Superdesigndev
βI have put the link in the description below so you can try this whole workflow for free on superdesign.dev.β
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.
βI have put the link in the description below so you can try this whole workflow for free on superdesign.dev.β
βI found this project called one context that is released this week where they are utilizing this method called get context controller that is defining a specific memory framework that is extremely simβ¦β
βSG lang is an open- source inference framework that eliminates that waste by caching computation that's already been done and vusing that in future messages.β
βI vested in the company and I had the founder come on and show us why this is an open claw killer when it comes to an executive assistant. This episode is a complete breakdown of how to use the producβ¦β
βAnd the first time this has changed is very recently with codecs and really starting in December, like I've been a kermagin. I've been I've got my way of doing things. I use my terminal. I use my Emacβ¦β
βRealtor.com, Homes.com, Redf Fin, YouTube LinkedIn Instagram sometimes Facebook, local websites.β
βGet in, experiment with it. It's available inside of both the Cap Cut app and inside of Runway right now.β
βRealtor.com, Homes.com, Redf Fin, YouTube LinkedIn Instagram sometimes Facebook, local websites.β
βHaving a password manager, having some sort of hardware security keys, doing more biometrics, understanding how security questions, how weak they can be, and how to improve that.β
βI'm an investor in a company called Stanto...they've been building is this new tool called Stanley that uses AI, looks at your feed, looks at your tone of voice...and tells you what you should postβ
βThe smartest thinking model that we're going to be able to get on our phone is going to be this Quinn 3.5. This is the one we're going to want.β
βNew on the Engineering Blog: How we designed Claude Code auto mode. Many Claude Code users let Claude work without permission prompts. Auto mode is a safer middle ground: we built and tested classifiβ¦β
βThe company Mistraw released a new model called Mistraw Small 4. This is actually an openweight model, so you can actually fine-tune it if you want and run it on your own servers.β
βI built Fabric AI and I started using lang chain and pine cone etc. And then open AI released 40 and became so much better. I just ripped out my entire back stackβ
βundeniable momentum. β So, you know, companies like Cursor and Decagon and 11 and a bridge and and, you know, others.β
βbillions of people now interact with Gemini models, whether that's through AI overview, AI mode, or the Gemini app.β
βIn January 2024, Google DeepMind released an AI model called Alpha Geometry... This is better than the performance of a silver medalist. This quite understandably generated a lot of buzz.β
βWith thanks to @AlphaSenseIncβ
βBlock is using Builder Bot and Builder Bot is this intelligence that Block is building a world model which gives you all this intelligence at your fingertips. It's integrated into Slack.β
βThe reason and right now if you try to get hoppers in the cloud it's all sold out. The reason for that is because CUDA is so programmable and we're constantly the whole world not just us the whole worβ¦β
βAre there companies who are doing real work on safety? I [music] mean, we hear about anthropic, we hear about Deep Mind. Are they helping on the safety front? Yes, I think both Dario Modi and Demis Abβ¦β
βWhat are your thoughts on the upscaling of Hogwarts Legacy and get in here a little closer? So, DLSS5, new AI upscaler happening in real time.β
βAccess to my Content Catalyst custom-built AI tool that help you write content that actually sells.β
βyou could save a lot of money by working with GPT 40 mini instead of GPT 40β
βQuick start: the Iris dataset in Keras and scikit-learnβ
βWe also include results for Command R7B which shares capability and architectural similarities to Command A.β
βfor um try uploading stuff uploading files it's pretty phenomenal if you've got a really long you know paper to readβ
βimages in images out um ... there's a lot of cool stuff you're ricking on a birthday card you're probably going to want to use both um make a little Custom Imageβ
βyou can go online test it for yourself the the web address is thereβ
βwe think we got there earlier this year um with the o1 releaseβ
βtell me what's your favorite open AI API I think the new realtime API is pretty awesomeβ
βWhen these EMVS methods are compared to Stochastic Search Variable Selection (SSVS), the EMVS methods surpass SSVS both in terms of computational speed and correctly identifying significant variables.β
βTo preserve the computational speed of EMVS we also implemented the Stochastic Dual Coordinate Descent (SDCA) algorithm.β
βI'd recommend using neotron 340b to enhance and make it better and we've already seen made llama better made all the other models betterβ
βyou can see with music, you can see you know uh Suno and IDO and so forth.β
βat the moment I've got vs code with co-pilot and I've got cursor and I've got Zed I'm still sticking in vs code co-pilot is the one that I use every dayβ
βIf you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakashβs bundle .β
βIf you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakashβs bundle .β
βIf you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakashβs bundle .β
βUsing pre-trained word embeddings in a Keras modelβ
βAndrej Karpathy confirmed it. The CLIs to install today: GitHub CLI ( gh ) - Claude is aggressively competent at it.β
βFirecrawl CLI - Clean web scraping without MCP overhead.β
βThe make slides skill from the episode includes Puppeteer so Claude can screenshot its HTML output, measure text overflow, and fix issues automatically.β
βThe web research skill replaces Claudeβs unreliable default web search (basically Google first-page results) with Tavily for higher-quality search and Firecrawl for clean markdown scraping.β
βTell Claude βuse your ask user questions toolβ and it generates a custom UI with checkboxes and input fields right inside the terminal.β
βThe answer is Jupyter notebooks . Tell Claude βanalyze this data in a Jupyter notebookβ and it creates a .ipynb file showing every query as a code cell, every result as output, every chart rendered inβ¦β
βAll mutations are done via [Server Actions](https://nextjs.org/docs/app/building-your-application/data-fetching/server-actions-and-mutations)β
βHe built a successful book summary platform called ReadIt. for me backed by billionaire investor and read a book a day for 10 years.β
βWelcome to E-arketer's weekly retail show, Reimagining Retail, an e-arketer podcast made possible by Rocked.β
βI'm I'm going to talk about a good way, a positive way because I I I don't really have anything bad to say about everyone who is out there working so hard. But I I was told to go check out Google's boβ¦β
βI think one really strong opportunity to add value is in the retailer and brandowned assistance. What we saw from our survey is that a lot of these AI assisted shoppers were already using the generalpβ¦β
βIn this work, I introduce Orkan, a simulation library...β
βBenchmarks against Qiskit Aer, QuEST, and Qulacs...β
βBenchmarks against Qiskit Aer, QuEST, and Qulacs...β
βI think what Amazon has been doing with Rufus and its own AI and embedding it throughout more of its site and app in different contexts is really interesting because then they're kind of promoting thiβ¦β
βSo, so what it's done since kind of chat GPT rode back a little bit on instant checkout. It's going to embed its own sparky assistant into chat GPT.β
βI've been reading the MLF blog on the Bloomberg terminal. You can read it too. MLIVgo uh is what you type.β
βDid you see the cereus has um a new llm that runs on phones that I reallys last night and this is Magic right because it crunches down you know it compresses a lot of human knowledge into that llm thaβ¦β
βyou could take the video or audio from this conversation stick it into chat GPT through Whisperers APIβ
βmind CB connects a lot of data and makes it really easy to run machine learning applications modelsβ
βI also work on speech recognition it's called The Deep speech system like one of the first large scale end to end speech recognition for English and Chineseβ
βAnd that's quite different to what is happening here with the online safety bill where social media companies have to basically age check the people who are using them in order to filter that content β¦β
βShe's led a campaign to force them to try and change their products to protect children through her organisation, the Five Rights Foundation, as well as doing many other things, such as pushing througβ¦β
βAnd on the homepage of that, you can click on a button and see the entire table of contents in detail. So, you know, what exactly we're talking about. And there's another button that will display. Andβ¦β
βAnd we'll link to it in the show notes, this researcher named Andrew Stokols, he has a really good sub-stack called Sino-Citiesβ
βUses [Drizzle ORM](https://orm.drizzle.team/docs/overview) and Zod as the data layerβ
βYou can never miss an episode by simply subscribing. Head to the Purple Patch channel of YouTube and you will find it there and you could subscribe.β
βif you like that video make sure to check out the outdoor Boys YouTube channel where we have hundreds of videos just like this and if you want to see our newest Adventures make sure to click subscribeβ¦β
βWe introduce PDDL-Mind, a neuro-symbolic framework that decouples environment state evolution from belief inference.β
βWe introduce QNAS, a neural architecture search framework that unifies hardware aware evaluation, multi objective optimization, and cutting overhead awareness for hybrid quantum classical neural netwoβ¦β
βI hope your listeners will visit my website and check that out. They can find my website at richardduncaneconomics.com. It's richduncaneconomics.com.β
βWe also wrap it in a tool that supports flexible choices of datasets and utility functions, enabling users to target the kinds of questions they care about.β
βWe demonstrate Peerispect through a live, publicly available demo (https://app.reviewer.ly/app/peerispect) and API services, accompanied by a video tutorial.β
βif anybody goes to our website which is just my name jasonhartman.com and you click on the properties page and you look at the performers and the properties you'll see that we even have properties nowβ¦β
βUniversal Paperclips as design inspiration: choosing weird over polished on purposeβ
βI do. And we I set up a website called moneyhabitbank.com. So you can find banks that support this.β
βThere's one bank in particular that's really aggressive. It's called dreamfirst. And when I say aggressive, they're actively supporting this and love it. And they focus on personal finances.β
βIt is. It is moneyhabit mentors and we have 40 certified mentors already. And so moneyhabitmentors.com is the website.β
βYeah. If you want to learn about the book and learn about me, it's mikemotoribike.com.β
βCheck out TidyCall.com. Think of it like Shopify for coaches or consultants. We have been improving it like crazy with subscriptions, better design landing pages, reviews, and more. It's also free. F-β¦β
βKill all of it. Every single subscription and put the entire company on one plan. Anthropics Clawed Team Plan. $24,000 a year. Every single teammate gets a seat. We called it Clawed For All.β
βWell, with the Name Your Price tool from Progressive, you can find options that fit your budget and potentially lower your bills. Try it at Progressive.com.β
βAmong the evaluated architectures, TSCeption achieved the highest average accuracy (0.907) and Macro-F1 score (0.901).β
βWe systematically address these questions on the LEXam benchmarkβ
βconfirming Chorus as a practical tool for generating high-quality deliberation data suitable for online discourse analysisβ
βAn accompanying open-source interactive tool, the Co-creation Provenance Lab, enables policymakers to audit and iteratively improve summaries, establishing genuine human-in-the-loop oversight at scaleβ¦β
βAuditing tools such as SliceFinder and SliceLine were proposed to detect such groups, but usually have conceptual disadvantages, such as the inability to directly address continuous covariates.β
βThrough simulation studies that include a direct comparison with SliceLine, we demonstrate that both approaches have a satisfactory rate of false-positive results.β
βKeras video tutorials from Dan Van Boxelβ
βAll methods are available through qdisc, an open-source Python library designed to make these tools accessible to the broader community.β
βour best model, which was finetuned from the pre-trained WavLM model with the proposed three-stage training strategy, achieve the Accuracy of 0.98, F1 Score of 0.95, AuC of 0.99β
βwe instantiate this paradigm via EVIAN (Explainable Visual Instruction-tuning Data AuditiNg), an automated framework that evaluates these components along the orthogonal axes of Image-Text Consistencyβ¦β
βThis paper proposes LayerTracer, an architecture-agnostic end-to-end analysis framework compatible with any LLM architecture.β
βmake your default homepage chat GPT Bard or Poe from core or whatever whichever one you want the sandbox or playground if you're a developer and just take make a list of everything you do every day anβ¦β
βCollection of tutorials setting up DNNs with Kerasβ
βWhen you use a command line tool, like the one I was using this morning is called Google Workspace command line interface. It doesn't use AI. So it's all programmatic text-based interface, sort of Zorβ¦β
βWe've talked before about the Trust Insights page scanner that you can just get a report of how your site's doing. We've actually got the pro version open now that we'll scan the whole site. That's noβ¦β
βThe items, per-model responses and complete leaderboard are published as a browsable web interface at https://actubench.de/en/, allowing readers and practitioners to inspect individual items without aβ¦β
βI used e Rank and I used Insight Factoryβ
βmake your default homepage chat GPT Bard or Poe from core or whatever whichever one you want the sandbox or playground if you're a developer and just take make a list of everything you do every day anβ¦β