Knowledge catalogue
Parse any PDF into agent-ready context. Fully local, free desktop app. No model / internet connection required! Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent,
Pinecone has introduced Nexus, a knowledge engine built specifically for AI agents. Instead of repeatedly searching documents with traditional RAG, Nexus compiles knowledge once from sources like data
.@satyanadella's Reverse Information Paradox is real. What @satyanadella's calling for already exists: open models. Over 9M+ developers have used @ollama to access open models and keep their competiti
so on-brand >be openai >release gpt 5.6 sol >max thinking budgets, full psycho >benchmark results take few days to roll in >“best model ever” >reviews locked in >4 days later >silently nerf it >nobody
Standard RL benchmarks are episodic and stationary, so they don't capture the the characteristics of real-world deployment. Morpheus is a new benchmark for continual learning that provides persistent
There is a massive opportunity for any startup to build specialized, domain-specific workflows that are at the Pareto frontier in accuracy, cost, and latency. It is clear that not every task requires
this is huge: best news I've heard all day..nice work, Hugging Face team. Big unlock for open-source AI inference: Hugging Face Transformers models can now run in vLLM at native speed, often matching
Today we present Morpheus, a persistent enterprise simulation platform designed to make Continual Learning a reality. Morpheus is the world’s first real world Reinforcement Learning environment. Every
We just shipped a full revamp of the RunAnywhere apps. iOS and Android, live now. One assistant, fully on-device, works offline: - new UI, opens straight into chat - device-aware model recommendations
We trained and released DSpark speculators for Kimi-K2.6 and Kimi-K2.7-Code on @huggingface, with native serving support in @vllm_project. Across six benchmarks in our batch-size-1 evaluation: Kimi-K2
We’re the only major open-source agentic sandbox platform and the only widely used sandbox platform licensed under Apache 2.0. Like LLMs, sandboxes are a critical part of AI infrastructure. Any smart
We've open sourced Ideogram V4 instant and fast, find them here! Fast: https://huggingface.co/fal/ideogram-v4-fast Instant: https://huggingface.co/fal/ideogram-v4-instant Try them out for free on fal
we've open-sourced our in-house distilled models again. much faster, with no quality loss. Try them free at @fal We've open sourced Ideogram V4 instant and fast, find them here! Fast: https://huggingf
Another big reason to use combination of frontier models. Chain-of-thought monitoring is treated as a reliable safety layer for agents. This DeepMind-affiliated study shows the layer can be argued out
Hit my Claude and Copilot limits three times in each of the last three days Of course a friendly prompt popped up suggesting I either buy more credits or upgrade my plan Simply switched to Gemini for
I don't think Anthropic realizes how disruptive these changes are to users. I appreciate the extension, but please stop playing games. Either keep it under the subscriptions or put it under the API al
playing with local AI models and doing some research and came across a fun extrapolation: 'consumer grade graphics cards will be running Fable-equivalent models by 2029' the argument: 1) been said tha
a prompt i like to use when having agents review other agent generated PRs tell the agent your coworker who you don't trust/think is that smart put up the PR, and it'll tend to find improvements/optim
Absolutely fascinating work by @SakanaAILabs reproducing @kenneth0stanley Picbreeder in a non-interactive, VLM-agentic way. I've had years to reflect on Kenneth Stanley's ideas as originally communica
As usual, legacy media is misrepresenting the situation. I just asked Tesla & SpaceX to try out Grok 4.5 to see if it solves their task, not use it no matter what! They should continue to use other AI
BAMF is a term Elon Musk referenced on X (formerly Twitter), likely relating to a project, concept, or feature associated with his work at Tesla, SpaceX, or another venture. Without access to the spec
ChatGPT still has study mode, but rather than /study you now have to type @ study It makes the AI act more like a tutor than a helpful assistant, and some work suggests it is better if you are trying
Community Profiles are live. Proof of work for vibe coders. Your profile, your flex: get an activity graph of your agent usage and checkpoints, plus a Replit Power Ranking for Pro users. Log in, claim
Elon Musk shared video content showcasing SpaceX's Starship Super Heavy rocket system on X (formerly Twitter). The post likely features footage of the integrated Starship vehicle stack or Super Heavy
For almost two decades people like @YLeCun and @geoffreyhinton dumped on me for saying we need symbols in addition to deep learning. But that’s exactly what loop engineering is: adding symbols to deep
Elon Musk announced the availability of a free trial for the Grok 4.5 model through the Grok Build CLI, allowing developers to access and test the latest version of xAI's Grok language model. This ann
Full Friday Showcase replay: → Community Profile Showcase w/ @NIftek, @noni_shehnoor, Victoria Cavazos & @marcelhaasIO → Announcing all 25 Proof of Work winners ($100 credits each) → This Week in Repl
OpenAI announced the global rollout of GPT-Live to all ChatGPT users, enabling real-time interaction capabilities. As part of the announcement, the company temporarily doubled voice usage limits for a
Grok 4.5 is an AI language model developed by xAI, featuring improvements in reasoning, coding, and multimodal capabilities compared to earlier versions. The model demonstrates enhanced performance ac
Grok Imagine is an AI image generation tool developed by xAI that creates visual artwork. The announcement highlights the capability of the system to produce high-quality, aesthetically pleasing image
Grok places second after Fable on real-world software engineering Grok 4.5 from @SpaceXAI places #2 on the APEX-SWE leaderboard at 51.2% Pass@1 (±6.0), behind Fable 5 (65.5% ±6.2) on our benchmark for
I gave Fable the code: 'take this game and do something incredible with it to make it something very different. Be creative' It created DEEP TIME: create a city, watch it be abandoned and forgotten, a
I really want to get artisanal with my model selection: Luna xHigh for recipes Sol Medium for sonnets Terra High for bad puns Luna xLow for limericks Sol Utra for true prophecies Sol Low for finding o
If solar power in space is harnessed for useful work at scale, the value of that will far exceed the Earth economy, because all of Earth civilization uses much less than a trillionth of our Sun’s powe
More interesting is the difference between 'Chat' and 'Work' modes in the ChatGPT mobile app It looks like Work mode can run code that talks to the Internet! I just tried having both modes use yt-dlp
nice! a prompt i like to use when having agents review other agent generated PRs tell the agent your coworker who you don't trust/think is that smart put up the PR, and it'll tend to find improvements
Nuanced Grok 4.5 solved it --- Answer: 더바른정육식당 (The Barun Jeongyuk Sikdang) 📍 서울 강남구 강남대로 482, 신논현/논현 · IG @barun_jo 1. Plate first. The tweet photo is a classic Korean 고깃집 사인 벽 — light vertical wood,
Ramp for Agents. Replit Agent can now incorporate your company, apply for Ramp, and get your business ready to spend, pay bills, and manage money. Every company used to start with paperwork. The next
sign up for membership and u can see the NML artwork! we are actively seeking more art and also donations to the Museum of Sponsor Swag https://x.com/mada299/status/2075718882376159261?s=20 AIE art is
Thats good for the dumb reason that I am burning tokens having Sol in Codex playing Slay the Spire 2’s daily challenge (so randomized rules, today it is Ascension 3 Defect with hoarder) to see if it c
The Anglo-Scottish Enlightenment – the real antidote to Rousseau and Voltaire The French Enlightenment and the Anglo-Scottish Enlightenment happened simultaneously, in the same century, reading the sa
Gary Marcus argues that the engineering and infrastructure surrounding large language models are more critical to their practical success than the models themselves. This reflects his broader perspect
They sure put a lot of effort into this crime Apple just sued OpenAI, and the wildest part is how they got caught: one candidate screenshotted confidential Apple files on his Apple work laptop hours b
This Week in Replit Three big drops this week: 1) Community Profiles launched, proof of work for vibe coders 2) A free custom domain, on us, through July 17 3) Ramp for Agents, incorporate and run you
To be clear, NotebookLM has its own issues, and is built for a specific use case (research and analysis of sources) but it is an example of how a UX might actually operate that treats knowledge work s
VLMは人間のような創造性を持てるか？ ケネス・スタンレー教授らの『目標という幻想（Why Greatness Cannot Be Planned）』は、明確な目標を設定することが、かえって真に偉大な発見を遠ざけてしまうという逆説を論じた書籍です。その議論の中核にあったのが「PicBreeder」の実験でした。 PicBreeder では、ユーザーが「面白い」と感じた画像を選び、それを少しずつ進化
This post likely reflects on the distinct emotional or relational significance of being called 'daddy' by a bisexual male partner, suggesting that the experience carries different meaning or impact co
Together AI's 'Why type when you can call?' post likely promotes their voice calling or audio interface capabilities as an alternative to text-based interactions with their AI models. The content prob
This appears to be a Wordle game result post from Anthropic's X (Twitter) account, showing that the word was solved in 4 attempts on puzzle #1,847 using the standard color-coded feedback system (gray
1/ I watched LangChain’s webinar on LLM wikis and agent memory and wrote up a working paper from my own small agent-fleet experiments: Soft-Cache: A Human-Supervisable Coherence Protocol for Persisten
Tesla has deployed 10 GWh of industrial energy storage products across Australia, a capacity equivalent to powering approximately 160,000 Tesla Model Y vehicles. This milestone reflects the growing ad
Clem Delangue suggests that Google DeepMind could significantly improve its public reputation by open-sourcing the Gemini 3.5 Pro model. The post implies that releasing this advanced AI model as open
agent memory has always been reactive. OpenWiki makes it proactive. connect to sources, tell it what you care about, and your agent hits the ground running . what we're building is really exciting! tr
Ahead of a dinner with a US senator, AI researcher Nate Soares (@So8res) was told: 'Don't give them any of the crazy crap. You know, play it cool.' His friends opened with the concern that someone cou
Nous Research is promoting Hermes Desktop, a tool designed for users already utilizing cloud services, available at hermes-agent.nousresearch.com. The product likely offers desktop-based functionality
This post addresses a question comparing 'Ultra' and 'Pro' product tiers or model versions, likely clarifying whether they represent meaningfully different offerings or are simply alternative names fo
And then what is the point of Work? Just a dumbed-down version of Codex that secretly does coding but hides it? (I can understand, maybe, if the release was a 1st step towards something but there is n
Another big langchain week 🚀langchain launches this week: all about open source models and memory! First: open source models. We partnered with @NVIDIAAI to launch a NemoClaw DeepAgents blueprint. Thi
Anyone can visit the Starship factory and launch site in Texas, as it is right next to on the public highway. It is incredibly inspiring to see! SpaceX has released the next episode of its new docuser
Anyone know if ChatGPT Codex (in the new ChatGPT desktop app) is a strict superset of ChatGPT Work? Liked if you're a software engineer who isn't intimidated by Git features is there any reason you'd