Dr. Kam Star

I see abstract AI agent architectures everywhere. But no one explains how to build them in practice. Here's a practical guide to doing it with n8n: 🧵

Check out my latest article: The Delicate Dance Of Leading Product in PE linkedin.com/pulse/delicate… via @LinkedIn

@OctopusEnergy Thank you for jumping on this, appreciate it. Fingers crossed the issue will be solved this time :)

@playgen I'm going to help get your meters up and running now, Kam. I'll reach out over email so we can get this sorted. 🐙

@OctopusEnergy 8 months I've been waiting! 8 months! All I get from customer service is 'we're about to fix it' - but I still can't see my usage after YOU insisted on replacing my meters. Guys #terrible #CustomerServiceFail #fail

I see some vocal objections: "Sora is not learning physics, it's just manipulating pixels in 2D". I respectfully disagree with this reductionist view. It's similar to saying "GPT-4 doesn't learn coding, it's just sampling strings". Well, what transformers do is just manipulating a sequence of integers (token IDs). What neural networks do is just manipulating floating numbers. That's not the right argument. Sora's soft physics simulation is an *emergent property* as you scale up text2video training massively. - GPT-4 must learn some form of syntax, semantics, and data structures internally in order to generate executable Python code. GPT-4 does not store Python syntax trees explicitly. - Very similarly, Sora must learn some *implicit* forms of text-to-3D, 3D transformations, ray-traced rendering, and physical rules in order to model the video pixels as accurately as possible. It has to learn concepts of a game engine to satisfy the objective. - If we don't consider interactions, UE5 is a (very sophisticated) process that generates video pixels. Sora is also a process that generates video pixels, but based on end-to-end transformers. They are on the same level of abstraction. - The difference is that UE5 is hand-crafted and precise, but Sora is purely learned through data and "intuitive". Will Sora replace game engine devs? Absolutely not. Its emergent physics understanding is fragile and far from perfect. It still heavily hallucinates things that are incompatible with our physical common sense. It does not yet have a good grasp of object interactions - see the uncanny mistake in the video below. Sora is the GPT-3 moment. Back in 2020, GPT-3 was a pretty bad model that required heavy prompt engineering and babysitting. But it was the first compelling demonstration of in-context learning as an emergent property. Don't fixate on the imperfections of GPT-3. Think about extrapolations to GPT-4 in the near future.

🚨Arrested for “intent” to hold a placard. What does this say about our “democracy”? #NotMyKing #Coronation #CoronationWeekend #Protest

10 technology trends that will shape the coming decade: 1 automation RPA 2 5G and IoT 3 cloud and edge compute 4 quantum computing  5 applied AI (ML NLP) 6 software 2.0 7 trust architecture (blockchain) 8 bio revolution 9 NG materials 10 clean tech wef.ch/3AznGR3

Goodbye twitter, been a good run. #RIPTwitter

#Intelligentautomation that works to make people’s jobs better: Listen to this podcast to hear Kam Star and Brad Hairston discuss human-centered #automation, and the importance of considering #digitalworkers as co-workers. 🎙️👇 ow.ly/L6qk50JkWvl bit.ly/3m0vTsG

Shout out to Guilherme Morandini, our Community member of the month for April! 🎉 Check out the blog about it here, and find out what names he has given his #digitalworkers! (Hint: 🦸) 👀👇 ow.ly/O7lu50J62lk

Many NHS organizations have been challenged with resourcing the preparation for the COVID-19 Public Inquiry. Join this webinar to hear how @AneurinBevanUHB have used their Blue Prism #digitalworkers to relieve pressure from NHS frontline staff 👇 ow.ly/KP2150J69tf

Afzal Khanani, Head of Retail Operations at @ADIBTweets discusses their measurable ROI after implementing #intelligentautomation into their systems. Find out more 👇 bit.ly/3LVs6Zq

Blue Prism survey reveals untapped opportunities of RPA adoption rates in financial services industry across APAC | Taiwan News | 2022-02-21 10:00:00 bit.ly/3pcMSKq

🎙️Podcast time!🎙️ Ensuring that #artificialintelligence is accessible and easy to support is key to scaling #automation. Brad Hairston talks with Michael Kern about how DataRobot simplifies #AI and helps establish "citizen data scientists" within... bit.ly/3IluqGY

🎙️Podcast time! 🎙️ We talked with Michael Kern, Director AI Enablement and GTM Execution at @DataRobot about how they can ensure #artificialintelligence is accessible and easy to support within organizations. Listen here 👇 ow.ly/hGX650I2wBM bit.ly/33Mdvyl

Join us to uncover the ‘what, when and how’ of process intelligence with #automation in our webinar with @ISG_News and learn how you can accelerate your automation efforts. Register here 👇 ow.ly/hrKK50I2fOw bit.ly/3BPWeAL

Blog post on my vision of a possible path towards autonomous AI: ML that learns more like animals & humans, machine common sense... Buids on SSL, Hierarchical Joint Embedding Predictive Architecture, Energy-Based Models, & planning under uncertainty. ai.facebook.com/blog/yann-lecu…

How can #processintelligence help identify opportunities for #intelligentautomation to accelerate supply chain processes in #manufacturing? Read more 👇 ow.ly/mnnM50HXsUh bit.ly/3s5Tigh

Technology is changing the way we work. If you’re a #compliance professional working in #financialservices, we’d love to hear your thoughts in this short survey, in partnership with @intcompassoc 👇 ow.ly/AVGv50HYxSt bit.ly/3BAPary