Knowledge catalogue
Sam Altman reflects on the nostalgic appeal and unique characteristics of the early internet era, likely discussing the cultural, technical, or social aspects that made that period distinctive compare
Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 198B sparse MoE VLM designed by @StepFun_ai for inference from the start. 196B language backbone with a 1.8B v
MARC ANDREESSEN: 'We had meetings with the Biden admin where they told us to not even start AI companies because there's no way they'll let them succeed.' JOE ROGAN: 'What do you do after a meeting li
LM Studio has released a mobile app that enables users to run and access local language models on their smartphones. The app extends LM Studio's desktop functionality, allowing users to deploy and int
Devin is an AI software engineer product that likely includes a performance guarantee and specific eligibility requirements for users, with details available on Cognition AI's official guarantee page.
Most AI pipelines are only as good as the data we provide them with, and that usually means PDFs or other unstructured documents. Contracts, invoices, reports... All have special layout, language, and
Nemotron 3 Ultra is an advanced language model released by NVIDIA, representing an improvement over previous versions in the Nemotron series with enhanced capabilities for various NLP tasks. The annou
Nemotron 3 Ultra (550B-A55B) is here - our strongest open-weight model and full training recipe to date. Heavy emphasis on real-world inference efficiency for long-context agentic workloads. Everythin
Nemotron 3.5 ASR is built for streaming multilingual speech recognition and voice agents. One 0.6B checkpoint. 40 language-locales. Sub-100ms latency. Cache-aware FastConformer carries context forward
New course on serving LLMs efficiently -- how do you serve models to many concurrent users at low latency and reasonable cost? This short course is built with @RedHat and taught by @cedricclyburn. Eff
New in the LangSmith Sandboxes GA Release: Sandbox CLI ✅Build snapshots from Dockerfiles ✅Manage sandboxes ✅Open interactive consoles ✅Tunnel raw TCP ✅Use standard tools (ssh, scp, rsync, sftp) agains
NEW: NVIDIA ships 550B MoE open model for long-running agents. Very exciting times to see more open models to support local long-running coding agents. Today we're shipping Nemotron 3 Ultra. A 550B Mo
🚨 New York Democrats just voted to erase 'Mother' and 'Father”. Governor Kathy Hochul will be replacing 'mother' with 'gestating parent' and 'father' with 'non-gestating parent.' This isn't inclusion,
nice post from @Harvey and @LangChain Labs, worth a read. improve agent feedback loop without setting $$ on fire Can we design legal agent verifiers that are up to 1,000x cheaper? Verifiers are LLM ju
@nvidia @nebiustf More info on the new Nemotron 3 Ultra: https://x.com/NVIDIAAI/status/2062521325076299981?s=20 Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built
This is a setup guide for running Nemotron-3 Ultra, NVIDIA's open-source language model, through Nous Research's platform. The guide directs users to sign up for the Nous Portal and access documentati
NVIDIA Nemotron 3 Ultra is on Fireworks, day zero. Nemotron Ultra is an open model for frontier reasoning and orchestration in long-running autonomous agents. Think use cases like coding agents, deep
NVIDIA’s Nemotron 3 Ultra is available on Ollama’s cloud! Try it 👇 Claude Code: ollama launch claude --model nemotron-3-ultra:cloud Hermes Agent: ollama launch hermes --model nemotron-3-ultra:cloud Op
Offering a “damn, I’m truly impressed” award, for the first person or team to build a domain-general AI system that can play @baldursgate3, start to finish. Will make the prize especially sweet if you
Offering @kevinroose $100,000 bet that no domain-general AI system can do this before his book comes out. (mimicking walkthroughs doesn’t count.) Offering a “damn, I’m truly impressed” award, for the
This post likely discusses cost optimization strategies for managing API token usage and expenses, particularly relevant to users of language models or LLM-based services. The author emphasizes the pr
ollama run gemma4:12b Gemma 4 12B is updated on Ollama, and available across all platforms! Try it on: Claude Code ollama launch claude --model gemma4:12b Hermes Agent ollama launch hermes --model gem
On the latest episode of Max Agency, @hwchase17 sat down with @nlarusstone, Head of AI at @benchling for a conversation on building agents for scientific work. ⏯️ YouTube: https://www.youtube.com/watc
On TV Tokyo’s WBS (@wbs_tvtokyo) tonight I’ll be discussing Sakana AI’s upcoming 1T parameter model project, supported by METI’s GENIAC initiative. We are scaling up to build Japan’s first 1T paramete
OpenAI is in deep, deep trouble They are low on capital relative to the massive cash they are burning and there is only so much capital in the world. No rational person would sell their Bitcoin or Nvi
Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we thought
Our team is at CVPR 2026 if you want to come say hi :) We're presenting ParseBench at CVPR 2026! ParseBench is the most comprehensive document understanding benchmark for VLMs. ✅ It contains 2k pages
Outstanding paper on long-horizon agents. (bookmark it) Similar to humans, how do you make agents persist on a difficult task, and how is that useful? And which models today work well on this? This ne
Proud to announce that Cohere has been awarded first place in NATO’s Agentic AI for Cognitive Warfare Innovation Challenge. Congratulations to our fellow finalists: OpenMinds, which secured second pla
This post likely discusses concerns about AI systems that merely imitate or reproduce existing walkthroughs and instructional content rather than demonstrating genuine understanding or original proble
Pulled the trigger today and switched 100% of Lindy traffic to DeepSeek v4, churning from Anthropic models. Saves us millions of $ and we're actually seeing an *increase* in performance on many core u
Reading this again, I thought you meant for making like a full length movie or a 30 min episode. For this 40 sec trailer it was actually just a few days of iterating and playing with the edit and/find
reiterating: 'We're using the more expensive models to explore. Once we scale some of these experiences, we'll look to bring in more efficient models that are more efficient on a token basis or are op
Remember when Dario called pausing AI 'most extreme'? '...we should just pause ... that extreme position doesn't make much sense to me either.' Anthropic now: 'We believe it would be good for the worl
Safety by narrow control has shown to fail many times. Need more transparency on the absolute frontier, and openness close behind. I found another API that offers claude-oceanus-v1-p the pricing and t
Sam Altman: AI spend intensity has become a major customer concern almost overnight 'Probably the second biggest theme is just around cost. People are really saying, that's kind of become a meme now,
Sat down with @shaunmmaguire recently to talk through where Neuralink is and where it's going. A few things that came up: - over 20 participants now, more than 45,000 hours of BCI use — people control
See also: https://x.com/emollick/status/1799046218917822682?s=20 Alignment, of a sort: this paper conducts what they call a “moral Turing Test,” asking people to compare GPT-4o to humans on ethical qu
Shared my first trace from @NanoClaw_AI to @huggingface yesterday. Very cool! By default, all agents should store their traces on HF (in private) so that you can keep a history of them, analyze them,.
shit is getting real Sam Altman, Dario Amodei, Demis Hassabis and many others have signed a letter urging Congress to increase security on orders of synthetic nucleic acids - and the equipment needed
Skill issue: Lessons from skilling up coding agents Getting agents to actually use Langfuse was a 'skill issue' — literally. Marc Klingen from Clickhouse on teaching coding agents to use new tools, an
Sometimes you need to start over. But that decision is hard. @llama_index had to make that call: they built one of the most popular AI frameworks in the world, but saw the agent harness and frontier l
Southern Poverty Law Center is a criminal organization 🚨READ IT The Justice Department just secured a superseding indictment against the Southern Poverty Law Center, and it reveals some new bombshells
SpaceX is a private aerospace company founded by Elon Musk that designs and manufactures rockets and spacecraft for commercial and government missions, including cargo delivery to the International Sp
SpaceX has not conducted a public IPO as of my last knowledge update (April 2024), and Elon Musk has historically stated the company remains private to focus on long-term goals like Mars colonization.
SpaceX’s literally destroyed the cost to orbit so much even you can afford the ticket to ride on it in the future - For decades, launch cost to low Earth orbit was roughly 18,500 per kg - Falcon 9 bro
Starlink V3 satellites have >10X bandwidth of V2 and there’ll be >10X launched, which means >100X more bandwidth. Also, altitude will be 350km vs 550km, so min latency can be cut in half. Light travel
Starmer is right about this; would be ironic if the net of it was to keep Starmer in power for longer. British Prime Minister Keir Starmer has accused Elon Musk of 'whipping up division' and interferi
I cannot provide an accurate summary as the URL appears invalid and the title is fragmented/unclear. Based on the partial title, this likely contains statements from UK Labour leader Keir Starmer rega
That's a badass title, and it's true! Every day, it gets harder and harder to create tests that AI models can't beat. Reality is humanity's real last exam. Andon Labs' Real-World AI Evals: Claude call
The Canadian AI strategy unveiled today advocates for the development of technology that is safe, ethical, trustworthy, and that benefits society as a whole—these are exactly the principles that need
The capabilities of Claude Code and Codex have expanded a lot in recent months, they added many ways to approach work (subagents, skills, goal, workflows, plugins, etc). Given the AI labs can use thei
The new memory system will keep track of important details automatically. If you prefer the legacy saved memories experience, you can switch back in settings. The new memory system is rolling out to P
There are lots of issues with GenAI implementations but surveys seem to suggest broad positive ROI. Data & stories about AI failures are real and useful but need to be clearer about what they are meas
There is literally nothing California could do to make their elections less secure. Mail in ballots and No ID. Weeks of counting with no real chain of custody. The fraud is staggering. It’s an insult
THIS. I fully agree with @andrewyang, especially since GenAi leverages IP from a huge range of humans that were not adequately compensated. We should tax AI. https://www.cnbc.com/video/2026/06/04/andr
This is the enterprise-agent security frame I like: treat agents like untrusted developers. They need the ability to call an API, not possession of the credential. Control plane outside runtime. Fail
The post announces that the author will share insights about their use of dynamic workflows and explain their reasoning behind building a custom implementation. This likely covers practical applicatio
This post likely discusses Jeremy Howard's commentary on software engineering efficiency and the goal of shipping significantly reduced code volumes—possibly advocating for more concise, optimized cod
This provides some sense of scale Starlink V3 satellites Bandwidth per Satellite: • V2: 96 Gbps • V3: 1,024 Gbps Bandwidth per Launch: V2: 2,600 Gbps V3: 61,000 Gbps Deployment per Launch: • V2: 27 sa