Ishan Anand
@ishananand.bsky.social
Stop just reading about AI. Start leading it! @ http://spreadsheets-are-all-you-need.ai
Prev: VP Product @ EdgioInc, CTO/Cofounder @ Layer0Deploy, MIT EECS
Prev: VP Product @ EdgioInc, CTO/Cofounder @ Layer0Deploy, MIT EECS
Reposted by Ishan Anand
So... how does AI work anyway?
@ishananand.bsky.social demystifies LLM internals for web devs using a real LLM implemented entirely in vanilla JS that runs in the browser. No Ph.D. needed!
www.youtube.com/watch?v=clqB...
Subscribe to get notified when we ship more videos from #CascadiaJS 2025! 📺
@ishananand.bsky.social demystifies LLM internals for web devs using a real LLM implemented entirely in vanilla JS that runs in the browser. No Ph.D. needed!
www.youtube.com/watch?v=clqB...
Subscribe to get notified when we ship more videos from #CascadiaJS 2025! 📺
October 29, 2025 at 9:14 PM
So... how does AI work anyway?
@ishananand.bsky.social demystifies LLM internals for web devs using a real LLM implemented entirely in vanilla JS that runs in the browser. No Ph.D. needed!
www.youtube.com/watch?v=clqB...
Subscribe to get notified when we ship more videos from #CascadiaJS 2025! 📺
@ishananand.bsky.social demystifies LLM internals for web devs using a real LLM implemented entirely in vanilla JS that runs in the browser. No Ph.D. needed!
www.youtube.com/watch?v=clqB...
Subscribe to get notified when we ship more videos from #CascadiaJS 2025! 📺
Reposted by Ishan Anand
Ishan Anand (@ishananand.bsky.social) is coming to #CascadiaJS to demystify LLM internals for web developers using a real LLM implemented entirely in vanilla JavaScript that runs in the browser. No Ph.D. needed! 🤓
September 5, 2025 at 9:00 PM
Ishan Anand (@ishananand.bsky.social) is coming to #CascadiaJS to demystify LLM internals for web developers using a real LLM implemented entirely in vanilla JavaScript that runs in the browser. No Ph.D. needed! 🤓
Reposted by Ishan Anand
Ishan Anand (@ishananand.bsky.social) is coming to #CascadiaJS to demystify LLM internals for web developers using a real LLM implemented entirely in vanilla JavaScript that runs in the browser. No Ph.D. needed! 🤓
#JavaScript #LLMs
#JavaScript #LLMs
June 24, 2025 at 7:01 PM
Ishan Anand (@ishananand.bsky.social) is coming to #CascadiaJS to demystify LLM internals for web developers using a real LLM implemented entirely in vanilla JavaScript that runs in the browser. No Ph.D. needed! 🤓
#JavaScript #LLMs
#JavaScript #LLMs
Why R1-Zero is more important than DeepSeek R1: spreadsheets-are-all-you-need.ai/arrrzero-why...
ArrrZero: Why DeepSeek R1 is less important than R1-Zero – Spreadsheets are all you need.ai
spreadsheets-are-all-you-need.ai
March 14, 2025 at 10:11 PM
Why R1-Zero is more important than DeepSeek R1: spreadsheets-are-all-you-need.ai/arrrzero-why...
Spreadsheets-are-all-you-need is finally building out a blog. spreadsheets-are-all-you-need.ai/flops-demyst... is the very first post: A deep dive on AI's most fundamental metric.
FLOPS Demystified: AI and the math behind DeepSeek training costs – Spreadsheets are all you need.ai
spreadsheets-are-all-you-need.ai
February 22, 2025 at 8:12 PM
Spreadsheets-are-all-you-need is finally building out a blog. spreadsheets-are-all-you-need.ai/flops-demyst... is the very first post: A deep dive on AI's most fundamental metric.
If you're a Product Manager in the Seattle area, checkout the ProductTank Seattle event "AI in Action" on March 20th.
Eric Jensen and I will be demystifying how LLMs work and how to use them to increase your productivity in daily product management tasks. www.meetup.com/producttank-...
Eric Jensen and I will be demystifying how LLMs work and how to use them to increase your productivity in daily product management tasks. www.meetup.com/producttank-...
February 21, 2025 at 7:45 PM
If you're a Product Manager in the Seattle area, checkout the ProductTank Seattle event "AI in Action" on March 20th.
Eric Jensen and I will be demystifying how LLMs work and how to use them to increase your productivity in daily product management tasks. www.meetup.com/producttank-...
Eric Jensen and I will be demystifying how LLMs work and how to use them to increase your productivity in daily product management tasks. www.meetup.com/producttank-...
This might be my best AI video yet but it's also my biggest FLOP:
- The difference between FLOP, FLOPS, & FLOPs in AI
- Crack open GPT-2 (using spreadsheets-are-all-you-need) to count every FLOP
- Analyze DeepSeek's viral $5.3M training cost claim
youtu.be/T3JiBtHHTMU
- The difference between FLOP, FLOPS, & FLOPs in AI
- Crack open GPT-2 (using spreadsheets-are-all-you-need) to count every FLOP
- Analyze DeepSeek's viral $5.3M training cost claim
youtu.be/T3JiBtHHTMU
youtu.be
February 20, 2025 at 4:30 PM
This might be my best AI video yet but it's also my biggest FLOP:
- The difference between FLOP, FLOPS, & FLOPs in AI
- Crack open GPT-2 (using spreadsheets-are-all-you-need) to count every FLOP
- Analyze DeepSeek's viral $5.3M training cost claim
youtu.be/T3JiBtHHTMU
- The difference between FLOP, FLOPS, & FLOPs in AI
- Crack open GPT-2 (using spreadsheets-are-all-you-need) to count every FLOP
- Analyze DeepSeek's viral $5.3M training cost claim
youtu.be/T3JiBtHHTMU
Reposted by Ishan Anand
This is wonderful! @ishananand.bsky.social gave a full masterclass on the Latent Space podcast - go watch it! I took his full LLM course on Maven, and it was one of the best I've attended. Congrats, Ishan and Swyx! 👏
www.youtube.com/watch?v=CHfj...
www.youtube.com/watch?v=CHfj...
GPT Internals Masterclass - with Ishan Anand
YouTube video by Latent Space TV (see @LatentSpacePod for Pod)
www.youtube.com
February 20, 2025 at 12:20 PM
This is wonderful! @ishananand.bsky.social gave a full masterclass on the Latent Space podcast - go watch it! I took his full LLM course on Maven, and it was one of the best I've attended. Congrats, Ishan and Swyx! 👏
www.youtube.com/watch?v=CHfj...
www.youtube.com/watch?v=CHfj...
Recently, I had the opportunity to talk at the LatentSpace paper club about OpenAI's GPT-2 model.
As I describe in the video, GPT-2 was important in the evolution of models leading to GPT-3 & ChatGPT.
Thanks @swyx.io and the paper club for having me.
www.youtube.com/watch?v=CHfj...
As I describe in the video, GPT-2 was important in the evolution of models leading to GPT-3 & ChatGPT.
Thanks @swyx.io and the paper club for having me.
www.youtube.com/watch?v=CHfj...
GPT Internals Masterclass - with Ishan Anand
YouTube video by Latent Space TV (see @LatentSpacePod for Pod)
www.youtube.com
February 19, 2025 at 7:23 PM
Recently, I had the opportunity to talk at the LatentSpace paper club about OpenAI's GPT-2 model.
As I describe in the video, GPT-2 was important in the evolution of models leading to GPT-3 & ChatGPT.
Thanks @swyx.io and the paper club for having me.
www.youtube.com/watch?v=CHfj...
As I describe in the video, GPT-2 was important in the evolution of models leading to GPT-3 & ChatGPT.
Thanks @swyx.io and the paper club for having me.
www.youtube.com/watch?v=CHfj...
Reposted by Ishan Anand
Ishan @ishananand.bsky.social provides a fantastic introduction to Deepseek and what sets this model apart in its construction. Understanding the fundamentals pays off!
youtu.be/DE6WpzsSvgU
youtu.be/DE6WpzsSvgU
ArrrZero: Why DeepSeek R1 is less important than R1-Zero
YouTube video by Spreadsheets are all you need
youtu.be
February 17, 2025 at 5:15 PM
Ishan @ishananand.bsky.social provides a fantastic introduction to Deepseek and what sets this model apart in its construction. Understanding the fundamentals pays off!
youtu.be/DE6WpzsSvgU
youtu.be/DE6WpzsSvgU
Earlier this week I had a great discussion with Anthony Campolo on his podcast.
We covered AI, DeepSeek and building an LLM entirely in vanilla JavaScript!
Check it out at www.youtube.com/watch?v=1y28...
We covered AI, DeepSeek and building an LLM entirely in vanilla JavaScript!
Check it out at www.youtube.com/watch?v=1y28...
JavaScript LLMs with Ishan Anand
YouTube video by Anthony Campolo
www.youtube.com
February 13, 2025 at 12:49 AM
Earlier this week I had a great discussion with Anthony Campolo on his podcast.
We covered AI, DeepSeek and building an LLM entirely in vanilla JavaScript!
Check it out at www.youtube.com/watch?v=1y28...
We covered AI, DeepSeek and building an LLM entirely in vanilla JavaScript!
Check it out at www.youtube.com/watch?v=1y28...
Reposted by Ishan Anand
Just typed out 'Wait' in a reply & now I can't help thinking 'am I just an LLM reasoning model??'
Might be consuming a bit too much info about these over the past week XD
Might be consuming a bit too much info about these over the past week XD
February 8, 2025 at 3:16 PM
Just typed out 'Wait' in a reply & now I can't help thinking 'am I just an LLM reasoning model??'
Might be consuming a bit too much info about these over the past week XD
Might be consuming a bit too much info about these over the past week XD
ArrrZero: Why DeepSeek R1 is less important than R1-Zero.
While everyone's talking about DeepSeek R1, the real game-changer is R1-Zero. In this video I cover how this model went straight from base model to reasoning chatbot in one giant leap.
youtu.be/DE6WpzsSvgU
While everyone's talking about DeepSeek R1, the real game-changer is R1-Zero. In this video I cover how this model went straight from base model to reasoning chatbot in one giant leap.
youtu.be/DE6WpzsSvgU
ArrrZero: Why DeepSeek R1 is less important than R1-Zero
YouTube video by Spreadsheets are all you need
youtu.be
January 31, 2025 at 11:19 PM
ArrrZero: Why DeepSeek R1 is less important than R1-Zero.
While everyone's talking about DeepSeek R1, the real game-changer is R1-Zero. In this video I cover how this model went straight from base model to reasoning chatbot in one giant leap.
youtu.be/DE6WpzsSvgU
While everyone's talking about DeepSeek R1, the real game-changer is R1-Zero. In this video I cover how this model went straight from base model to reasoning chatbot in one giant leap.
youtu.be/DE6WpzsSvgU
It appears DeepSeek may have sparked an unexpected surge in interest running AI models locally (see graph of Google Trends for Ollama, a tool for running models locally, below).
January 29, 2025 at 10:25 PM
It appears DeepSeek may have sparked an unexpected surge in interest running AI models locally (see graph of Google Trends for Ollama, a tool for running models locally, below).
Yesterday I had the chance to explain how LLMs work on the JavaScript Jabber podcast. We discussed my JavaScript implementation of GPT2 but also touched on DeepSeek, AI, RAG and more.
Thx @cmaxw.bsky.social, AJ O'Neal, Steve Edwards & @danshappir.bsky.social!
www.youtube.com/watch?v=n94c...
Thx @cmaxw.bsky.social, AJ O'Neal, Steve Edwards & @danshappir.bsky.social!
www.youtube.com/watch?v=n94c...
How LLM's Work and more with Ishan Anand
YouTube video by Top End Devs
www.youtube.com
January 28, 2025 at 11:41 PM
Yesterday I had the chance to explain how LLMs work on the JavaScript Jabber podcast. We discussed my JavaScript implementation of GPT2 but also touched on DeepSeek, AI, RAG and more.
Thx @cmaxw.bsky.social, AJ O'Neal, Steve Edwards & @danshappir.bsky.social!
www.youtube.com/watch?v=n94c...
Thx @cmaxw.bsky.social, AJ O'Neal, Steve Edwards & @danshappir.bsky.social!
www.youtube.com/watch?v=n94c...
Reposted by Ishan Anand
RAG - Retrieval Augmented Generation in a nutshell:
January 15, 2025 at 8:50 AM
RAG - Retrieval Augmented Generation in a nutshell:
Reposted by Ishan Anand
Reposted by Ishan Anand
We all engage in motivated reasoning from time to time. Looking back at my predictions for 2024, I definitely did that on a couple of them hurting my overall grade. If you're curious, check out how I graded my predictions. remotesynthesis.com/blog/reviewi...
Remote Synthesis | Grading my 2024 Predictions for Developers
I wasn't bold and nonetheless I didn't do great. Sheesh.
remotesynthesis.com
January 7, 2025 at 6:13 PM
We all engage in motivated reasoning from time to time. Looking back at my predictions for 2024, I definitely did that on a couple of them hurting my overall grade. If you're curious, check out how I graded my predictions. remotesynthesis.com/blog/reviewi...
Would you listen to this podcast?
An experiment in using NotebookLM to do a daily summary of Y Combinator's HackerNews. youtu.be/AL2Jk2y26ho
An experiment in using NotebookLM to do a daily summary of Y Combinator's HackerNews. youtu.be/AL2Jk2y26ho
Hacker News Discussion 2024-01-05
YouTube video by Ishan Anand
youtu.be
January 6, 2025 at 8:48 PM
Would you listen to this podcast?
An experiment in using NotebookLM to do a daily summary of Y Combinator's HackerNews. youtu.be/AL2Jk2y26ho
An experiment in using NotebookLM to do a daily summary of Y Combinator's HackerNews. youtu.be/AL2Jk2y26ho
When I ported Spreadsheets-are-all-you-need (an Excel implementation of GPT-2) to the web, I knew the first place to showcase it had to be AI Tinkerers — where the journey of the original began. Last month, I had the privilege of debuting it there. Here's the quick video. youtu.be/Csp198KCgGI
Web version of Spreadsheets-are-all-you-need at AI Tinkerers Dec 11, 2024
YouTube video by Spreadsheets are all you need
youtu.be
January 3, 2025 at 5:51 PM
When I ported Spreadsheets-are-all-you-need (an Excel implementation of GPT-2) to the web, I knew the first place to showcase it had to be AI Tinkerers — where the journey of the original began. Last month, I had the privilege of debuting it there. Here's the quick video. youtu.be/Csp198KCgGI
Here’s a process for New Year’s Resolutions that works no matter how audacious your goals:
1️⃣ Write out your New Year’s Resolutions.
2️⃣ For each resolution, ask how AI can help you accomplish the goal.
3️⃣ 365 days from now, write out the same list as in Step 1. 😂
1️⃣ Write out your New Year’s Resolutions.
2️⃣ For each resolution, ask how AI can help you accomplish the goal.
3️⃣ 365 days from now, write out the same list as in Step 1. 😂
January 1, 2025 at 4:19 PM
Here’s a process for New Year’s Resolutions that works no matter how audacious your goals:
1️⃣ Write out your New Year’s Resolutions.
2️⃣ For each resolution, ask how AI can help you accomplish the goal.
3️⃣ 365 days from now, write out the same list as in Step 1. 😂
1️⃣ Write out your New Year’s Resolutions.
2️⃣ For each resolution, ask how AI can help you accomplish the goal.
3️⃣ 365 days from now, write out the same list as in Step 1. 😂
Three under-the-radar AI trends to watch in 2025
Here are three critical but less-discussed trends that could shape the AI landscape next year:
Here are three critical but less-discussed trends that could shape the AI landscape next year:
December 30, 2024 at 8:26 PM
Three under-the-radar AI trends to watch in 2025
Here are three critical but less-discussed trends that could shape the AI landscape next year:
Here are three critical but less-discussed trends that could shape the AI landscape next year:
Reposted by Ishan Anand
An LLM is made of just approx. 500 lines of code and 100+ billions of raw numbers (parameters). These AI models are closer to giant number-crunching machines than traditional if-then-else software. One of my favorite talks of 2024 by @ishananand.bsky.social 👏
youtu.be/NamKkerrlnQ
youtu.be/NamKkerrlnQ
Decoding the Decoder LLM without de code: Ishan Anand
YouTube video by AI Engineer
youtu.be
December 23, 2024 at 12:44 PM
An LLM is made of just approx. 500 lines of code and 100+ billions of raw numbers (parameters). These AI models are closer to giant number-crunching machines than traditional if-then-else software. One of my favorite talks of 2024 by @ishananand.bsky.social 👏
youtu.be/NamKkerrlnQ
youtu.be/NamKkerrlnQ
Are you a web developer curious about how AI/ML and LLMs actually work? Check out this talk I gave yesterday at CFE that walks you through a real LLM entirely in JavaScript. You can even debug it using browser DevTools!
Link in the comments.
Link in the comments.
December 20, 2024 at 4:48 PM
Are you a web developer curious about how AI/ML and LLMs actually work? Check out this talk I gave yesterday at CFE that walks you through a real LLM entirely in JavaScript. You can even debug it using browser DevTools!
Link in the comments.
Link in the comments.
Happening at the top of the hour!
Are you web developer curious about how LLMs actually work under the hood?
Then mark your calendar for Dec 19th! I'll be speaking at CFE and taking the audience inside the brain of an LLM using the new, JavaScript edition of Spreadsheets-are-all-you-need! Link in the comments.
Then mark your calendar for Dec 19th! I'll be speaking at CFE and taking the audience inside the brain of an LLM using the new, JavaScript edition of Spreadsheets-are-all-you-need! Link in the comments.
December 19, 2024 at 5:08 PM
Happening at the top of the hour!