Pedro Madruga
@pedromadruga.com
Applied AI Scientist (in 🇩🇰 since 2012) • http://pedromadruga.com • Interested in Information Retrieval at scale • Lead AI Scientist at Karnov Group
Opinions are my own.
Opinions are my own.
Reposted by Pedro Madruga
The best compliment i can give OpenAI's Codex 5.3 is that it feels way more like Claude Code
February 6, 2026 at 6:07 PM
The best compliment i can give OpenAI's Codex 5.3 is that it feels way more like Claude Code
Reposted by Pedro Madruga
Quilicura, Chile, one of the communities I wrote about in EMPIRE OF AI, has launched a brilliant initiative to inspire more responsible AI prompting. Today, don't use AI; ask the townspeople instead: quili.ai. So heartened to see this creative act of resistance.
January 31, 2026 at 1:25 PM
Quilicura, Chile, one of the communities I wrote about in EMPIRE OF AI, has launched a brilliant initiative to inspire more responsible AI prompting. Today, don't use AI; ask the townspeople instead: quili.ai. So heartened to see this creative act of resistance.
Reposted by Pedro Madruga
The future of software engineering isn't less human, but more focused on higher-level problem-solving. Engineers will evolve to master AI tools, leveraging them to build more robust, thoughtful solutions. #FutureOfWork 6/6
January 31, 2026 at 8:00 PM
The future of software engineering isn't less human, but more focused on higher-level problem-solving. Engineers will evolve to master AI tools, leveraging them to build more robust, thoughtful solutions. #FutureOfWork 6/6
This can't be good for Europe.
ASML staffing changes could result in a net reduction of around 1700 positions
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇
ASML Statement on Strengthening Focus on Engineering and Innovation
www.asml.com
January 28, 2026 at 4:55 PM
This can't be good for Europe.
For all the hate that LangGraph gets, there is a hundred times more people using it in battle-tested grounds (such as gitlab, elastic, klarna, cisco and so on).
Also, it's silly to hate a framework.
Also, it's silly to hate a framework.
January 27, 2026 at 10:13 AM
For all the hate that LangGraph gets, there is a hundred times more people using it in battle-tested grounds (such as gitlab, elastic, klarna, cisco and so on).
Also, it's silly to hate a framework.
Also, it's silly to hate a framework.
With the amount of AI-assisted tools for development coming out - thus impacting teams' development practices from the ground up - the concept of cross-functional teams seems ancient.
A developer that understands these tools will hardly fit in the same team with one that rejects them vehemently.
A developer that understands these tools will hardly fit in the same team with one that rejects them vehemently.
January 26, 2026 at 10:13 AM
With the amount of AI-assisted tools for development coming out - thus impacting teams' development practices from the ground up - the concept of cross-functional teams seems ancient.
A developer that understands these tools will hardly fit in the same team with one that rejects them vehemently.
A developer that understands these tools will hardly fit in the same team with one that rejects them vehemently.
Domain driven AI - where domain knowledge drives AI implementations - is the best approach for AI-based products.
January 25, 2026 at 10:13 AM
Domain driven AI - where domain knowledge drives AI implementations - is the best approach for AI-based products.
Software engineering is, fundamentally, a solved problem. AI Science isn't.
The ones who treat AI challenges as software engineering ones are doomed to fail.
The ones who treat AI challenges as software engineering ones are doomed to fail.
January 24, 2026 at 10:13 AM
Software engineering is, fundamentally, a solved problem. AI Science isn't.
The ones who treat AI challenges as software engineering ones are doomed to fail.
The ones who treat AI challenges as software engineering ones are doomed to fail.
This year, I've tried Helium and Waterfox browsers. I found the former to be buggy and there's something about Chromium-based browsers that doesn't bode well with me. And I've always been a Firefox user, since its Firebird days.
Waterfox was perfect since the get-go. Both on Mac, Linux and Android.
Waterfox was perfect since the get-go. Both on Mac, Linux and Android.
December 23, 2025 at 9:18 AM
This year, I've tried Helium and Waterfox browsers. I found the former to be buggy and there's something about Chromium-based browsers that doesn't bode well with me. And I've always been a Firefox user, since its Firebird days.
Waterfox was perfect since the get-go. Both on Mac, Linux and Android.
Waterfox was perfect since the get-go. Both on Mac, Linux and Android.
Reposted by Pedro Madruga
The Going Dark initiative or ProtectEU is a Chat Control 3.0 attempt
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇
Mullvad VPN (@[email protected])
The European Commission lost the Chat Control 2.0 battle over access to end-to-end encrypted data. By the summer 2026, they will be back with their next attempt: Going Dark. This time some EU member states want to include VPN services.
The Going Dark initiative, or ProtectEU as the Commission now calls it, wants to “enable law enforcement authorities to access encrypted data in a lawful manner”. This is a Chat Control 3.0 attempt.
mastodon.online
December 22, 2025 at 8:00 PM
The Going Dark initiative or ProtectEU is a Chat Control 3.0 attempt
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇
This was also a year where I have been migrating to European-based services. Went from iCloud to Proton Drive, Gmail to Proton Mail and so on.
Migrated from iPhone to Android, since I bought a FairPhone and am very happy with it. FP is much better than I anticipated!
Migrated from iPhone to Android, since I bought a FairPhone and am very happy with it. FP is much better than I anticipated!
December 22, 2025 at 7:18 PM
This was also a year where I have been migrating to European-based services. Went from iCloud to Proton Drive, Gmail to Proton Mail and so on.
Migrated from iPhone to Android, since I bought a FairPhone and am very happy with it. FP is much better than I anticipated!
Migrated from iPhone to Android, since I bought a FairPhone and am very happy with it. FP is much better than I anticipated!
Doing a "year in review" on the technologies I've tried/read about.
One thing that comes to mind is the hostility towards MCP, especially by people who didn't try it.
And I used to do Javascript, which got a lot of heat back in the day. MCP is just a Protocol, people.
One thing that comes to mind is the hostility towards MCP, especially by people who didn't try it.
And I used to do Javascript, which got a lot of heat back in the day. MCP is just a Protocol, people.
December 21, 2025 at 7:45 AM
Doing a "year in review" on the technologies I've tried/read about.
One thing that comes to mind is the hostility towards MCP, especially by people who didn't try it.
And I used to do Javascript, which got a lot of heat back in the day. MCP is just a Protocol, people.
One thing that comes to mind is the hostility towards MCP, especially by people who didn't try it.
And I used to do Javascript, which got a lot of heat back in the day. MCP is just a Protocol, people.
I just read "AI Agents in Action". It's well-supported by code and drawings. Being quite heavy on OpenAI and Microsoft tooling is a drawback. Online reviews are pretty mixed as well.
It's not a beginner-level book but needs more depth. Decent read, all in all.
www.manning.com/books/ai-age...
It's not a beginner-level book but needs more depth. Decent read, all in all.
www.manning.com/books/ai-age...
AI Agents in Action - Micheal Lanham
Create LLM-powered autonomous agents and intelligent assistants tailored to your business and personal needs.
www.manning.com
December 20, 2025 at 10:13 AM
I just read "AI Agents in Action". It's well-supported by code and drawings. Being quite heavy on OpenAI and Microsoft tooling is a drawback. Online reviews are pretty mixed as well.
It's not a beginner-level book but needs more depth. Decent read, all in all.
www.manning.com/books/ai-age...
It's not a beginner-level book but needs more depth. Decent read, all in all.
www.manning.com/books/ai-age...
Reposted by Pedro Madruga
📢 Launching EuroLLM-22B - a fully open, EU-made LLM supporting all 24 EU languages (+11 more)!
🤝 Built by a Europe-wide consortium with #HorizonEurope & @eurohpc-ju.bsky.social support.
🔓 Available now on Hugging Face: lnkd.in/e-xgQXTX
🔗 Learn more: lnkd.in/e6FdpYrN
🤝 Built by a Europe-wide consortium with #HorizonEurope & @eurohpc-ju.bsky.social support.
🔓 Available now on Hugging Face: lnkd.in/e-xgQXTX
🔗 Learn more: lnkd.in/e6FdpYrN
December 15, 2025 at 1:11 PM
📢 Launching EuroLLM-22B - a fully open, EU-made LLM supporting all 24 EU languages (+11 more)!
🤝 Built by a Europe-wide consortium with #HorizonEurope & @eurohpc-ju.bsky.social support.
🔓 Available now on Hugging Face: lnkd.in/e-xgQXTX
🔗 Learn more: lnkd.in/e6FdpYrN
🤝 Built by a Europe-wide consortium with #HorizonEurope & @eurohpc-ju.bsky.social support.
🔓 Available now on Hugging Face: lnkd.in/e-xgQXTX
🔗 Learn more: lnkd.in/e6FdpYrN
Reposted by Pedro Madruga
Dolphin-v2 🐬 new document parsing model released by Bytedance
huggingface.co/ByteDance/Do...
✨ 3B - MIT license
✨ Works on any document: PDFs, scans, photos
✨ Understands 21 types of content: text, tables, code, formulas, figures & more
✨ Pixel-level precision via absolute coordinate prediction
huggingface.co/ByteDance/Do...
✨ 3B - MIT license
✨ Works on any document: PDFs, scans, photos
✨ Understands 21 types of content: text, tables, code, formulas, figures & more
✨ Pixel-level precision via absolute coordinate prediction
ByteDance/Dolphin-v2 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
December 12, 2025 at 12:54 PM
Dolphin-v2 🐬 new document parsing model released by Bytedance
huggingface.co/ByteDance/Do...
✨ 3B - MIT license
✨ Works on any document: PDFs, scans, photos
✨ Understands 21 types of content: text, tables, code, formulas, figures & more
✨ Pixel-level precision via absolute coordinate prediction
huggingface.co/ByteDance/Do...
✨ 3B - MIT license
✨ Works on any document: PDFs, scans, photos
✨ Understands 21 types of content: text, tables, code, formulas, figures & more
✨ Pixel-level precision via absolute coordinate prediction
The influence of domain knowledge is huge when it comes to applied AI.
Domain expertise can prevent overengineering and/or unnecessary costs.
Working in the legal industry as an AI scientist it became obvious early on how crucial it is to build the bridge towards domain experts.
Every day.
Domain expertise can prevent overengineering and/or unnecessary costs.
Working in the legal industry as an AI scientist it became obvious early on how crucial it is to build the bridge towards domain experts.
Every day.
December 10, 2025 at 10:13 AM
The influence of domain knowledge is huge when it comes to applied AI.
Domain expertise can prevent overengineering and/or unnecessary costs.
Working in the legal industry as an AI scientist it became obvious early on how crucial it is to build the bridge towards domain experts.
Every day.
Domain expertise can prevent overengineering and/or unnecessary costs.
Working in the legal industry as an AI scientist it became obvious early on how crucial it is to build the bridge towards domain experts.
Every day.
A chatbot that interacts with NeurIPS 2025 papers: neurips.zeroentropy.dev
Went in to find Information Retrieval related papers and there's a few. Happy reading!
Went in to find Information Retrieval related papers and there's a few. Happy reading!
December 9, 2025 at 10:13 AM
A chatbot that interacts with NeurIPS 2025 papers: neurips.zeroentropy.dev
Went in to find Information Retrieval related papers and there's a few. Happy reading!
Went in to find Information Retrieval related papers and there's a few. Happy reading!
Reposted by Pedro Madruga
We tested one of the most common prompting techniques: giving the AI a persona to make it more accurate
We found that telling the AI "you are a great physicist" doesn't make it significantly more accurate at answering physics questions, nor does "you are a lawyer" make it worse.
We found that telling the AI "you are a great physicist" doesn't make it significantly more accurate at answering physics questions, nor does "you are a lawyer" make it worse.
December 8, 2025 at 6:32 PM
We tested one of the most common prompting techniques: giving the AI a persona to make it more accurate
We found that telling the AI "you are a great physicist" doesn't make it significantly more accurate at answering physics questions, nor does "you are a lawyer" make it worse.
We found that telling the AI "you are a great physicist" doesn't make it significantly more accurate at answering physics questions, nor does "you are a lawyer" make it worse.
We have come full circle.
December 8, 2025 at 8:45 AM
We have come full circle.
Reposted by Pedro Madruga
TITANS & MIRAS: real continual learning
MIRAS = a unifying theory of transformers (attention) and state space models (SSM, e.g. Mamba, RNNs)
TITANS = an optimal MIRAS implementation that’s “halfway between” SSM & transformer with a CL memory module
let’s dive in!
research.google/blog/titans-...
MIRAS = a unifying theory of transformers (attention) and state space models (SSM, e.g. Mamba, RNNs)
TITANS = an optimal MIRAS implementation that’s “halfway between” SSM & transformer with a CL memory module
let’s dive in!
research.google/blog/titans-...
Titans + MIRAS: Helping AI have long-term memory
research.google
December 6, 2025 at 4:04 PM
TITANS & MIRAS: real continual learning
MIRAS = a unifying theory of transformers (attention) and state space models (SSM, e.g. Mamba, RNNs)
TITANS = an optimal MIRAS implementation that’s “halfway between” SSM & transformer with a CL memory module
let’s dive in!
research.google/blog/titans-...
MIRAS = a unifying theory of transformers (attention) and state space models (SSM, e.g. Mamba, RNNs)
TITANS = an optimal MIRAS implementation that’s “halfway between” SSM & transformer with a CL memory module
let’s dive in!
research.google/blog/titans-...
I am a fan of SDD but it often gets confused with Vibe Coding, specially in companies where innovation is met with resistance.
This articles shares some criticism, yet by someone who actually tried it. I disagree with the article and it seems that HN people in thread do too.
Give SDD a try!
This articles shares some criticism, yet by someone who actually tried it. I disagree with the article and it seems that HN people in thread do too.
Give SDD a try!
Spec-Driven Development: The Waterfall Strikes Back | Hacker News
Its not a surprise to me that this approach also helps AI coding agents to work more effectively, as in-depth planning is essentially moving the thinking upfront.(I wrote more about this here:…
news.ycombinator.com
November 18, 2025 at 11:01 AM
I am a fan of SDD but it often gets confused with Vibe Coding, specially in companies where innovation is met with resistance.
This articles shares some criticism, yet by someone who actually tried it. I disagree with the article and it seems that HN people in thread do too.
Give SDD a try!
This articles shares some criticism, yet by someone who actually tried it. I disagree with the article and it seems that HN people in thread do too.
Give SDD a try!
I have been trying lefthook and damn this thing is fast. Also, the ability to run scripts is handy if you like to keep the config tidy.
GitHub - evilmartians/lefthook: Fast and powerful Git hooks manager for any type of projects.
Fast and powerful Git hooks manager for any type of projects. - evilmartians/lefthook
github.com
November 17, 2025 at 6:08 PM
I have been trying lefthook and damn this thing is fast. Also, the ability to run scripts is handy if you like to keep the config tidy.
“Before being technical, science is visionary”
Carlo Rovelli, Reality Is Not What It Seems
Carlo Rovelli, Reality Is Not What It Seems
November 15, 2025 at 9:28 AM
“Before being technical, science is visionary”
Carlo Rovelli, Reality Is Not What It Seems
Carlo Rovelli, Reality Is Not What It Seems