Jasper Ai
βlike the Jasper AIS of the world and and others who were building really interesting thingsβ
What the smart people are recommending. 8874 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
βlike the Jasper AIS of the world and and others who were building really interesting thingsβ
βAnd I call this a JEPA, so that means joint embedding predictive architecture because there's joint embedding and there is this predictor that predicts the representation of the good guy from the bad β¦β
βUses [Next.js 14](https://nextjs.org/) with [App Router](https://nextjs.org/docs/app/building-your-application/routing) and [RSC](https://nextjs.org/docs/app/building-your-application/rendering/serverβ¦β
βIf you haven't tried, uh, give the new Gemini Flash Latest and Gemini Flashlight latest models, uh, a shot. They're pretty good.β
βIf you think it can't do it you probably haven't tried enough or you probably haven't used the paid versions The gp4s the clae 3s the Google because all of them basically solve every problem visually β¦β
βI worked um since I was about 13 or 14 years old building my own tools and learning from uh namely Linux and and Linux tovs and he taught the world um what it means to share something of of real note β¦β
βI'd be excited to first of all I just want to take a moment to thank you for writing these excellent tutorials on Julia that we published on the Freo Camp Community publicationβ
βI would say go out and fail on something, iterate, go try to have an objective just like he's saying, try to use a coding agent to do it. Try to use even something as simple as like download a Claude-β¦β
βand kind of did a survey of the of what's out there and uh you know we looked at dask we looked at Ry we looked at probably like you know half dozen other projects and Ry was was uh by far the the winβ¦β
βyou can expect integrations like uh browser base and browser use. They're building browser infrastructure for agents.β
βHow Trellix cut log parsing time from days to minutes with LangGraph Studio and LangSmithβ
βyou are \uh have said on other programs and on your YouTube channel which I suggest everybody go search for and follow right now because you're speaking directly to the people on X and on your YouTubeβ¦β
βI created an organization called IP which which is Iran prosperity project but it first focus is the first 100 days.β
βSo like the time trajectory is actually interesting. So, so we want la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la la launched Lang cβ¦β
βyou can find us on the internet remotion.com so r e m o t i o n.com and you can also email me at alexanderormation.com would love to hear from you and we're we're always looking for people to build wiβ¦β
βWith AI, it's possible, and with Juro, it's a reality. Juro is a complete AI solution for business contracting from draft to signature and beyond.β
βMCP is a new standard that allows agents to talk to existing SAS applications or any kind of application and it's really going to enable this agentic future that I think is the next big wave in AI.β
βit basically lets me like write code in English and I shipped a whole production app in a couple hours I'm not trying to sh the product I'm just literally this is exactly what it does it's really sickβ
βdidn't you build like a websockets Library prior to forell socket.io I became obsessed with real-time communication I became obsessed with democratizing how this greatest applications workedβ
βI worked on image compression a system called djvu which I heard was pretty popular in Poland actually in Eastern Europe more generallyβ
βthen they will use claude 4.6 opus to orchestrate things.β
βShe does play bass guitar riffs and brings those into Abton Live uh to do to add some humanness.β
βNotebook LM is free and you can check out this guide also for free... one of the most underrated AI tools by Googleβ
βI'm kind of waiting for the Google version of Open Claw because I don't really want to share all my documents with some new service.β
βWe recommend running these notebooks on Colab, which provides a hosted runtime with all the dependencies you will need.β
βSo there's also L2s, Aztec and IntMax I think are both very impressive.β
βGPT-5.2-Codex is now out in the API! `codex -m gpt-5.2.codex`β
βHere's an example of the new Box Agent filling out an RFP response from an existing knowledge base.β
βUm, the second entry was a um a new programming language. Uh so hands up here who's into programming or software development. Okay, see a bunch of hands go up. Uh anyone into lisp programming? β
βTo install vLLM, follow the directions hereβ
βWe launched it at dev day. It's actually been a huge hit. I've been very very surprised.β
βOpen AI and Open AI of course has been at the leading front of the development of generative AI tools and uh most notably Chatg GPT and Dolly and uh many others and and so it's just a thrill to have hβ¦β
βCurrently, two official plugins are available: - [@vitejs/plugin-react](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react/README.md) uses [Babel](https://babeljs.io/) for Faβ¦β
βRequires Ruby β₯ 3.1 and [Nix](https://nixos.org/download/).β
βBuilt with [Three.js](https://threejs.org/).β
βnearly 400,000 people subscribe to his one useful thing newsletter.β
βCLI tool for creating charts from CSV, TSV, JSON, JSONL, or SQLite data using matplotlib. Designed to work well with Showboat.β
βone of the most remarkable things about what XAI did is they stood up the biggest data center at the time in you know like a quarter of the time that anyone else had done the same thingβ
βWe found that GPT-5.2 models are much better at extended autonomous work: following instructions, keeping focus, avoiding drift, and implementing things precisely and completely.β
βIntroducing Showboat and Rodney, so agents can demo what theyβve builtβ
βBy connecting Jira, Confluence, Loom, and Rovo, teams can easily align work to real business goals, plan and track progress together, remove knowledge silos, and access the real magic.β
βI built an AI agent that monitors it for me: https://alignednews.com/aiβ
β# Recraft V4: image generation with design tasteβ
βLearn more here: https://mistral.ai/news/forgeβ
βAgent 4 fixes this.β
βbuilding a working game in excel, with a built-in game AI powered by complex formulas:β
βhow can I have not just a single session of clot code or codeex or some of these agent harnesses.β
βUses [pnpm](https://pnpm.io/installation) for package managementβ
βMaybe even more dramatic example of this is deep wiki where it's not just the raw content of these files. uh this is from Devon but also like they have Devon basically do analysis of the GitHub repoβ
βThis repository showcases example UI components to be used with the [Apps SDK](https://developers.openai.com/apps-sdk), as well as example MCP servers that expose a collection of components as tools. β¦β
βA [Pen](https://codepen.io/jjob1391/pen/xeoWYK) by [Jeremy](https://codepen.io/jjob1391) on [CodePen](https://codepen.io).β
βAI natives can now build with Wan 2.7 on Together AIβ
βWhen Opus 4.5 came out, it was a one-way door to a new way of engineering.β
βUse Codex from inside Claude Code for code reviews or to delegate tasks to Codex.β
ββ’ Embeddings: A local @nomic_ai model via @huggingface transformers.jsβ
ββ’ Vector storage: A local @qdrant_engine edge shard (custom-built in Rust and compiled as a native add-on)β
βyou do you do H hand your video over to like Luma Ai and turn it into a Nerf or a gossan Splat no no no I mean I do I'll do it inum decentralized you know me right I'm more of a decentralized guy I doβ¦β
βHe's the creator of Pulsia. It's an agentic system. It's not OpenClaw. It was built while Peter was off building OpenClaw. It's a separate agentic system, Jason, that helps businesses run their operatβ¦β
β# Aurora _Blog post by Together AI_ https://www.together.ai/blog/auroraβ
βπ Flux: conversational STT with 250ms end-of-turn detection using conversational contextβ
βWe're doubling Composer 2 usage through the end of this weekend. We recommend trying it out in our new interface, available in Cursor 3.β
βYou have a person that was a staunch advocate that I need to use Emacs. You will never see him using an IDE. And he skipped autocomplete. He skipped Chat, and now he is directly using Anti-Gravity to β¦β
βActually, we shipped a model called Flash, Gemini 3 Flash. And the coding capability is actually on par with Pro.β
βPerhaps the craziest thing that was introduced on the Keras community call today: Keras Kinetic, a new library that lets you run jobs on cloud TPU/GPU via a simple decorator -- like Modal but with TPUβ¦β
βInstall this tool using `pip`: ```bash pip install scan-for-secretsβ
βI don't even know anymore. You know, I I retained on chrisbroen.com, but it's just sitting there. It's just a shell.β
βNew @X API + @Replit is lots of fun.β
βCodex app server makes it easy to build your own agentic apps:β
βa bit like Wikipedia right you you can't have just Wikipedia in one language that has to cover all languages all cultures and everythingβ
βI noticed with Vzero um is you took a slightly different approach which I really like and I I thought it was cool was that you empower developers that are specialized in one area which is like really β¦β
βI always use the example of how we are building an externalized technology today how Google uh created Alpha Zero the chess engine and and Magnus Carlson in our regionβ
βKPMG's KPMG Audit Chat represents the most advanced integration of AI into professional audit processes, with the dual cloud strategy (Microsoft + Google) providing comprehensive AI capabilities acrosβ¦β
βstring book as like an alternatives to Jupiter notebooksβ
βChatPwC: Private generative AI tool built with OpenAI's technology, fine-tuned with internal data [5]β
βAgentic coding assistants shine when you want to interact with a mix of local tools installed on your computer as well as cloud services like maybe Postman, [music] Figma, or Google Docs.β
βyou have to evaluate these robots inside a virtual gym that represents the physical world... That's a second computer. We call that omniverse.β
βRequirements: Claude Code, [Git](https://git-scm.com/)β
βI remember back in I think it was marchish of 2023 uh there were a few of these autonomous agents that really captured everyone's imaginations like baby AI autog GPT a few of theseβ
βif you look at our if you look at our pipeline in Clara from cryo electron microscopy to x-ray crystallography to um uh uh uh you know Gene sequencing to uh amino acid to uh structure prediction uh alβ¦β
βwe saw kind of like the Clara customer support bot um kind of like come online and get a lot of hypeβ
βUnix versus Windowsβ
βBy the way, if you guys want to see what I've built with AI recently, go to cody.hat This is wild. You can talk to me for free and get all of my insights on questions you have surrounding buying businβ¦β
βSkills in LangSmith Fleetβ
βi'd point out some of the work that we've done at linkchain with elastic for example they have kind of like an elastic assistant an elastic agent in productionβ
βso think Harvey AI for those specialized legal modelsβ
βOne of the core parts of that is tracing. Why are traces so popular? Because they tell you exactly what goes on inside your agent at every step.β
βSymphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.β
βyou see like Kimi an open source model came out from this lab called Moonshot and um it's almost as good as Cloud for Opus and it's open source. So we're we're we're constantly going to benefit from aβ¦β
βSeedance 2.0 (Fast): https://replicate.com/bytedance/seedance-2.0-fastβ
βUh and I think they're also compromising light LLM and exios and all these things.β
βI mean I think for example Lama CPP which allows things to βwhich allow people to run things on Mac was amazingβit's just a great Community to feed great model tube soβ
βand then after that came BERT that also came out of Google which was this idea of using self-supervised learning where I take a sequence of words corrupt it remove some of the words and then train thiβ¦β
βWe propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding.β
βIf you read about us, this is called Lattis in a lot of our like published literature. It's fundamental tech that allows you to consume data, make sense of it, and then manipulate robots basically. Liβ¦β
βUses [Next.js 14](https://nextjs.org/) with [App Router](https://nextjs.org/docs/app/building-your-application/routing) and [RSC](https://nextjs.org/docs/app/building-your-application/rendering/serverβ¦β
βUsed [v0](https://v0.dev) to generate all initial UIs with [Tailwind](https://tailwindcss.com/), [Shadcn UI](https://ui.shadcn.com/) and [Radix UI](https://www.radix-ui.com/)β
βYou can either go to dribble mob or any website to get some UI reference and just copy the image over and ask cursor or super design to extract CSS stylesheet from the UI mock.β
βThere are more userfriendly version like yo-yo where it receive a snapshot and you can add some additional instructions to remember what the changes are.β
βAnd pro tip, if you drop this into Claude or Chat GBT, you can actually ask it based on what it knows about you to actually develop a plan that you can use.β
βfor me I remember getting access to Twilio, you know, back in the day. So like 2012 or 2013 getting access to Twilio and I had I I was just overwhelmed with creativity because I was like wow now I havβ¦β