Enrico Bottazzi (@backaes) header
Enrico Bottazzi (@backaes) profile picture

Oulipian pataphysicist

Joined December 2012
Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)Photo by Enrico Bottazzi (@backaes)
The interconcept space What lies between two concepts (according to an LLM)? What lies between moral persuasion and James Bond's Ford GT?
2
1
4
202
8/n Here, the interconcept space reads like supercars battery engineering
1
13
“There are too many ideas and things and people. Too many directions to go. I was starting to believe the reason it matters to care passionately about something is that it whittles the world down to a more manageable size.”
1
3
166
Effective egoism
4
171
Brandolini law
The bullshit asimmetry: the amount of energy needed to refute bullshit is an order of magnitude bigger than to produce it.
4
142
As always, an ironic turn of events. The tech guy who likes things that fit neatly into binary classifiers is now being automated by the same technology that they contributed to building, while the girl into open-ended disciplines such as medievalism is left untouched.
3
172
Here are interactions with Emma-6, the "Italian" LLM, that make me think there might be a market for dumb LLMs
3
7
1,176
Robo-Schadenfreude: pleasure at watching a robot fail.
2
201
The affordances of model steering via Mech Interpretability techniques
1
173
Thanks to Elisabetta Rocchetti and Carlo Martinucci (@melkon88) from AI Safety Italia for feedback and discussion
1
52
Here's my take on AI safety. In short, forget about anthropomorphizing the models and training them to be moral agents. Just train them to do exactly what their operator asks. It will make our lives easier.
3
208