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.
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
Business-applied AI development requires a much higher level of experimentation than traditional software development.
This is because AI development requires a very tight connection to domain knowledge. And each domain requires its own approach, for the most part.
This is because AI development requires a very tight connection to domain knowledge. And each domain requires its own approach, for the most part.
November 14, 2025 at 10:00 AM
Business-applied AI development requires a much higher level of experimentation than traditional software development.
This is because AI development requires a very tight connection to domain knowledge. And each domain requires its own approach, for the most part.
This is because AI development requires a very tight connection to domain knowledge. And each domain requires its own approach, for the most part.
A short (way too short) yet fantastic reading. Rovelli has the gift of explaining complex things simply.
I have quickly moved to reading The Order of Time, another of his books. The way he explains time is just so accessible - thus mind blowing.
I have quickly moved to reading The Order of Time, another of his books. The way he explains time is just so accessible - thus mind blowing.
November 11, 2025 at 6:45 AM
A short (way too short) yet fantastic reading. Rovelli has the gift of explaining complex things simply.
I have quickly moved to reading The Order of Time, another of his books. The way he explains time is just so accessible - thus mind blowing.
I have quickly moved to reading The Order of Time, another of his books. The way he explains time is just so accessible - thus mind blowing.
It’s reasonably amusing to see the resistance from some traditional software developers to some AI tooling. MCP for example, gets a lot of focus from tech doomers because it’s new.
It’s Ok to not use those don’t fit a use case but until they try it it’s just preemptive criticism.
It’s Ok to not use those don’t fit a use case but until they try it it’s just preemptive criticism.
November 10, 2025 at 11:30 AM
It’s reasonably amusing to see the resistance from some traditional software developers to some AI tooling. MCP for example, gets a lot of focus from tech doomers because it’s new.
It’s Ok to not use those don’t fit a use case but until they try it it’s just preemptive criticism.
It’s Ok to not use those don’t fit a use case but until they try it it’s just preemptive criticism.
TIL!
I started using the ThunderAI add-on in Thunderbird. Now my local LLM automatically classifies, auto-replies (reviewable), and summarizes emails across multiple accounts. I did not expect to appreciate it this much!
#Thunderbird #ThunderAI #Productivity #PrivacyFirst #LLM
#Thunderbird #ThunderAI #Productivity #PrivacyFirst #LLM
November 7, 2025 at 8:13 PM
TIL!
The term Agentic Coding is something that resonates quite a lot. But I’ve heard Spec Driven Development and it is spot on.
Both these are almost polar opposite to what Vibe Coding is (imo), even though all are AI powered.
Also, for prototyping: vibe coding all the way.
Both these are almost polar opposite to what Vibe Coding is (imo), even though all are AI powered.
Also, for prototyping: vibe coding all the way.
November 4, 2025 at 1:33 PM
The term Agentic Coding is something that resonates quite a lot. But I’ve heard Spec Driven Development and it is spot on.
Both these are almost polar opposite to what Vibe Coding is (imo), even though all are AI powered.
Also, for prototyping: vibe coding all the way.
Both these are almost polar opposite to what Vibe Coding is (imo), even though all are AI powered.
Also, for prototyping: vibe coding all the way.
An important component of the success of AI-based products is the ability to intertwine data science and (software) engineering.
Enforcing a separation of those is a recipe for failure.
When it works though, it feels like a dance: there might be toe-stepping but the song is the same.
Enforcing a separation of those is a recipe for failure.
When it works though, it feels like a dance: there might be toe-stepping but the song is the same.
September 12, 2025 at 7:54 PM
An important component of the success of AI-based products is the ability to intertwine data science and (software) engineering.
Enforcing a separation of those is a recipe for failure.
When it works though, it feels like a dance: there might be toe-stepping but the song is the same.
Enforcing a separation of those is a recipe for failure.
When it works though, it feels like a dance: there might be toe-stepping but the song is the same.
When people ask what am I doing with so many Pi’s
Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇 #hacker-news
View Article | Join the HN Conversation
Summary of HN discussion 🧵👇 #hacker-news
[v0.16.0] Qwen3 30B A3B Q40 on 4 x Raspberry Pi 5 8GB · b4rtaz/distributed-llama · Discussion #255
qwen3_30b.mov Setup [🔀 TP-Link LS1008G Switch] | | | | | | | |_______ 🔸 raspberrypi2 (ROOT) 10.0.0.2 | | |_________ 🔹 raspberrypi1 (WORKER 1) 10.0.0.1 | |___________ 🔹 raspberrypi3 (WORKER 2) 10.0....
github.com
September 7, 2025 at 6:06 PM
When people ask what am I doing with so many Pi’s
Reposted by Pedro Madruga
this seems like a very good idea actually
August 15, 2025 at 1:38 PM
this seems like a very good idea actually
Phi4 didn’t even try
August 12, 2025 at 7:16 PM
Phi4 didn’t even try
So Anthropic is now the enterprise AI market leader. After having been playing with Opus 4 for the last month, this is rather unsurprising.
Open-source LLMs adoption has stalled.
Src: menlovc.com/perspective/...
Open-source LLMs adoption has stalled.
Src: menlovc.com/perspective/...
August 5, 2025 at 5:46 AM
So Anthropic is now the enterprise AI market leader. After having been playing with Opus 4 for the last month, this is rather unsurprising.
Open-source LLMs adoption has stalled.
Src: menlovc.com/perspective/...
Open-source LLMs adoption has stalled.
Src: menlovc.com/perspective/...
Context engineering (CE) makes sense.
It exposes one of the limitations of RAG: the retrieved chunks lack a structure, thus turning the prompt into a spaghetti of information (inc w/ rerankers).
CE, by providing formatting guidelines, improves the final output - while making testing easier.
It exposes one of the limitations of RAG: the retrieved chunks lack a structure, thus turning the prompt into a spaghetti of information (inc w/ rerankers).
CE, by providing formatting guidelines, improves the final output - while making testing easier.
August 3, 2025 at 6:07 AM
Context engineering (CE) makes sense.
It exposes one of the limitations of RAG: the retrieved chunks lack a structure, thus turning the prompt into a spaghetti of information (inc w/ rerankers).
CE, by providing formatting guidelines, improves the final output - while making testing easier.
It exposes one of the limitations of RAG: the retrieved chunks lack a structure, thus turning the prompt into a spaghetti of information (inc w/ rerankers).
CE, by providing formatting guidelines, improves the final output - while making testing easier.
I've finally clean the dust of my blog and have a few nice blogposts coming in. I'll be writing mostly on Applied AI (scalability, techniques, technical leadership of a successful AI product, etc) from experience in the industry.
Sharing my learnings here: pedromadruga.com/newsletter/
Sharing my learnings here: pedromadruga.com/newsletter/
Newsletter
Hi! This newsletter is a way to get the content I write on my blog delivered to your inbox. Alternatively, you can subscribe to my RSS feed. I’ll write about industry-applied Artificial Intelligence,…
pedromadruga.com
July 27, 2025 at 6:00 AM
I've finally clean the dust of my blog and have a few nice blogposts coming in. I'll be writing mostly on Applied AI (scalability, techniques, technical leadership of a successful AI product, etc) from experience in the industry.
Sharing my learnings here: pedromadruga.com/newsletter/
Sharing my learnings here: pedromadruga.com/newsletter/
“In science if you know what you are doing you should not be doing it.
In engineering if you do not know what you are doing you should not be doing it.”
- Richard Hamming, The Art of Doing Science and Engineering
In engineering if you do not know what you are doing you should not be doing it.”
- Richard Hamming, The Art of Doing Science and Engineering
July 25, 2025 at 2:44 PM
“In science if you know what you are doing you should not be doing it.
In engineering if you do not know what you are doing you should not be doing it.”
- Richard Hamming, The Art of Doing Science and Engineering
In engineering if you do not know what you are doing you should not be doing it.”
- Richard Hamming, The Art of Doing Science and Engineering
Lumo.
Mistral it is. 👍🏼
Mistral it is. 👍🏼
July 24, 2025 at 4:21 PM
Lumo.
Mistral it is. 👍🏼
Mistral it is. 👍🏼
Reposted by Pedro Madruga
What are your favorite recent papers on using LMs for annotation (especially in a loop with human annotators), synthetic data for task-specific prediction, active learning, and similar?
Looking for practical methods for settings where human annotations are costly.
A few examples in thread ↴
Looking for practical methods for settings where human annotations are costly.
A few examples in thread ↴
July 23, 2025 at 8:10 AM
What are your favorite recent papers on using LMs for annotation (especially in a loop with human annotators), synthetic data for task-specific prediction, active learning, and similar?
Looking for practical methods for settings where human annotations are costly.
A few examples in thread ↴
Looking for practical methods for settings where human annotations are costly.
A few examples in thread ↴
One of the best parts of SIGIR2025 were the talks I had with the authors during breaks. So much information to unpack that can only be obtained by being there.
Another great thing was all the amazing work presented.
Another great thing was all the amazing work presented.
July 22, 2025 at 9:58 AM
One of the best parts of SIGIR2025 were the talks I had with the authors during breaks. So much information to unpack that can only be obtained by being there.
Another great thing was all the amazing work presented.
Another great thing was all the amazing work presented.
Reposted by Pedro Madruga
🚨 New paper from us: Given they are trained on human data, can you use psychological techniques that work on humans to persuade AI?
Yes! Applying Cialdini's principles for human influence more than doubles the chance of GPT-4o-mini agreeing to objectionable requests compared to controls.
Yes! Applying Cialdini's principles for human influence more than doubles the chance of GPT-4o-mini agreeing to objectionable requests compared to controls.
July 18, 2025 at 5:08 PM
🚨 New paper from us: Given they are trained on human data, can you use psychological techniques that work on humans to persuade AI?
Yes! Applying Cialdini's principles for human influence more than doubles the chance of GPT-4o-mini agreeing to objectionable requests compared to controls.
Yes! Applying Cialdini's principles for human influence more than doubles the chance of GPT-4o-mini agreeing to objectionable requests compared to controls.
Particularly relevant for speed and cost-saving purposes: post-training quantization seems to yield really good results. It seems that between binary, trinary and 4- and 8-bit quantization, seems 4-bit is the sweet spot since it it's as good as 8-bit.
jina.ai/news/quantiz...
jina.ai/news/quantiz...
Quantization-Aware Training of jina-embeddings-v4
Quantization gives smaller embeddings. We show you fine-tuned quantization gives you even lossless embeddings.
jina.ai
July 7, 2025 at 10:37 AM
Particularly relevant for speed and cost-saving purposes: post-training quantization seems to yield really good results. It seems that between binary, trinary and 4- and 8-bit quantization, seems 4-bit is the sweet spot since it it's as good as 8-bit.
jina.ai/news/quantiz...
jina.ai/news/quantiz...