All entries

I wish the logos and textbox-at-the-bottom interfaces for Discord and Codex did not look so alike at a glance. I have confused the two a couple of times, leading to a confused GPT-5.5 and a confused g

I wonder how many founders will pass on investors who passed on them in prior rounds I wonder how many would have three dinners & give them an allocation only to slash it to zero at the last moment. A

I work in AI, I appreciate data, but my god the public data gathering is going too far. Walked into a restaurant with half the seats open. In order to sit down and eat, you had to give them your phone

If your daughter needs tutoring in algebra, you can probably find someone cheaper than Albert Einstein. Giving every task to GPT5.5 or Opus 4.8 is overkill. Often times you can get the task done just

II-Agent is now live on the App Store. Your sovereign AI workspace for building, researching, writing, designing, and automating from one intelligent interface. Download it. Bring your own key. Build

Il faudra, un jour, faire le Nuremberg du wokisme. Mais pour la première fois dans l'histoire, il n'y aura pas de bourreau à juger. Pas d'homme à pointer du doigt. Seulement des idées. Une empathie de

Replit announced support for image generation capabilities using GPT-Image 2, video creation with Seedance, and the ability to create animated SVGs, expanding the platform's generative AI features. Th

Devin Desktop is a unified management interface from Cognition AI that enables users to coordinate multiple AI agents operating across local and cloud environments. The platform streamlines workflows

Introducing Devin Desktop: the next generation of Windsurf Manage fleets of local and cloud agents from one surface Support for any ACP-compatible agent With a full IDE for when you need to jump into

This post likely presents a humanitarian appeal contrasting named individuals (Iryna and Henry) with the reader, suggesting empathy for victims or affected people in a conflict or crisis situation. Wi

It is difficult to know how good MAI-Thinking-1 is from the scores alone (like weirdly low GPQA & Terminal Bench 2.0) But Microsoft makes it really hard to try its models upon release (a general issue

It is this or death Enough is enough - a deep line needs to be drawn in the sand. Talk is weak. Britain needs to say no more, and mean it. A Restore Britain Government, with the British people's appro

It’s over Britain had a moment of silence for George Floyd. Our politicians kneeled en masse to show their outrage at his killing. 'I can't breathe' became a slogan. George Floyd died on the other sid

This appears to be a music release or project announcement shared by Sonya Huang on X (formerly Twitter), featuring artist @itsalfredw and @Konstantine with links to the track on Apple Music, Spotify,

Je me suis longtemps passionné pour la psychologie, et une période m'obsède plus que toutes les autres. L'après-guerre. Le moment où des chercheurs se sont posé la question la plus dérangeante du sièc

@jerryjliu0 — Founder & CEO of @llama_index — on Venture with Grace, sharing why data is at the center of the agentic AI boom. AI agents are proliferating rapidly — and with them comes an explosion of

Nous Research is hosting a livestream featuring team members Karan and Yoni speaking from NVIDIA, likely discussing AI research, model development, or collaboration between Nous Research and NVIDIA. T

Perplexity AI demonstrates a hybrid approach to AI inference that combines on-device processing for sensitive data with cloud-based AI services to achieve scalability and contextual understanding. Thi

Law professors wrote questions they were asked during office hours. Gemini 2.5 & humans answered them then other law professors blindly judged the results: -Gemini had a 75% win rate vs. professors -G

Legacy medias lies both by promoting false stories and by ignoring true ones Did they show or even mention the Henry Nowak footage? Legacy Media… CNN: No MSNBC: No ABC News: No CBS News: No NBC News:

Swyx, a prominent figure in the AI community, uses paper-based tools and methods despite working in a high-tech field centered on artificial intelligence, which resonates with others who appreciate an

Gary Marcus poses a question to Yann LeCun and Jürgen Schmidhuber about whether automation of AI systems (possibly referring to AI development or reasoning processes) might be feasible, suggesting a d

Microsoft MAI models. Coming soon to Fireworks. Intelligence you control. End-to-end lineage you can prove. Fine-tune MAI reasoning models for your enterprise tasks. Your data. Your custom models. You

Microsoft Build conference featuring Satya Nadella is streaming live on build.microsoft.com and X's native broadcast platform. The stream announcement was shared by Swyx and references appearances by

This post compiles recent AI news and developments from Microsoft and NVIDIA, likely covering topics such as NVIDIA's Cosmos 3 model and Nemotron 3 framework, along with other significant updates in t

MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse attention, paged MSA decode, optimized index scoring

Gary Marcus argues that SpaceX's valuation is significantly inflated, contending that the company is not worth the trillion-dollar valuations that have been suggested. The critique appears to challeng

MOSS-TTS-v1.5 just reached #1 on Hugging Face Trending for Text-to-Speech, with 20.6K downloads. A multilingual, controllable TTS model with stable voice cloning, long-form generation, and precise pau

Move from test to production by running high-performance inference directly on Foundry. At #MSBuild, we demoed an end-to-end workflow showing how unified infrastructure improves latency, reduces cost,

NEW: Ahead of the SpaceX IPO, we tracked hundreds of promises that Musk has made over the years (FSD, Mars etc). His success rate is…not good. And it’s getting worse. Some actual data in our months lo

New in Deep Agents: Agent Rubrics! Attach a rubric to your agent invocation, and a grader evaluates and self-corrects output until it satisfies all requirements. This is helpful for long/complex tasks

new in deepagents: agent rubrics! you define a rubric, and the agent self-evaluates and iterates until it satisfies every rubric criterion. this is similar to /goal in claude code or codex, but more f

Not convinced that this kind of nationalization by fiat is at all the right way to go (and for that matter don’t expect the current breed of technology to generate trillions), but I am glad that Sande

one of the quotes i find most inspiring on a hard day: 'Whatever your hand finds to do, do it with all your might, for in the realm of the dead, where you are going, there is neither working nor plann

Open-weight models have overtaken closed models on OpenRouter. 69.1% of token volume now goes to open-weight models. 30.9% to closed. Competition is a discovery procedure — and developers are discover

People who say this kind of thing are completely lost about what I actually said about deep learning, and I would strongly encourage them to read “Deep learning is hitting a wall” (2022). What I said

OpenAI announced a sales plugin for Codex that streamlines sales preparation and improves selling strategies through AI-assisted tools. The plugin leverages Codex's code generation capabilities to hel

Pretty refreshing for foundation model training in 2026. I wonder how much of the capability gap between their model and other frontier models is because of this constraint. from: https://microsoft.ai

Prompting agents to 'do better' is unreliable 🙅 Giving them a rubric, a grader, and a correction loop is much closer to how you get your agent do what you want! Similar to /goal in Claude Code or othe

This post likely provides a brief explanation of a managed deepagents offering, describing what deepagents are, how the managed service works, and its key benefits or use cases. As a post from Harriso

RAGE How many more young British men and women are going to die? Bleeding in the street, alone and terrified. Cuffed, in a pool of their own blood. Begging for help. How many more parents are going to

Perplexity discusses hybrid agentic inference in Perplexity Computer, which likely describes a computational approach that combines processing between local machines and data centers. The concept sugg

Windsurf has announced that Windsurf is now being rebranded or integrated as Devin Desktop, representing a significant update to the product's identity or functionality. This announcement likely detai

Remind me, @Elonmusk, was GPT-5 really smarter than the smartest humans? @viktaur27 @Teslarati The rate of improvement from original GPT to GPT-3 is impressive. If this rate of improvement continues,

Replit Canvas, the platform's visual development tool, received several new updates that are detailed on the Replit website. The announcement was made via an open thread on X (formerly Twitter) to inf

RubricMiddleware is a LangChain feature that enables agents to verify task completion by delegating grading to a specialized subagent using predefined rubrics. This approach parallels the goal-verific