Paul VanderSpek

Anthropic's latest Claude AI model is taking human-AI interaction to a whole new level! 🖥️🤖 The new Claude 3.5 Sonnet can now use computers just like a human would - by looking at the screen, moving the cursor, clicking buttons, and typing text. This is a major leap forward in AI capabilities. Key features: Operates based on screenshots, emulating human computer use Can perform complex multi-step tasks across different applications Self-corrects and retries when encountering obstacles2 Accessible via API for developers to build with Why it's game-changing: This opens up incredible possibilities for AI assistance in data entry, form filling, software testing, and automating repetitive computer tasks13. Imagine having an AI assistant that can seamlessly work alongside you, handling tedious computer work while you focus on higher-level tasks. While still in beta, this technology demonstrates how AI is rapidly advancing toward more human-like interaction with digital interfaces. As it develops further, it could revolutionize how we work with computers and boost productivity across industries. The future of human-AI collaboration just got a lot more exciting! What do you think about this new capability? #AIInnovation #FutureOfWork Here is a video about it: https://lnkd.in/gh8aNYEu

6

Project update! My application tracking extension is now doing fuzzier matching and injecting new information into LinkedIn (and other sites) to keep me from doubling up on applications. Next up: local storage and bulk import/export operations...

12

2 Comments

ModernBERT is an open-source embedding model which represents a significant leap in encoder-only transformer architecture merging: > Long context (8k tokens) > Local-global attention for efficiency > Up-to-date code and text training data (2 trillion tokens) > FlashAttention & Unpadding to push performance on consumer and server GPUs > High retrieval and classification accuracy that sets new benchmarks across GLUE, BEIR, code tasks, and more. Learn more about this exciting new embedding model here: https://lnkd.in/en5ud9VE

2

Hey everyone, I am an investor and advisor to Katanemo.... They are reinventing the infrastructure primitives for GenAI and launched Arch - https://lnkd.in/gCrbbkEV - an intelligent prompt gateway. Give the project a look on Github, and star the project if it resonates

88

3 Comments

I've started using CachyOS; more specifically the KDE / Plasma / Wayland stack with NVIDIA and it's very good indeed. Getting the more modern Wayland going with performant graphics drivers has been hard work the last few months, with many false starts. I now use vanilla headless Ubuntu 22 over SSH for my primary multiGPU compute, with a wireguard VPN into that from CachyOS, basically a VERY thick client/hybrid model. I am building software on the server side within Cursor.so and VSCode/CLINE directly using an SSH remote in the IDE, but this means I can slip to local very easily, pushing the focus of the Docker builds back and forth in the moment. https://lnkd.in/emZQuAcS I commend this approach!

1

Want to tease something my team has been working on over at Buffer! The attached image isn't a mockup, but a screenshot of a live prototype of RSS feeds directly in Buffer! It's only available internally and still pretty rough at this point, but we'll have it available for user testing soon. With this enhancement, we hope to help Buffer users easily find new and engaging content to share with their audiences. What do you think? Will RSS feeds in Buffer help you create more content?

19

1 Comment

The latest snapshot builds of Spring AI now include multimodal audio support for OpenAI's gpt-4o-audio-preview model. To see how it works, have a look at https://lnkd.in/gMNnbDrv.

22

The latest edition of The Driverless Digest has just been published! Highlights from this week: 🤖 Waymo now at $45 Billion valuation but how do they stack up to Uber at a public market cap of $150 billion? 💵🔥Zoox to launch in San Francisco and Las Vegas. 🤖 Waymo working on scheduled rides feature which is great for customers but read why I think it’s only going to hurt their utilization. Check it out here - https://lnkd.in/gNywsSmW

18

I just realized: we should start saying "build memoization" rather than "build caching." We aren't really talking about least-recently-used or time-to-live algorithms, we're talking about "don't bother recompiling this piece if none of its inputs changed." (It has been puzzling me that some people are so deeply fearful of "build cache" as a concept, and honestly I think it's mostly because most build systems have non-hermetic state scattered all over the place. Maybe a slightly more precise term for the type of caching we're concerned with would clarify the semantics in question.)

83

9 Comments

🌶🌶🌶 Hot take… Old problem: if we put more devs on the project, we can deliver it sooner. Same thinking, new manifestation: we can hire more overseas devs for less total money to produce the same result as our US staff. Flaw in that thinking: product development is not an assembly line. Devs are not “interchangeable”. Software is as much an art as it is science. It’s a team sport. The people on your team matters. #tech #staffing #management #hiring #jobs #layoffs #software #startup #teamleadership

25

6 Comments

Waymo is probably both more expensive and longer waits on average than Uber or Lyft today, but they are close enough, and rapidly getting better. These markets will flip to fully autonomous when the tech is ready.

2

My team and I built an AI agent that helps us debug our production issues. And now we're sharing some code for you to build your own 👩‍💻 I’ve talked to quite a few engineering teams that want to launch an agent for engineering teams to investigate and fix production issues faster. Because there’s no great reference architecture, template, or guide, it took me months of trial and error to get to a point I’m happy with. Now, my colleague Eric Abruzzese has written down several pro tips and steps on how to build an AI agent so you can learn from (and avoid) our mistakes. So what took us months could take you a few hours to do (if not less). In our 3-part series, we cover: 1. How to set up an application in Chainlit 2. How to connect your application to an LLM (in this case, gpt-4o) 3. How to make your Agent faster and add real-time “typing” (similar to ChatGPT) 4. How to give your Agent a personality and specialization 5. How to give your Agent the ability to search a collection of files 6. How to integrate your Agent with external tools (in this case, PagerDuty) Check out part 1 of the guide on our site (link in comments), and keep an eye out for part 2 coming soon (if you want a sneak peek, drop a comment and I'll send you the private Notion page 🕵️).

116

8 Comments

The revoultion in Storytelling coming to us via Generative AI is two-fold. One, we are soon to be able to assemble small, and very talented creative teams (writers, artists, directors, and actors) and create vast universes and intricate stories that while still driven from their center by human hearts, minds, and hands, have the ability to explode into being and even evolve over time at the highest fidelity and in myriad or even blended styles. Two, these narratives will become increasingly personalized, immersive, but still social shared experiences that sustain engagement in ways that give each of us what we love most without compromising the integrity of the storytelling universe, succumbing to the weight of insurmountable costs, or being hindered by the production timeline realities of today. It will be a disruptive shift, but one that can be ultimately democratizing in ways that will eventually encourage and empower artists again and give rise to new talents and new stories of all kinds because the gap between the audience and the creator will close to the point of intimacy. #media #generativeai #storytelling #ai #artists #streaming

11

Check out this solution for building user authentication features into generative AI RAG applications!

2

I'm excited to announce that I'll be presenting at the Codeborging: AI-Powered Programming Meetup on June 12 on "Harnessing OpenAI Assistants for Dynamic Content Generation." In this session, I'll share insights from my journey of using OpenAI Assistants to streamline content creation and enhance productivity. Key highlights will include: - Knowledge Bot: A context-driven OpenAI Assistant that personalizes content generation using advanced GPT-4o models. - Amazon Treasures Chat: Enhancing the e-commerce experience with AI-driven conversational interfaces. We will dive into practical code examples, demonstrating how to set up these assistants, craft effective prompts, and integrate them into your projects. Key Takeaways: - How to prepare data and configure OpenAI Assistants - Practical Tips for Generating Natural Language Search Results - Real-world applications to boost daily productivity, like generating blog posts, handling communications, etc. Join us and unlock the potential of AI in your projects. Don't miss this opportunity to elevate your content strategy and productivity with AI! #AI #ContentCreation #OpenAI #TechTalk #MachineLearning #Productivity #SoftwareDevelopment Artium LeanDog

12

1 Comment

If you're wondering how to use AI and events to enable real world workflows like podcast production, my colleague Sean Falconer has written a great blog post showing you how to do this.

4

The session unfortunately wasn't recorded, but here are the slides from my talk at LFMS on quantifying the ROI of contributing to OSS https://lnkd.in/gwdQa3UZ

66

5 Comments