Hello, I'm Sara!
I'm an experienced software engineer currently based in Europe. I write and give talks about LLMs, NLP, GenAI and AI in general. I'm an open-source contributor and former CERN employee.
Recent Posts
August 04, 2026
A Sycophantic Model Can't Be AGI
We won't ever manage to build an LLM that is smarter than us if we incentivize it to always agree with us.
July 05, 2026
Reasoning makes translations worse
We tend to believe that making the LLM reason more can only improve its answer, regardless of the task. However, when translating from a language to another, the opposite happens.
June 12, 2026
What's an agent harness?
The intelligence of modern AI agents is due to the LLMs, but their practical capabilities only exist thanks to their harness.
May 26, 2026
Reasoning effort defaults across the GPT-5.x family
If you never pinned the reasoning effort across model upgrades, you may have accidentally changed your reasoning effort dramatically.
Recent Talks
October 27, 2026
[UPCOMING] ODSC AI West - From RAG to AI Agent: A Step By Step Build
August 19, 2026
[UPCOMING] AMTA - AI and the Future of Low-Resource Languages
May 19, 2026
The Economist's Impact 2nd AI Compute Summit - Smarter systems, leaner models: reducing compute costs without sacrificing quality
April 29, 2026
ODSC AI East - From RAG to AI Agent