Yesterday my new colleague J. successfully defended their PhD thesis at Delft University. It was fun to attend. It’s been a while since I was last at a PhD defense. The location was the Senate haal in the brutalist Aula building. Visiting the Aula while I was orienting myself on which university to attend as a teenager was a rather depressing experience, and one of the elements that made me decide against Delft.


The university logo woven into the carpet of the Senate hall where PhD defenses take place.

Also had a pleasant lunch in Delft with colleague P beforehand.

Watching the recorded session about the use of LLMs of the personal knowledge management course I am following this fall provided an interesting question.

Fellow participant H asked different models questions about a paper he uploaded (and also wrote, so he knows what’s in it). One question was to give a summary, one was a highly targeted question for a specific fact in the paper.

He did so first in GPT4All both with local and with online models (ChatGPT etc.). The local models were Llama and Phi.
Here the local models summarised ok but failed the specific question. The online models in contrast did succeed at the targeted question.

He then did the same in LM Studio, and with the same local models got a different result. Both local models now performed well both on the summary and at the targeted question.

So same LLM, same uploaded paper, but a marked difference in output between GPT4All and LM Studio. What would make the difference? The tokenizer that processed the uploaded paper? Other reasons?

Elevator voices full of anguish, as if a terminally bored AGI got stuck announcing floor numbers. It’s a thing. Last summer we stayed one night in the Residence Inn in Ghent, Belgium. Getting in, the elevator announced flooor zeeroooo in a wailing voice. And doing that for the other floors too. We felt for the elevator’s voice. If it was in that bad a mental state, it should get help. The Moaning Myrtle of elevators. Then the elevator in our Berlin hotel last week seemed to also have a bit distorted voice.

Is something eroding the mental health of elevator voice announcers?

This year our apple tree had a good year. The summer was a good mix of sun and rain, and we didn’t have as many wasps, snails or birds taking the apples for themselves as in some previous years.

We gave neighbours and the parents of Y’s best friend each 1-2kgs of apples, ate some, and filled the fridge. There’s still some on the tree to be picked too.


Y standing on a small ladder, disappearing into the apple tree with only her legs visible


Part of the harvest laid out on the garden table.