Federico Adolfi
@fedeadolfi.bsky.social
Computation & Complexity | AI Interpretability | Meta-theory | Computational Cognitive Science
https://fedeadolfi.github.io
https://fedeadolfi.github.io
Pinned
Federico Adolfi
@fedeadolfi.bsky.social
· Apr 18
I will be presenting this ✨ spotlight 💫 paper at #ICLR2025 with @martinagvilas.bsky.social. Come say hi if you're interested in DNN circuits, complexity and #interpretability
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
A lot of my work seems to involve my inner voice saying “oh well, try again tomorrow”
November 26, 2025 at 6:20 PM
A lot of my work seems to involve my inner voice saying “oh well, try again tomorrow”
In the privacy of your own mind you can substitute names like Cozy Sequences and Banal Spaces and even Mortal Wombat for the actual names. The important thing to remember is you don’t have to inflict this onto other people by posting it on oops sorry
November 23, 2025 at 2:03 PM
In the privacy of your own mind you can substitute names like Cozy Sequences and Banal Spaces and even Mortal Wombat for the actual names. The important thing to remember is you don’t have to inflict this onto other people by posting it on oops sorry
A surprising number of books:
Title: A friendly introductory primer on the first steps towards [subject]
Preface: for people who are extremely knowledgeable about [subject]
Title: A friendly introductory primer on the first steps towards [subject]
Preface: for people who are extremely knowledgeable about [subject]
November 21, 2025 at 2:20 PM
A surprising number of books:
Title: A friendly introductory primer on the first steps towards [subject]
Preface: for people who are extremely knowledgeable about [subject]
Title: A friendly introductory primer on the first steps towards [subject]
Preface: for people who are extremely knowledgeable about [subject]
Reposted by Federico Adolfi
— Meanwhile, in some math department —
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
November 19, 2025 at 5:46 PM
— Meanwhile, in some math department —
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
Reposted by Federico Adolfi
This but for "realism" and philosophy
— Meanwhile, in some math department —
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
November 19, 2025 at 5:56 PM
This but for "realism" and philosophy
— Meanwhile, in some math department —
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
November 19, 2025 at 5:46 PM
— Meanwhile, in some math department —
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
- this is so cool, what should we call it?
- easy, a kernel
- cool
- wait haven’t we used that term for 39 different unrelated objects already?
- what’s your point?
- yeah you’re right sorry
I’d love to lead my own research group but I’m worried about uncontrollable procrastination (spending 6 months on the lab acronym and logo)
November 18, 2025 at 5:33 PM
I’d love to lead my own research group but I’m worried about uncontrollable procrastination (spending 6 months on the lab acronym and logo)
Reposted by Federico Adolfi
MiniThread: I was reading this paper and through it was worth a comment because the results are very counterintuitive to me (and the authors too)
Miller, G. A., & Selfridge, J. A. (1950). Verbal context and the recall of meaningful material. The American journal of psychology, 63(2), 176-185.
Miller, G. A., & Selfridge, J. A. (1950). Verbal context and the recall of meaningful material. The American journal of psychology, 63(2), 176-185.
November 13, 2025 at 5:06 PM
MiniThread: I was reading this paper and through it was worth a comment because the results are very counterintuitive to me (and the authors too)
Miller, G. A., & Selfridge, J. A. (1950). Verbal context and the recall of meaningful material. The American journal of psychology, 63(2), 176-185.
Miller, G. A., & Selfridge, J. A. (1950). Verbal context and the recall of meaningful material. The American journal of psychology, 63(2), 176-185.
If I were forced to trade my prince..hood..ness for something I wood rather have an m-dash than a mere hyphen
November 12, 2025 at 10:48 PM
If I were forced to trade my prince..hood..ness for something I wood rather have an m-dash than a mere hyphen
I’m looking at the public comments on a manuscript submitted to an ML conference
authors are being nasty to a reviewer because they think it’s secretly a chatbot, some randos are accusing a reviewer of using AI to hallucinate non-existent references, and yet others are showing the papers exist
👍🏻🫠
authors are being nasty to a reviewer because they think it’s secretly a chatbot, some randos are accusing a reviewer of using AI to hallucinate non-existent references, and yet others are showing the papers exist
👍🏻🫠
November 12, 2025 at 10:33 PM
I’m looking at the public comments on a manuscript submitted to an ML conference
authors are being nasty to a reviewer because they think it’s secretly a chatbot, some randos are accusing a reviewer of using AI to hallucinate non-existent references, and yet others are showing the papers exist
👍🏻🫠
authors are being nasty to a reviewer because they think it’s secretly a chatbot, some randos are accusing a reviewer of using AI to hallucinate non-existent references, and yet others are showing the papers exist
👍🏻🫠
Funder: provide a thorough justification for your research program
Me: because if I do this, other researchers will do something else and *they* might discover something huge
Me: because if I do this, other researchers will do something else and *they* might discover something huge
November 12, 2025 at 3:11 PM
Funder: provide a thorough justification for your research program
Me: because if I do this, other researchers will do something else and *they* might discover something huge
Me: because if I do this, other researchers will do something else and *they* might discover something huge
Reposted by Federico Adolfi
I don’t know why people complain about writing research grants. It’s basically looking at your history and realizing that all the pieces represent excellent decisions and figuring out how they point in a specific and promising direction
which is definitely not a form of soul destroying self-harm
which is definitely not a form of soul destroying self-harm
November 11, 2025 at 6:23 PM
I don’t know why people complain about writing research grants. It’s basically looking at your history and realizing that all the pieces represent excellent decisions and figuring out how they point in a specific and promising direction
which is definitely not a form of soul destroying self-harm
which is definitely not a form of soul destroying self-harm
I don’t know why people complain about writing research grants. It’s basically looking at your history and realizing that all the pieces represent excellent decisions and figuring out how they point in a specific and promising direction
which is definitely not a form of soul destroying self-harm
which is definitely not a form of soul destroying self-harm
November 11, 2025 at 6:23 PM
I don’t know why people complain about writing research grants. It’s basically looking at your history and realizing that all the pieces represent excellent decisions and figuring out how they point in a specific and promising direction
which is definitely not a form of soul destroying self-harm
which is definitely not a form of soul destroying self-harm
Documentary filmmakers: the thing that makes these documentaries special is that you can hear the stories directly from the mouths of those who experienced these remarkable events
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
October 25, 2025 at 2:08 PM
Documentary filmmakers: the thing that makes these documentaries special is that you can hear the stories directly from the mouths of those who experienced these remarkable events
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
Reposted by Federico Adolfi
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
October 20, 2025 at 7:55 AM
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
October 20, 2025 at 7:55 AM
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
Reposted by Federico Adolfi
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
October 17, 2025 at 12:26 PM
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
October 17, 2025 at 12:26 PM
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Reposted by Federico Adolfi
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
October 15, 2025 at 8:24 AM
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
October 15, 2025 at 8:24 AM
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
Reposted by Federico Adolfi
What problem is explainability/interpretability research trying to solve in ML, and do you have a favorite paper articulating what that problem is?
October 8, 2025 at 7:27 PM
What problem is explainability/interpretability research trying to solve in ML, and do you have a favorite paper articulating what that problem is?
Reposted by Federico Adolfi
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
October 7, 2025 at 9:40 AM
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
October 7, 2025 at 9:40 AM
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Reposted by Federico Adolfi
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines
September 17, 2025 at 8:09 AM
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines
September 17, 2025 at 8:09 AM
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines