Alex Strick van Linschoten
@strickvl.bsky.social
ML Engineer (@ ZenML), researcher (& author of a few books).
Pinned
🤔 Do you ever wonder how companies are putting LLMs and GenAI apps into production? What stacks do they use? What architecture did they go with?
I put together a database of known public technical writeups with summaries of the key technical features.
I put together a database of known public technical writeups with summaries of the key technical features.
Reposted by Alex Strick van Linschoten
Something I found interesting about reading this thread is that it made me wonder how many people think of ChatGPT as primarily a tool for writing things for you
I use ChatGPT/Claude/Gemini possibly 100+ times a day and NONE of those uses are to produce writing that I then share with other people
I use ChatGPT/Claude/Gemini possibly 100+ times a day and NONE of those uses are to produce writing that I then share with other people
Maybe it will help a _little_ if I and others like me start saying publicly for the record that we just don’t use ChatGPT.
Writing can be really hard — organizing a piece of writing can be especially hard — but I don’t use ChatGPT.
If you read my stuff you’re reading something an LLM can’t do.
Writing can be really hard — organizing a piece of writing can be especially hard — but I don’t use ChatGPT.
If you read my stuff you’re reading something an LLM can’t do.
May 8, 2025 at 1:39 AM
Something I found interesting about reading this thread is that it made me wonder how many people think of ChatGPT as primarily a tool for writing things for you
I use ChatGPT/Claude/Gemini possibly 100+ times a day and NONE of those uses are to produce writing that I then share with other people
I use ChatGPT/Claude/Gemini possibly 100+ times a day and NONE of those uses are to produce writing that I then share with other people
🔍 Seeking DeepSeek Prompting Insights for ML Labeling
I'm gathering effective prompting strategies for DeepSeek models (R1/V3) specifically for large-scale data labeling operations.
I'm gathering effective prompting strategies for DeepSeek models (R1/V3) specifically for large-scale data labeling operations.
May 8, 2025 at 11:43 AM
🔍 Seeking DeepSeek Prompting Insights for ML Labeling
I'm gathering effective prompting strategies for DeepSeek models (R1/V3) specifically for large-scale data labeling operations.
I'm gathering effective prompting strategies for DeepSeek models (R1/V3) specifically for large-scale data labeling operations.
Have been participating in a group that is doing fastAI part 1 for the first time. Took the opportunity in lesson 1 to use the text dataloaders / trainers to do a little miniproject to see how well fastAI does at classifying between the outputs of different LLM families.
May 5, 2025 at 9:54 AM
Have been participating in a group that is doing fastAI part 1 for the first time. Took the opportunity in lesson 1 to use the text dataloaders / trainers to do a little miniproject to see how well fastAI does at classifying between the outputs of different LLM families.
Wrote up a few initial thoughts on the new iteration of Google's Deep Research
mlops.systems/posts/2025-0...
mlops.systems/posts/2025-0...
Alex Strick van Linschoten - First impressions of the new Gemini Deep Research (with 2.5 Pro)
Some initial fast impressions of Google Deepmind's new iteration of Gemini Deep Research that uses their 2.5 Pro model.
mlops.systems
April 9, 2025 at 1:33 PM
Wrote up a few initial thoughts on the new iteration of Google's Deep Research
mlops.systems/posts/2025-0...
mlops.systems/posts/2025-0...
Reposted by Alex Strick van Linschoten
Been meaning to use the latest Gemini(2.x series) models for a while now. Perfect timing by @strickvl.bsky.social with this set of practical examples in this standalone site.
The only thing that could have made this even better for me would be direct curl examples, but maybe I'm asking too much. 😅
The only thing that could have made this even better for me would be direct curl examples, but maybe I'm asking too much. 😅
Little weekend project: 'Gemini By Example' – practical examples for building with Google's AI models 🚀
I built this simple site to complement Google DeepMind's Gemini SDK with focused, practical code examples - inspired by the "Go By Example" approach.
geminibyexample.com
I built this simple site to complement Google DeepMind's Gemini SDK with focused, practical code examples - inspired by the "Go By Example" approach.
geminibyexample.com
Gemini by Example
Learn the Gemini API through annotated examples
geminibyexample.com
April 7, 2025 at 4:13 PM
Been meaning to use the latest Gemini(2.x series) models for a while now. Perfect timing by @strickvl.bsky.social with this set of practical examples in this standalone site.
The only thing that could have made this even better for me would be direct curl examples, but maybe I'm asking too much. 😅
The only thing that could have made this even better for me would be direct curl examples, but maybe I'm asking too much. 😅
Little weekend project: 'Gemini By Example' – practical examples for building with Google's AI models 🚀
I built this simple site to complement Google DeepMind's Gemini SDK with focused, practical code examples - inspired by the "Go By Example" approach.
geminibyexample.com
I built this simple site to complement Google DeepMind's Gemini SDK with focused, practical code examples - inspired by the "Go By Example" approach.
geminibyexample.com
Gemini by Example
Learn the Gemini API through annotated examples
geminibyexample.com
April 7, 2025 at 12:25 PM
Little weekend project: 'Gemini By Example' – practical examples for building with Google's AI models 🚀
I built this simple site to complement Google DeepMind's Gemini SDK with focused, practical code examples - inspired by the "Go By Example" approach.
geminibyexample.com
I built this simple site to complement Google DeepMind's Gemini SDK with focused, practical code examples - inspired by the "Go By Example" approach.
geminibyexample.com
Just published a blog post about our new ZenML MCP Server - a tool that lets you chat with your ML pipelines using natural language!
www.zenml.io/blog/chat-wi...
www.zenml.io/blog/chat-wi...
Chat With Your ML Pipelines: Introducing the ZenML MCP Server - ZenML Blog
Discover the new ZenML MCP Server that brings conversational AI to ML pipelines. Learn how this implementation of the Model Context Protocol allows natural language interaction with your infrastructur...
www.zenml.io
March 10, 2025 at 9:26 AM
Just published a blog post about our new ZenML MCP Server - a tool that lets you chat with your ML pipelines using natural language!
www.zenml.io/blog/chat-wi...
www.zenml.io/blog/chat-wi...
So excited to read this (just arrived). Had been waiting a long time.
March 8, 2025 at 4:23 PM
So excited to read this (just arrived). Had been waiting a long time.
In Berlin for the Amazon Web Services (AWS) GenAI Loft Week they're putting on. I'll be speaking about the lessons learned from the ZenML LLMOps Database for what it means to put LLMs in production. Do lmk if you're in town!
Free registration for the Monday event:
aws.amazon.com/startups/eve...
Free registration for the Monday event:
aws.amazon.com/startups/eve...
GenAI Loft Berlin - Day 6: Vertical Velocity – Accelerating GenAI in Specific Industries | AWS Startups
GenAI Loft Berlin - Day 6: Vertical Velocity – Accelerating GenAI in Specific Industries
aws.amazon.com
March 1, 2025 at 8:04 PM
In Berlin for the Amazon Web Services (AWS) GenAI Loft Week they're putting on. I'll be speaking about the lessons learned from the ZenML LLMOps Database for what it means to put LLMs in production. Do lmk if you're in town!
Free registration for the Monday event:
aws.amazon.com/startups/eve...
Free registration for the Monday event:
aws.amazon.com/startups/eve...
Working with historical documents in Dari, Pashto, and Arabic made me realise how challenging document translation remains, even with modern LLMs. The models often refuse to translate content (esp for sensitive topics), struggle with long documents and frequently lose context across page boundaries.
February 16, 2025 at 5:56 PM
Working with historical documents in Dari, Pashto, and Arabic made me realise how challenging document translation remains, even with modern LLMs. The models often refuse to translate content (esp for sensitive topics), struggle with long documents and frequently lose context across page boundaries.
Reposted by Alex Strick van Linschoten
These are the kinds of NLP stories I love! TFW you "accidentally" train a great 2 MB (!) task-specific model 🤯 @strickvl.bsky.social
February 14, 2025 at 9:43 AM
These are the kinds of NLP stories I love! TFW you "accidentally" train a great 2 MB (!) task-specific model 🤯 @strickvl.bsky.social
let's do this!
February 10, 2025 at 4:37 PM
let's do this!
Reposted by Alex Strick van Linschoten
FYI...my understanding is that most, if not all of the dead have been buried in Lebanon, with families being told that repatriation of the remains could cost up to $3,000 US, which few of these families could ever afford. Governments are not offering assistance of any kind.
February 10, 2025 at 9:55 AM
FYI...my understanding is that most, if not all of the dead have been buried in Lebanon, with families being told that repatriation of the remains could cost up to $3,000 US, which few of these families could ever afford. Governments are not offering assistance of any kind.
Reposted by Alex Strick van Linschoten
These deaths have been successfully buried.
African leaders are not publicly commenting, fearing backlash at home for their failure to rescue citizens & to avoid ruining valued relations with Israel. Beirut based African diplomats (from at least two countries) have been instructed to stay mum.
African leaders are not publicly commenting, fearing backlash at home for their failure to rescue citizens & to avoid ruining valued relations with Israel. Beirut based African diplomats (from at least two countries) have been instructed to stay mum.
February 10, 2025 at 9:42 AM
These deaths have been successfully buried.
African leaders are not publicly commenting, fearing backlash at home for their failure to rescue citizens & to avoid ruining valued relations with Israel. Beirut based African diplomats (from at least two countries) have been instructed to stay mum.
African leaders are not publicly commenting, fearing backlash at home for their failure to rescue citizens & to avoid ruining valued relations with Israel. Beirut based African diplomats (from at least two countries) have been instructed to stay mum.
Reposted by Alex Strick van Linschoten
Frustrated rant thread:
Israel's 2023-2024 bombing campaign of Lebanon killed >4,000 people, the grand majority, civilians with no affiliation with any armed entity.
Among them, anywhere from a dozen to 30 African migrants (maybe more), most of them Ethiopian women employed as domestic workers.
Israel's 2023-2024 bombing campaign of Lebanon killed >4,000 people, the grand majority, civilians with no affiliation with any armed entity.
Among them, anywhere from a dozen to 30 African migrants (maybe more), most of them Ethiopian women employed as domestic workers.
February 10, 2025 at 9:38 AM
Frustrated rant thread:
Israel's 2023-2024 bombing campaign of Lebanon killed >4,000 people, the grand majority, civilians with no affiliation with any armed entity.
Among them, anywhere from a dozen to 30 African migrants (maybe more), most of them Ethiopian women employed as domestic workers.
Israel's 2023-2024 bombing campaign of Lebanon killed >4,000 people, the grand majority, civilians with no affiliation with any armed entity.
Among them, anywhere from a dozen to 30 African migrants (maybe more), most of them Ethiopian women employed as domestic workers.
yeah this is really clear
February 1, 2025 at 5:10 PM
yeah this is really clear
Reposted by Alex Strick van Linschoten
Very nice recipe for creating a custom classifier on top of ModernBert. DeepSeek is used to generate labels to train on.
Why choose between strong #LLM reasoning and efficient models?
Use DeepSeek to generate high-quality training data, then distil that knowledge into ModernBERT for fast, efficient classification.
New blog post: danielvanstrien.xyz/posts/2025/d...
Use DeepSeek to generate high-quality training data, then distil that knowledge into ModernBERT for fast, efficient classification.
New blog post: danielvanstrien.xyz/posts/2025/d...
Distiling DeepSeek reasoning to ModernBERT classifiers
How can we use the reasoning ability of DeepSeek to generate synthetic labels for fine tuning a ModernBERT model?
danielvanstrien.xyz
January 29, 2025 at 2:19 PM
Very nice recipe for creating a custom classifier on top of ModernBert. DeepSeek is used to generate labels to train on.
Reposted by Alex Strick van Linschoten
Holy moly. I'm trying to write an academic paper, and nearly every application I'm using is not only offering Generative AI as an option for writing, but *pushing it* -- pervading the design to the point where a simple misclick would make my content AI-generated. Here's why that's a problem. 🧵
January 27, 2025 at 6:38 PM
Holy moly. I'm trying to write an academic paper, and nearly every application I'm using is not only offering Generative AI as an option for writing, but *pushing it* -- pervading the design to the point where a simple misclick would make my content AI-generated. Here's why that's a problem. 🧵
Reposted by Alex Strick van Linschoten
A little over two months since my latest book came out! Society Girl — A Tale of Sex, Lies, and Scandal, with Tooba Masood Khan; a true crime story wrapped in a social history of Pakistan in the 70s. Available now in India and Pakistan, and on the Kindle store societygirlbook.com
January 27, 2025 at 7:29 AM
A little over two months since my latest book came out! Society Girl — A Tale of Sex, Lies, and Scandal, with Tooba Masood Khan; a true crime story wrapped in a social history of Pakistan in the 70s. Available now in India and Pakistan, and on the Kindle store societygirlbook.com
📚 Notes on Ch.7 of @chiphuyen.bsky.social's AI Engineering: Fine-tuning isn't your first move - start with prompts & RAG. Memory matters, PEFT helps, and model merging opens interesting doors for multitask learning. Finetune for form, use RAG for facts.
mlops.systems/posts/2025-0...
mlops.systems/posts/2025-0...
Alex Strick van Linschoten - Notes on ‘AI Engineering’ (Chip Huyen) chapter 7: Finetuning
Explores when and how to implement finetuning effectively, looking at key technical aspects like memory considerations and PEFT, while emphasising fine-tuning as a last-resort approach after simpler…
mlops.systems
January 26, 2025 at 3:26 PM
📚 Notes on Ch.7 of @chiphuyen.bsky.social's AI Engineering: Fine-tuning isn't your first move - start with prompts & RAG. Memory matters, PEFT helps, and model merging opens interesting doors for multitask learning. Finetune for form, use RAG for facts.
mlops.systems/posts/2025-0...
mlops.systems/posts/2025-0...
Realise that this stuff is a bit late 2000s web 2.0 style visualization, but have been enjoying checking in with trains.fyi every so often. A live / real-time map of passenger train locations, speeds etc in North America.
trains.fyi
A live, real-time map of passenger train locations in North America.
trains.fyi
January 26, 2025 at 1:25 PM
Realise that this stuff is a bit late 2000s web 2.0 style visualization, but have been enjoying checking in with trains.fyi every so often. A live / real-time map of passenger train locations, speeds etc in North America.
🎯 For the past few weeks, I've been sharing deep dives into our LLMOps database - exploring everything from RAG implementations to security practices. Today's post brings it all together AND introduces a new way to browse our 457 case studies!
www.zenml.io/blog/llmops-...
www.zenml.io/blog/llmops-...
LLMOps in Production: 457 Case Studies of What Actually Works - ZenML Blog
A comprehensive overview of lessons learned from the world's largest database of LLMOps case studies (457 entries as of January 2025), examining how companies implement and deploy LLMs in production. ...
www.zenml.io
January 20, 2025 at 9:51 AM
🎯 For the past few weeks, I've been sharing deep dives into our LLMOps database - exploring everything from RAG implementations to security practices. Today's post brings it all together AND introduces a new way to browse our 457 case studies!
www.zenml.io/blog/llmops-...
www.zenml.io/blog/llmops-...