Michael Blake @MichaelBlakeDev

Happy 35th anniversary to Python! Python 0.9.0, the first public version of the popular programming language, released #otd in 1991.

All major neural networks, in one chart. v/The Asimov Institute

@John_T_Harvey Thank you. I have it print and I'll compare it with the audio version as a sleep aid. 😴 We should have a call to catch-up sometime soon.

Unbelievable... Was circling back to write docs on a CI/CD workflow I authored (a few weeks back) and needed quick access links to service account secrets. We have multiple GCP projects with secrets scattered everywhere. Had been feeling lazy and didn't want to manually click through all the IAM/Service Account consoles... I first tried Chrome history (complete waste of time... should have known better) Then started going through hundreds of service accounts jumping in and out of projects.. again no luck and was starting to get annoyed... So I decided to just ask @getpieces and it cooked up a BEAUTIFUL one-shot response.... I'll admit, I was skeptical that the links would actually be proper but sure enough I clicked them and was left speechless... just sooooo good... Currently in complete awe 🫢✨ Then asked a quick follow-up for the same secrets but in another GCP project... and again Pieces just totally nailed it 😇🙌 Lesson learned!!! Pieces for the major win - could have saved myself 5-10 min if I'd started there 🫠

keyboard_arrow_left Previous keyboard_arrow_right Next

@SamBroner Very cool! Dark mode would be extra cool.

Which coding assistants are you using?🤖 Others - drop in comments!

Live from @CivoCloud Navigate NA ‘24 in Austin, TX! 🚀 Join us at the Pieces For Developers booth, where we're diving deep into the transformative realms of AI/ML and Large Language Models. Pieces CEO and Technical Co-Founder, Tsavo Knott, along with Sam Jones, Chief Artificial Intelligence Officer, just led a discussion on Implementing AI Technologies into Developer Tools! Don't miss the chance to talk with our team from Cincinnati, San Francisco, and Spain! We can’t wait to meet you.😄 Learn more: news.pieces.app/2024/pieces-at… #CivoNavigate

@karpathy Amen to this. Thanks for the insight Andrej.

# on shortification of "learning" There are a lot of videos on YouTube/TikTok etc. that give the appearance of education, but if you look closely they are really just entertainment. This is very convenient for everyone involved : the people watching enjoy thinking they are learning (but actually they are just having fun). The people creating this content also enjoy it because fun has a much larger audience, fame and revenue. But as far as learning goes, this is a trap. This content is an epsilon away from watching the Bachelorette. It's like snacking on those "Garden Veggie Straws", which feel like you're eating healthy vegetables until you look at the ingredients. Learning is not supposed to be fun. It doesn't have to be actively not fun either, but the primary feeling should be that of effort. It should look a lot less like that "10 minute full body" workout from your local digital media creator and a lot more like a serious session at the gym. You want the mental equivalent of sweating. It's not that the quickie doesn't do anything, it's just that it is wildly suboptimal if you actually care to learn. I find it helpful to explicitly declare your intent up front as a sharp, binary variable in your mind. If you are consuming content: are you trying to be entertained or are you trying to learn? And if you are creating content: are you trying to entertain or are you trying to teach? You'll go down a different path in each case. Attempts to seek the stuff in between actually clamp to zero. So for those who actually want to learn. Unless you are trying to learn something narrow and specific, close those tabs with quick blog posts. Close those tabs of "Learn XYZ in 10 minutes". Consider the opportunity cost of snacking and seek the meal - the textbooks, docs, papers, manuals, longform. Allocate a 4 hour window. Don't just read, take notes, re-read, re-phrase, process, manipulate, learn. And for those actually trying to educate, please consider writing/recording longform, designed for someone to get "sweaty", especially in today's era of quantity over quality. Give someone a real workout. This is what I aspire to in my own educational work too. My audience will decrease. The ones that remain might not even like it. But at least we'll learn something.

Today would have been the 81st birthday of Professor Patrick Winston, who passed away in 2019 after directing MIT’s AI lab for 25 years. Here are his complete video lectures for 6.034, which have been watched nearly 5 million times: bit.ly/PHWvideos

Wow @LMStudioAI is AMAZING. Just works. I set up local models running on my NVidia and was running in 10 minutes! THEN a local proxy that pretends to be an OpenAI endpoint and I'm writing C# chat apps in airplane mode! lmstudio.ai Damn near perfect app #ai #chatgpt

New blog post!😄 See how Pieces stands out among other competitors as the only full-featured free alternative to GitHub Copilot: code.pieces.app/blog/best-free…

“The most effective debugging tool is still careful thought, coupled with judiciously placed print statements.” — Brian Kernighan, co-creator of Unix

Watch "Connecting a RAG chat app to #AzureCosmosDB" today at 2PM PT / 5PM ET, part of the Hack Together: The AI Chat App Hack youtube.com/watch?v=cpbzQ-…

Many many of you have reached out to me and said you are interested in learning more about the AI validator/red-teamer/adoption driver roles in the AI-verse, aka the people who make sure AI is actually doing what it's supposed to be and also not showing random bias. Good news! There is now training available for it delivered by @_Ioana_Tanase (who does this for a living) on Feb 16th and moderated by meeeee 😁 A reminder of what this role looks like: 🔬Validator/Adoption Driver - Ensures solution does not have strange biases - Deploys to right people - Teaches people how to use the solution (takes longer than you think!) This will be a great job for people from non-tech backgrounds who have expertise in humanities, the arts, language, etc because we need to be able to identify and mitigate wrong info & bias in AI prods. They will also be responsible for helping people in an organization use AI. The job titles will be varied, it might have names like PM, validator, AI tester, adoption driver, AI trainer, etc. The homework I assigned previously to people who want to learn this "Create a prompt library and an AI Skilling program for your space" but HOW do you even get skilled up to do this and also pursue/create jobs? THAT is the question that will be answered on Feb 16th at 8 am PST 👉🏽ioanatanase.com/products/how-t…

Tune in TOMORROW for the inaugural release of our Levy Institute Podcast, featuring conversations that explore alternative perspectives in economics and public policy. Follow the link below for more information. thelevypodcast.podbean.com

#MSAITour keynote