John Alexander

Christ Follower, #Accessability focused w CP, AI App Dev Storyteller @ Microsoft; RL,AI, VR/AR, IOT. Opinions mine. RTs & likes!=endorse

[John Alexander @JohnAlexander]

Here is the resource guide for today's Transforming Your Future with Prompt Engineering and Generative AI presentation at DevSum 2023: https://t.co/E1NOpc5SRk #DevSum

[a16z @a16z]

“There’s a Mexican standoff happening between product manager, designer, and coder.”

Marc Andreessen on how AI is reshaping core tech roles:

“Every coder now believes they can also be a product manager and a designer, because they have AI. Every product manager thinks they can be a coder and a designer. And every designer knows they can be a product manager and a coder.”

“People in each of those roles now know or believe that with AI, they don’t need the other two roles anymore.”

@pmarca on Lenny's Podcast with @lennysan

[Ethan Mollick @emollick]

“Write a single paragraph about someone who doles out their remaining words like wartime rations, having been told they only have ten thousand left in their lifetime. They’re at 47 words remaining, holding their newborn.”

[I Am Devloper @iamdevloper]

every time

[Simon Willison @simonw]

Qwen3-4B-Thinking (a 4GB download) just became the first model I've tested to directly push back against my pelican riding a bicycle test, calling it "oddly specific and completely unrealistic" and saying "this request violates physics and biology"
https://t.co/Vkij4NFYit

[elvis @omarsar0]

Getting huge productivity boosts by combining Claude Code with Obsidian vaults.

Everything in Obsidian is .md, so this is like the most delicious context for LLMs.

Everything is in one place: notes, bookmarks, instructions, LLM context, AI outputs, and so on.

[zak @0xzak]

I've been in crypto for over 10 years and I’ve Never been hacked. Perfect OpSec record.

Yesterday, my wallet was drained by a malicious @cursor_ai extension for the first time.

If it can happen to me, it can happen to you. Here’s a full breakdown. 🧵👇

[John Alexander @JohnAlexander]

@markrendle

[John Alexander @JohnAlexander]

@timheuer No, you have no headcount... Nor do I.... :)

[John Alexander @JohnAlexander]

@shanselman And the loser's head pops up like Rockem Sockem Robots.

[David Fowler @davidfowl]

I am finally planning to write down some of what's been juggling around in my brain for years about writing high performance .NET code. I figure it would initially be a similar format to https://t.co/p7xVCJtGCn.

[AK @_akhaliq]

On the Origin of LLMs: An Evolutionary Tree and Graph for 15,821 Large Language Models

paper page: https://t.co/pExuXuoOHO

Since late 2022, Large Language Models (LLMs) have become very prominent with LLMs like ChatGPT and Bard receiving millions of users. Hundreds of new LLMs are announced each week, many of which are deposited to Hugging Face, a repository of machine learning models and datasets. To date, nearly 16,000 Text Generation models have been uploaded to the site. Given the huge influx of LLMs, it is of interest to know which LLM backbones, settings, training methods, and families are popular or trending. However, there is no comprehensive index of LLMs available. We take advantage of the relatively systematic nomenclature of Hugging Face LLMs to perform hierarchical clustering and identify communities amongst LLMs using n-grams and term frequency-inverse document frequency. Our methods successfully identify families of LLMs and accurately cluster LLMs into meaningful subgroups. We present a public web application to navigate and explore Constellation, our atlas of 15,821 LLMs. Constellation rapidly generates a variety of visualizations, namely dendrograms, graphs, word clouds, and scatter plots.

[John Alexander @JohnAlexander]

This is very very cool. Nice job!!!

[David Pine @davidpine7]

🤓 Did you know that @aspnet Minimal APIs can return IAsyncEnumerable<T> and you can consume said APIs with await foreach too?!

@stephentoub shared this API with me and it's 🔥.

#dotnet #csharp

1️⃣ API returns IAsyncEnumerable<T>
2️⃣ JsonSerializer.DeserializeAsyncEnumerable<T>

[Hao Liu @haoliuhl]

Many thanks to @_akhaliq for sharing our arxiv paper :)
https://t.co/86w1e6eSDs

[John Alexander @JohnAlexander]

#NewProfilePic

[Kansas City Developer Conference @kc_dc]

https://t.co/p3TxIVka2p

[Luis Quintanilla.rss @ljquintanilla]

Looking to improve the outputs generated by GPT? Check out this blog post 👇

#dotnet #openai #promptengineering #llm #azure #ai

https://t.co/KMhHVlPQnl

[John Alexander @JohnAlexander]

@Darcy_Lussier I will try it out!

[John Alexander @JohnAlexander]

"Sometimes all you need for exceptional results is average effort repeated for an above-average amount of time."

– @JamesClear

[John Alexander @JohnAlexander]

@slhamlet @Scobleizer @jowyang And if that happens, it will be interesting to watch the legal fights over who owns the IP for those scripts…