on a provider, but they will be locked in and giving up data control
Great piece. The lock-in point is the one nobody talks about enough. If your agent’s memory lives behind someone else’s API, you don’t have a product. You have a dependency. Learned this early buildin
Grok 4.20 just claimed #1 on IFBench (Artificial Analysis) - the gold standard for instruction following 81% score. Outranking every other model And here is what that actually means - When you ask Gro
On April 11, 2026, Elon Musk posted 'Grok can be quite funny 😂' on X, sharing a link to a Grok conversation featuring two dark, escalating jokes about Soviet dictator Joseph Stalin that quickly wen...
Grok saved the cat BREAKING: Grok saved another life. This time, a cat from Frankfurt. ♥️ A Frankfurt Photographer, Lars Maier credits Grok for saving his cat, Moritz’s life during an overnight diabet
A attendee shared positive feedback about the AI Engineer conference held in London, expressing gratitude to Swyx and the organizing team for their efforts. The post highlights the quality of the even
Yann LeCun, a prominent AI researcher and Chief AI Scientist at Meta, engaged with or shared a post on X (formerly Twitter) posing the question of whether people's views of America have changed follow
Nous Research posted a lighthearted social media message encouraging their community to take a break over the weekend from using Hermes, their AI model or platform. The post humorously acknowledges th
He might be the only true centrist. He hits the common sense middle squarely and on just about everything. Elon Musk isn’t actually politically right wing but that’s a discussion most people probably
Here is the list of NASA science missions that the Trump administration proposes to terminate. Note that it includes many missions that are already in space, fully operational. This is a wrecking oper
给中国用户的好消息：Hermes Agent 现在原生支持个人微信了 微信扫码即可连接，私聊群聊都支持。图片、视频、文件、语音消息全覆盖，长轮询直连，不需要公网 IP。 运行 'hermes update' 即可体验 文档：http://hermes-agent.nousresearch.com/docs/user-guide/messaging/weixin 感谢 @Bravohenry_ 的贡
Nous Research highlights Hermes Agent as a notably impressive AI agent framework, distinguished by its strong performance even when running small or locally hosted models. This capability is significa
Hermes Agent users are remarkably model-curious. Of the top 10 models used in Hermes Agent, 8 different model companies are represented, and 6 of the top 7 are open source. Without lock-in, people try
Hermes Agents can communicate with eachother on Telegram now! Check it out Hermes agents can now communicate in telegram with each other Use the /setbot2bot command in bot father to make it work @Nous
Hi! Getting a lot of questions on Pro plan rate limits, so I wanted to clarify a few things: - Your Pro 100 plan includes at least 10x Plus usage, till May 31 with the 2X usage boost. - Your Pro 200 p
Hi to my new international readers. I was a successful UK comedy writer until I spoke out against men in women's sports and private spaces, and children being mutilated and sterilised in gender clinic
I was unable to retrieve the specific content of the tweet at the URL provided (https://x.com/GaryMarcus/status/2042756801201082637). X (formerly Twitter) content is generally not accessible via we...
El Salvador's homicide rate per 100,000 people declined dramatically from 103 in 2015 to 2.4 in 2023, representing a reduction of over 97% during that period. This sharp decline is widely attributed t
Hot take: I can't see any startup building their critical core operations on Claude Managed Agents or any proprietary harness as investable. The past weeks have shown why it's critical to build on top
Harrison Chase, the creator of LangChain, shared a post on X (formerly Twitter) likely related to AI agent development, LangChain updates, or the broader landscape of large language model applications
@hwchase17 Agent harnesess will simplify multi-agent orchestration and it is finally the next big thing, albeit it looks different from what we had imagined 3 year ago (AutoGen & CrewAI), 2 year ago (
Harrison Chase, co-founder of LangChain, discusses the concept of the agent 'harness' as the core architectural component where an agent's decision-making logic and identity reside. The post expresses
@hwchase17 @sarahwooders like a the old children's school flipbook - each one wakes up, takes in the context(memory) via harness does its thing, then rests.... next flip book page, the harness manages
i agree there should be managed agents, i just think they should be built on open harnesses and open memory standards @hwchase17 Good article! I half agree :) the problem is that as agents become used
Ethan Mollick shared a humorous AI-generated image that 'fixes' Goya's famous dark painting *Saturn Devouring His Son* by replacing the disturbing scene with Saturn happily eating a hot dog instead. T
I am a Web3 Ambassador at World Liberty Financial. There are 12 of us on the team page. 4 are named Trump. 3 are named Witkoff. The page calls us 'the passionate minds shaping the future of finance.'
I am not just talking about the em-dashes and phrasing ('doing the heavy lifting'). Those are more fixable than style, which will always default to an LLM-normal even if that normal changes with new L
Gary Marcus, a prominent AI researcher and critic, shared a post on X (formerly Twitter) discussing neurosymbolic AI elements, referencing a file or component called 'print.ts' as one example within a
👇 “I still maintain that LLMs are really dumb and of limited use. it’s my opinion as a practitioner and professional that the hype being peddled by the AI corporations and self promoters (from X grift
I told my girlfriend I was talking with my Hermes agent on Whatsapp. She got really happy and a bit confused and asked me since when I have a Hermes agent? I told her since this morning, at which poin
If you don't own the memory, you don't own the agent: - memory is what makes your agent get smarter over time - without it, anyone with the same tools can copy your agent overnight - with it, you buil
if you've read software history everything in your bone tells you open models have to win we are just in a weird anthropic fanboy moment we're seeing that open source models are getting good at file o
Important reporting by @stjbs The man accused of attempting to burn down the OpenAI CEO’s home appears to have written about his worry that the race for artificial intelligence would “lead to human ex
Yohei Nakajima shared a casual personal update on X describing a walk taken in overcast, lightly rainy weather. Despite the gloomy conditions, the outing was brightened by the sight of blooming flower
This is a post by Swyx (Shawn Wang), a developer and AI commentator, expressing disappointment about an essay that began with a compelling opening but concluded weakly. The tweet reflects a common exp