Blog
Field notes from a working AI lab
Research essays, lab diaries, and shorter posts — an illustrative editorial section demonstrating the proposed blog.
19 posts
The EU AI Act at enforcement: a lab's field guide
The European AI Act has teeth in 2026. Here's the working checklist we use before a model touches a hospital, a municipality, or a grid operator.
Small language models are eating the enterprise
The frontier-model arms race dominates Twitter. The real deployments we see in Portuguese hospitals and municipalities are almost entirely 3B–14B models.
Reasoning models vs retrieval: when test-time compute wins
Two families of techniques — retrieval-augmented generation and reasoning models — are often pitted against each other. The truth is they solve different problems.
Clinical LLMs in Portuguese hospitals: the factuality problem
Deploying a Portuguese-language LLM alongside a radiologist taught us that factuality isn't an evaluation metric — it's a product requirement.
Concept drift in production: keeping maintenance models honest
Concept drift is the quiet killer of predictive-maintenance models on live industrial data. A worked example of the detection stack that catches it.
Safety audits for multi-agent systems: a practitioner's checklist
Multi-agent systems exhibit emergent failure modes that single-agent systems cannot. Here is the audit we run before one leaves the lab.
Sim-to-real at the edge: the robot-learning bottleneck no one talks about
The sim-to-real literature is full of clever domain-adaptation tricks. The bottleneck we hit in the LIACC robotics lab is simpler: the real robot is slow.
Five LLM prompts we use weekly at LIACC
Five prompts we copy-paste around the lab. The point isn't that they are magic — it's that they give you something to iterate on.
The research engineer's toolbox, 2026 edition
The tools we actually reach for in 2026. Nothing speculative — all shipping, all in our daily loops.
What I learned debugging a 70B model at 3am
The story of a bad deploy and what it taught me. The short version: logs you wrote three months ago save future-you.
Inside a RoboCup week — a photo diary
What a RoboCup week looks like from inside a team: a short, illustrative photo diary of a run and the year of work behind it.
If you're new to AI research: start here
If you are an MSc or first-year PhD student at Porto or elsewhere, here is the short path I'd give you for your first twelve months.
Open-weight models we actually ship in 2026
A short, opinionated rundown of which open-weight models we deploy at LIACC in 2026, and for what.
A day inside the Porto Ring Road digital twin
An illustrative tour of what a Porto Ring Road digital twin looks like from the inside.
Twelve Portuguese NLP benchmarks you should know
A curated list of twelve Portuguese NLP benchmarks. If you evaluate on Portuguese, one of these is probably on your shortlist.
AI for the rest of us: nine use cases that ship in 2026
Nine concrete AI use cases I've seen ship in small Portuguese teams over the last twelve months.
How I quit writing slides (and picked up a static site generator)
A short, opinionated essay on why I replaced Keynote with a static site generator for most of my internal presentations.
Thesis supervisors want you to know this
Six unwritten rules of writing a good master's thesis that supervisors wish they didn't have to repeat every year.
When to ignore benchmarks
Public benchmarks rank models on the wrong things for most deployments. A short guide on when to look away.