John Berryman
@jnbrymn.bsky.social
LLM consulting @ https://arcturus-labs.com/
Author x2: https://amzn.to/3TXmDHk, https://amzn.to/3zKIxGG
Formerly Eventbrite, GitHub (code search and Copilot)
Author x2: https://amzn.to/3TXmDHk, https://amzn.to/3zKIxGG
Formerly Eventbrite, GitHub (code search and Copilot)
𝐓𝐡𝐢𝐧𝐤 𝐨𝐟 𝐲𝐨𝐮𝐫 𝐋𝐋𝐌 𝐚𝐬 𝐚𝐧 𝐢𝐧𝐭𝐞𝐫𝐧 𝐨𝐧 𝐭𝐡𝐞𝐢𝐫 𝐟𝐢𝐫𝐬𝐭 𝐝𝐚𝐲.
The AI intern is:
- 𝐁𝐫𝐢𝐠𝐡𝐭 𝐛𝐮𝐭 𝐧𝐨𝐭 𝐩𝐬𝐲𝐜𝐡𝐢𝐜
- 𝐏𝐫𝐞𝐟𝐞𝐫𝐬 𝐟𝐚𝐦𝐢𝐥𝐢𝐚𝐫𝐢𝐭𝐲
- 𝐍𝐞𝐞𝐝𝐬 𝐭𝐢𝐦𝐞 𝐭𝐨 𝐭𝐡𝐢𝐧𝐤
- 𝐇𝐚𝐬 𝐚𝐭𝐭𝐞𝐧𝐭𝐢𝐨𝐧 𝐢𝐬𝐬𝐮𝐞𝐬
- 𝐂𝐚𝐧 𝐛𝐞 𝐚 𝐜𝐨𝐧𝐯𝐢𝐧𝐜𝐢𝐧𝐠 𝐥𝐢𝐚𝐫
- 𝐇𝐚𝐬 𝐮𝐧𝐮𝐬𝐮𝐚𝐥 𝐯𝐢𝐬𝐢𝐨𝐧
- 𝐂𝐚𝐧'𝐭 𝐟𝐨𝐫𝐦 𝐧𝐞𝐰 𝐦𝐞𝐦𝐨𝐫𝐢𝐞𝐬
Full blog post is here arcturus-labs.com/blog/2025/10...
The AI intern is:
- 𝐁𝐫𝐢𝐠𝐡𝐭 𝐛𝐮𝐭 𝐧𝐨𝐭 𝐩𝐬𝐲𝐜𝐡𝐢𝐜
- 𝐏𝐫𝐞𝐟𝐞𝐫𝐬 𝐟𝐚𝐦𝐢𝐥𝐢𝐚𝐫𝐢𝐭𝐲
- 𝐍𝐞𝐞𝐝𝐬 𝐭𝐢𝐦𝐞 𝐭𝐨 𝐭𝐡𝐢𝐧𝐤
- 𝐇𝐚𝐬 𝐚𝐭𝐭𝐞𝐧𝐭𝐢𝐨𝐧 𝐢𝐬𝐬𝐮𝐞𝐬
- 𝐂𝐚𝐧 𝐛𝐞 𝐚 𝐜𝐨𝐧𝐯𝐢𝐧𝐜𝐢𝐧𝐠 𝐥𝐢𝐚𝐫
- 𝐇𝐚𝐬 𝐮𝐧𝐮𝐬𝐮𝐚𝐥 𝐯𝐢𝐬𝐢𝐨𝐧
- 𝐂𝐚𝐧'𝐭 𝐟𝐨𝐫𝐦 𝐧𝐞𝐰 𝐦𝐞𝐦𝐨𝐫𝐢𝐞𝐬
Full blog post is here arcturus-labs.com/blog/2025/10...
Context Engineering Requires AI Empathy
Transform your AI applications by thinking like an AI intern on their first day. This post reveals how empathy-driven context engineering leads to better LLM performance, covering everything from hand...
arcturus-labs.com
October 27, 2025 at 4:22 PM
𝐓𝐡𝐢𝐧𝐤 𝐨𝐟 𝐲𝐨𝐮𝐫 𝐋𝐋𝐌 𝐚𝐬 𝐚𝐧 𝐢𝐧𝐭𝐞𝐫𝐧 𝐨𝐧 𝐭𝐡𝐞𝐢𝐫 𝐟𝐢𝐫𝐬𝐭 𝐝𝐚𝐲.
The AI intern is:
- 𝐁𝐫𝐢𝐠𝐡𝐭 𝐛𝐮𝐭 𝐧𝐨𝐭 𝐩𝐬𝐲𝐜𝐡𝐢𝐜
- 𝐏𝐫𝐞𝐟𝐞𝐫𝐬 𝐟𝐚𝐦𝐢𝐥𝐢𝐚𝐫𝐢𝐭𝐲
- 𝐍𝐞𝐞𝐝𝐬 𝐭𝐢𝐦𝐞 𝐭𝐨 𝐭𝐡𝐢𝐧𝐤
- 𝐇𝐚𝐬 𝐚𝐭𝐭𝐞𝐧𝐭𝐢𝐨𝐧 𝐢𝐬𝐬𝐮𝐞𝐬
- 𝐂𝐚𝐧 𝐛𝐞 𝐚 𝐜𝐨𝐧𝐯𝐢𝐧𝐜𝐢𝐧𝐠 𝐥𝐢𝐚𝐫
- 𝐇𝐚𝐬 𝐮𝐧𝐮𝐬𝐮𝐚𝐥 𝐯𝐢𝐬𝐢𝐨𝐧
- 𝐂𝐚𝐧'𝐭 𝐟𝐨𝐫𝐦 𝐧𝐞𝐰 𝐦𝐞𝐦𝐨𝐫𝐢𝐞𝐬
Full blog post is here arcturus-labs.com/blog/2025/10...
The AI intern is:
- 𝐁𝐫𝐢𝐠𝐡𝐭 𝐛𝐮𝐭 𝐧𝐨𝐭 𝐩𝐬𝐲𝐜𝐡𝐢𝐜
- 𝐏𝐫𝐞𝐟𝐞𝐫𝐬 𝐟𝐚𝐦𝐢𝐥𝐢𝐚𝐫𝐢𝐭𝐲
- 𝐍𝐞𝐞𝐝𝐬 𝐭𝐢𝐦𝐞 𝐭𝐨 𝐭𝐡𝐢𝐧𝐤
- 𝐇𝐚𝐬 𝐚𝐭𝐭𝐞𝐧𝐭𝐢𝐨𝐧 𝐢𝐬𝐬𝐮𝐞𝐬
- 𝐂𝐚𝐧 𝐛𝐞 𝐚 𝐜𝐨𝐧𝐯𝐢𝐧𝐜𝐢𝐧𝐠 𝐥𝐢𝐚𝐫
- 𝐇𝐚𝐬 𝐮𝐧𝐮𝐬𝐮𝐚𝐥 𝐯𝐢𝐬𝐢𝐨𝐧
- 𝐂𝐚𝐧'𝐭 𝐟𝐨𝐫𝐦 𝐧𝐞𝐰 𝐦𝐞𝐦𝐨𝐫𝐢𝐞𝐬
Full blog post is here arcturus-labs.com/blog/2025/10...
I had an absolute blast talking about the "7 Deadly Sins of AI Applications" with Hugo Bowne-Anderson, and I'm really pumped to see it in text form now!
(But I do think that neither cartoon John or cartoon Hugo are as handsome as the real deal.)
hugobowne.substack.com/p/patterns-a...
(But I do think that neither cartoon John or cartoon Hugo are as handsome as the real deal.)
hugobowne.substack.com/p/patterns-a...
October 24, 2025 at 1:02 PM
I had an absolute blast talking about the "7 Deadly Sins of AI Applications" with Hugo Bowne-Anderson, and I'm really pumped to see it in text form now!
(But I do think that neither cartoon John or cartoon Hugo are as handsome as the real deal.)
hugobowne.substack.com/p/patterns-a...
(But I do think that neither cartoon John or cartoon Hugo are as handsome as the real deal.)
hugobowne.substack.com/p/patterns-a...
Reposted by John Berryman
@jnbrymn.bsky.social and I are going to have a controversial discussion where maybe we don't agree
maven.com/p/3ad9c7/ai-...
maven.com/p/3ad9c7/ai-...
AI Chat Startups - Is the bubble about to pop?
Investor money chases chat-style interfaces for every domain. I believe this is wrongheaded: ChatGPT and pals will do your domain better as they address more and more long tail-use cases, and better i...
maven.com
July 28, 2025 at 3:49 PM
@jnbrymn.bsky.social and I are going to have a controversial discussion where maybe we don't agree
maven.com/p/3ad9c7/ai-...
maven.com/p/3ad9c7/ai-...
I'm super excited to present to 7CTOs tomorrow on "Wresting with AI Evaluations"
Register here: lu.ma/u9cp3exb
Register here: lu.ma/u9cp3exb
Cutting Through AI Hype with John Berryman (Part 2 of 2) · Zoom · Luma
Join us for the second in a two-part series that goes beyond AI buzz and into practical insight. This event will feature a dynamic blend of presentation, group…
lu.ma
June 25, 2025 at 7:18 PM
I'm super excited to present to 7CTOs tomorrow on "Wresting with AI Evaluations"
Register here: lu.ma/u9cp3exb
Register here: lu.ma/u9cp3exb
You probably knew you could turn an LLM into a classifier. But the basic approach returns a hard classification – yes or no; good or bad.
In this post I'll show you a simple technique to make your LLM classifiers more nuanced – they tell you HOW good or HOW bad something is.
In this post I'll show you a simple technique to make your LLM classifiers more nuanced – they tell you HOW good or HOW bad something is.
June 12, 2025 at 3:14 PM
You probably knew you could turn an LLM into a classifier. But the basic approach returns a hard classification – yes or no; good or bad.
In this post I'll show you a simple technique to make your LLM classifiers more nuanced – they tell you HOW good or HOW bad something is.
In this post I'll show you a simple technique to make your LLM classifiers more nuanced – they tell you HOW good or HOW bad something is.
With the staggering amount of AI paradigms – Workflows, RAG, Agents – it seem impossible to get started learning AI and building your own projects.
But once you realize that all of the ideas are built upon the same simple foundations, you become free to let your ideas flow.
But once you realize that all of the ideas are built upon the same simple foundations, you become free to let your ideas flow.
The Hidden Simplicity of GenAI Systems
At first, GenAI seems neatly split into agents, RAG, and workflows, but up close, it’s messy. This talk clears the fog by uncovering the small set of principles behind all major patterns. Once you gra...
maven.com
June 6, 2025 at 5:33 PM
With the staggering amount of AI paradigms – Workflows, RAG, Agents – it seem impossible to get started learning AI and building your own projects.
But once you realize that all of the ideas are built upon the same simple foundations, you become free to let your ideas flow.
But once you realize that all of the ideas are built upon the same simple foundations, you become free to let your ideas flow.
This should be a really fun talk, Shawn Simister and I have been recalling to ourselves how it all worked. What we realized is that we were doing an early form of LLM-as-judge back in early 2023.
maven.com/p/da8264/how...
maven.com/p/da8264/how...
How Evals Made GitHub Copilot Happen
GitHub Copilot stands as one of the first commercially successful generative AI applications. To make the product work, the copilot team had to invent evaluation methodologies with no existing bluepri...
maven.com
May 8, 2025 at 2:50 AM
This should be a really fun talk, Shawn Simister and I have been recalling to ourselves how it all worked. What we realized is that we were doing an early form of LLM-as-judge back in early 2023.
maven.com/p/da8264/how...
maven.com/p/da8264/how...
I'm looking forward to seeing you live-code a vector database. Lucky for me my only job for the call is to throw tomatoes. :D
Live coding a vector db (HNSW) Wednesday. It'll be fine right? Be kind @jnbrymn.bsky.social
May 5, 2025 at 7:09 PM
I'm looking forward to seeing you live-code a vector database. Lucky for me my only job for the call is to throw tomatoes. :D
Reposted by John Berryman
MAJOR ANNOUNCEMENT
SoftwareDoug LLC has accepted $2K in seed funding from Turnbull Family Grocery Fund to bring you search/AI/RAG consulting, coaching, and training
SoftwareDoug LLC has accepted $2K in seed funding from Turnbull Family Grocery Fund to bring you search/AI/RAG consulting, coaching, and training
April 10, 2025 at 2:48 PM
MAJOR ANNOUNCEMENT
SoftwareDoug LLC has accepted $2K in seed funding from Turnbull Family Grocery Fund to bring you search/AI/RAG consulting, coaching, and training
SoftwareDoug LLC has accepted $2K in seed funding from Turnbull Family Grocery Fund to bring you search/AI/RAG consulting, coaching, and training
OpenAI just revolutionized image generation, but that's just the beginning. The real game-changer? Visual reasoning is coming - where AI won't just manipulate images, but will actually think through problems using visual simulation.
April 7, 2025 at 4:03 AM
OpenAI just revolutionized image generation, but that's just the beginning. The real game-changer? Visual reasoning is coming - where AI won't just manipulate images, but will actually think through problems using visual simulation.
@merlehazard.bsky.social well hi! Any new economic ballads recently? Surely you've no lack of inspiration right now. There's got to be some sort of ballad related to tarrifs.
February 11, 2025 at 4:07 PM
@merlehazard.bsky.social well hi! Any new economic ballads recently? Surely you've no lack of inspiration right now. There's got to be some sort of ballad related to tarrifs.
Exciting times ahead! As we enter a new golden age of creation with LLMs, I dive deep into RAG, AI-assisted coding, and the future of dev tools in my latest podcast with
@dmitrykan.bsky.social for Vector Podcast
@dmitrykan.bsky.social for Vector Podcast
People in every walk of life are much more effective and efficient at creating.. if you love creating, I think we are approaching a new golden age, and it is exponential” youtu.be/60HAtHVBYj8 new episode with @jnbrymn.bsky.social
Code search, Copilot, LLM prompting with empathy and Artifacts - John Berryman, ex-GitHub Copilot
YouTube video by Vector Podcast
youtu.be
February 11, 2025 at 4:05 PM
Exciting times ahead! As we enter a new golden age of creation with LLMs, I dive deep into RAG, AI-assisted coding, and the future of dev tools in my latest podcast with
@dmitrykan.bsky.social for Vector Podcast
@dmitrykan.bsky.social for Vector Podcast
👋 Want to know how to build AI agency into your application? Do it incrementally.
Vlog here:
youtube.com/watch?v=f5qW... and original post in video description. 🤙
Vlog here:
youtube.com/watch?v=f5qW... and original post in video description. 🤙
youtube.com
January 21, 2025 at 11:31 PM
👋 Want to know how to build AI agency into your application? Do it incrementally.
Vlog here:
youtube.com/watch?v=f5qW... and original post in video description. 🤙
Vlog here:
youtube.com/watch?v=f5qW... and original post in video description. 🤙
Building Reliable AI Apps? Start by Firing Yourself.
Don't dive straight into complex AI agents. Start manual, document processes, then systematically automate each task.
Full breakdown + case study:
arcturus-labs.com/blog/2025/01...
Don't dive straight into complex AI agents. Start manual, document processes, then systematically automate each task.
Full breakdown + case study:
arcturus-labs.com/blog/2025/01...
Fire Yourself First: The E-Myth Approach to Iteratively AI App Development - Arcturus Labs
Discover how to build reliable LLM applications by applying the E-Myth's systematic approach to automation. Learn why starting with human processes and incrementally automating tasks leads to more rob...
arcturus-labs.com
January 18, 2025 at 4:00 AM
Building Reliable AI Apps? Start by Firing Yourself.
Don't dive straight into complex AI agents. Start manual, document processes, then systematically automate each task.
Full breakdown + case study:
arcturus-labs.com/blog/2025/01...
Don't dive straight into complex AI agents. Start manual, document processes, then systematically automate each task.
Full breakdown + case study:
arcturus-labs.com/blog/2025/01...
Turnbull's law: "The best way to get the right answer on the Internet is not to ask a question; it's to post the wrong answer." I love it! :D
December 20, 2024 at 5:15 PM
Turnbull's law: "The best way to get the right answer on the Internet is not to ask a question; it's to post the wrong answer." I love it! :D
Home for the holidays means cozy blankets, the scent of pine, and a tech book in the stocking. Prompt Engineering for LLMs—the perfect gift for the developer who finds magic in code and creativity in AI.
December 20, 2024 at 5:02 PM
Home for the holidays means cozy blankets, the scent of pine, and a tech book in the stocking. Prompt Engineering for LLMs—the perfect gift for the developer who finds magic in code and creativity in AI.
I recorded 2 podcasts this week all about LLM application development. My recordings will be out soon, but until then make sure to check out these great programs:
How AI is Built w/ @nicolaygerold open.spotify.com/show/3hhSTyH...
Vector Podcast w/ @DmitryKan open.spotify.com/show/13JO3vh...
How AI is Built w/ @nicolaygerold open.spotify.com/show/3hhSTyH...
Vector Podcast w/ @DmitryKan open.spotify.com/show/13JO3vh...
How AI Is Built
Podcast · Nicolay Gerold · How AI is Built dives into the different building blocks necessary to develop AI applications: how they work, how you can get started, and how you can master them. Build on ...
open.spotify.com
December 20, 2024 at 4:56 PM
I recorded 2 podcasts this week all about LLM application development. My recordings will be out soon, but until then make sure to check out these great programs:
How AI is Built w/ @nicolaygerold open.spotify.com/show/3hhSTyH...
Vector Podcast w/ @DmitryKan open.spotify.com/show/13JO3vh...
How AI is Built w/ @nicolaygerold open.spotify.com/show/3hhSTyH...
Vector Podcast w/ @DmitryKan open.spotify.com/show/13JO3vh...
This is super exciting: Prompt Engineering for LLMs, has been selected for an upcoming beta feature on the O'Reilly Learning platform—AI-powered audio summaries.
They've created two versions (next posts) tell me what you think.
They've created two versions (next posts) tell me what you think.
December 17, 2024 at 7:53 PM
This is super exciting: Prompt Engineering for LLMs, has been selected for an upcoming beta feature on the O'Reilly Learning platform—AI-powered audio summaries.
They've created two versions (next posts) tell me what you think.
They've created two versions (next posts) tell me what you think.
Look out folks! I am Liu-certified to be an AI Consultant now!
Kidding aside, this course really helped me organize how I think about consulting. If you're thinking about tech consulting (even outside of AI), you should consider joining the next cohort maven.com/s/course/3aa...
Kidding aside, this course really helped me organize how I think about consulting. If you're thinking about tech consulting (even outside of AI), you should consider joining the next cohort maven.com/s/course/3aa...
December 16, 2024 at 9:00 PM
Look out folks! I am Liu-certified to be an AI Consultant now!
Kidding aside, this course really helped me organize how I think about consulting. If you're thinking about tech consulting (even outside of AI), you should consider joining the next cohort maven.com/s/course/3aa...
Kidding aside, this course really helped me organize how I think about consulting. If you're thinking about tech consulting (even outside of AI), you should consider joining the next cohort maven.com/s/course/3aa...
Reposted by John Berryman
Read the book, then leave a review! It’s great!
The feedback on Prompt Engineering for LLMs has been good so far! But in order to reach the most people
@thewunderalbert and I need your help. If you've read our book, and if you've learned something useful, then please take a moment to leave a review amzn.to/4fMj2Ef
@thewunderalbert and I need your help. If you've read our book, and if you've learned something useful, then please take a moment to leave a review amzn.to/4fMj2Ef
Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications
Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications
amzn.to
December 13, 2024 at 4:20 PM
Read the book, then leave a review! It’s great!
Mission accomplished. I'm done for the day.
December 13, 2024 at 10:50 PM
Mission accomplished. I'm done for the day.
If you haven't read our book yet, you should! It contains a wealth of information about how to
- source information for your prompts
- properly organize it
- craft prompts so it's understandable to the model
- create a series of prompts to build agency, assistants, & workflows
amzn.to/4fMj2Ef
- source information for your prompts
- properly organize it
- craft prompts so it's understandable to the model
- create a series of prompts to build agency, assistants, & workflows
amzn.to/4fMj2Ef
Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications
Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications
amzn.to
December 13, 2024 at 3:59 PM
If you haven't read our book yet, you should! It contains a wealth of information about how to
- source information for your prompts
- properly organize it
- craft prompts so it's understandable to the model
- create a series of prompts to build agency, assistants, & workflows
amzn.to/4fMj2Ef
- source information for your prompts
- properly organize it
- craft prompts so it's understandable to the model
- create a series of prompts to build agency, assistants, & workflows
amzn.to/4fMj2Ef
The feedback on Prompt Engineering for LLMs has been good so far! But in order to reach the most people
@thewunderalbert and I need your help. If you've read our book, and if you've learned something useful, then please take a moment to leave a review amzn.to/4fMj2Ef
@thewunderalbert and I need your help. If you've read our book, and if you've learned something useful, then please take a moment to leave a review amzn.to/4fMj2Ef
Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications
Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications
amzn.to
December 13, 2024 at 3:58 PM
The feedback on Prompt Engineering for LLMs has been good so far! But in order to reach the most people
@thewunderalbert and I need your help. If you've read our book, and if you've learned something useful, then please take a moment to leave a review amzn.to/4fMj2Ef
@thewunderalbert and I need your help. If you've read our book, and if you've learned something useful, then please take a moment to leave a review amzn.to/4fMj2Ef
Is there an Anti-AI Butlerian Jihad on Bluesky? @eugeneyan.com thinks there might be.
eugeneyan.com/writing/anti...
eugeneyan.com/writing/anti...
A Spark of the Anti-AI Butlerian Jihad (on Bluesky)
How the sharing of 1M Bluesky posts uncovered the strong anti-AI sentiment on Bluesky.
eugeneyan.com
December 12, 2024 at 5:11 PM
Is there an Anti-AI Butlerian Jihad on Bluesky? @eugeneyan.com thinks there might be.
eugeneyan.com/writing/anti...
eugeneyan.com/writing/anti...
Are long boring blog posts not your thing? Here's a 10 minute video covering "Roaming RAG – RAG without the Vector Database" www.youtube.com/watch?v=uOLF...
December 10, 2024 at 3:56 PM
Are long boring blog posts not your thing? Here's a 10 minute video covering "Roaming RAG – RAG without the Vector Database" www.youtube.com/watch?v=uOLF...