Dileep George @dileeplearning
@dileeplearning.bsky.social
AGI research @DeepMind.
Ex cofounder & CTO Vicarious AI (acqd by Alphabet),
Cofounder Numenta
Triply EE (BTech IIT-Mumbai, MS&PhD Stanford). #AGIComics
blog.dileeplearning.com
Ex cofounder & CTO Vicarious AI (acqd by Alphabet),
Cofounder Numenta
Triply EE (BTech IIT-Mumbai, MS&PhD Stanford). #AGIComics
blog.dileeplearning.com
Good conclusion :-).
May 15, 2025 at 1:22 AM
Good conclusion :-).
somehow chatGPT understand my opinion about successor representations? 4/
May 15, 2025 at 1:22 AM
somehow chatGPT understand my opinion about successor representations? 4/
I didn't mention partial observability specifically, so it is impressive that this was picked up. Looks like we did something right in our CSCG paper in making this explicit? 3/
May 15, 2025 at 1:22 AM
I didn't mention partial observability specifically, so it is impressive that this was picked up. Looks like we did something right in our CSCG paper in making this explicit? 3/
It is quite impressive that chatGPT picked up these nuances, picks up a relevant quote from the paper and even emphasizes portions of the response. 2/
May 15, 2025 at 1:22 AM
It is quite impressive that chatGPT picked up these nuances, picks up a relevant quote from the paper and even emphasizes portions of the response. 2/
This paper turned up on a feed, I was intrigued by it and started reading...
..but then I was quite baffled because our CSCG work seem to have tackled many of these problems in a more general setting and it's not even mentioned!
So I asked ChatGPT... ...I'm impressed by the answer1. 1/🧵
..but then I was quite baffled because our CSCG work seem to have tackled many of these problems in a more general setting and it's not even mentioned!
So I asked ChatGPT... ...I'm impressed by the answer1. 1/🧵
May 15, 2025 at 1:22 AM
This paper turned up on a feed, I was intrigued by it and started reading...
..but then I was quite baffled because our CSCG work seem to have tackled many of these problems in a more general setting and it's not even mentioned!
So I asked ChatGPT... ...I'm impressed by the answer1. 1/🧵
..but then I was quite baffled because our CSCG work seem to have tackled many of these problems in a more general setting and it's not even mentioned!
So I asked ChatGPT... ...I'm impressed by the answer1. 1/🧵
Wow, very cool to see this work from Alla Karpova's lab. She had shown me the results when I visited @hhmijanelia.bsky.social and I was blown away.
www.biorxiv.org/content/10.1...
1/
www.biorxiv.org/content/10.1...
1/
April 29, 2025 at 12:05 AM
Wow, very cool to see this work from Alla Karpova's lab. She had shown me the results when I visited @hhmijanelia.bsky.social and I was blown away.
www.biorxiv.org/content/10.1...
1/
www.biorxiv.org/content/10.1...
1/
It's kinda obvious. #AGIComics has already figured out which brain region is the most important. 😇
April 27, 2025 at 8:56 PM
It's kinda obvious. #AGIComics has already figured out which brain region is the most important. 😇
And whether top-down't influence is multiplicative or not is very context-dependent. (this is also what is seen in neurobiology). www.science.org/doi/10.1126/...
April 26, 2025 at 12:59 AM
And whether top-down't influence is multiplicative or not is very context-dependent. (this is also what is seen in neurobiology). www.science.org/doi/10.1126/...
April 26, 2025 at 12:57 AM
March 18, 2025 at 11:37 PM
.... "anxiety", "emotional states" etc. are in quotes, and then used freely.
"stupid" article, in my "humble" opinion.
"stupid" article, in my "humble" opinion.
March 18, 2025 at 10:02 PM
.... "anxiety", "emotional states" etc. are in quotes, and then used freely.
"stupid" article, in my "humble" opinion.
"stupid" article, in my "humble" opinion.
This research is "nonsense". The reviewers and editors that let this pass should be "ashamed".
March 18, 2025 at 9:56 PM
This research is "nonsense". The reviewers and editors that let this pass should be "ashamed".
It was fun to visit Weinan's lab @sunw37.bsky.social at Cornell to give this talk. Exciting to see the experiments he's cooking up, and we had lots of fun discussions about PFC, hippocampus, consciousness and meditation!
Part of the talk content is here: blog.dileeplearning.com/p/space-is-a...
Part of the talk content is here: blog.dileeplearning.com/p/space-is-a...
March 14, 2025 at 10:31 PM
It was fun to visit Weinan's lab @sunw37.bsky.social at Cornell to give this talk. Exciting to see the experiments he's cooking up, and we had lots of fun discussions about PFC, hippocampus, consciousness and meditation!
Part of the talk content is here: blog.dileeplearning.com/p/space-is-a...
Part of the talk content is here: blog.dileeplearning.com/p/space-is-a...
Not True for the papers above. The map is not being created by human in the loop and the organism itself doesn't "read the map". And this is not just our work, many other recent papers on cognitive maps have similar properties too.
March 7, 2025 at 2:38 PM
Not True for the papers above. The map is not being created by human in the loop and the organism itself doesn't "read the map". And this is not just our work, many other recent papers on cognitive maps have similar properties too.
yes. And the papers above do offer this.
1) "maps" are induced as latent graphs from sequence of sensory aliased sensory observations.
2) They perform the following computations (non-exhaustive):
- inferring the current latent state based on history.
- planning computations for reaching goals.
1) "maps" are induced as latent graphs from sequence of sensory aliased sensory observations.
2) They perform the following computations (non-exhaustive):
- inferring the current latent state based on history.
- planning computations for reaching goals.
March 7, 2025 at 2:38 PM
yes. And the papers above do offer this.
1) "maps" are induced as latent graphs from sequence of sensory aliased sensory observations.
2) They perform the following computations (non-exhaustive):
- inferring the current latent state based on history.
- planning computations for reaching goals.
1) "maps" are induced as latent graphs from sequence of sensory aliased sensory observations.
2) They perform the following computations (non-exhaustive):
- inferring the current latent state based on history.
- planning computations for reaching goals.
....yet to be found? I don't think so. At least the papers above provide exactly these mechanisms.
March 7, 2025 at 2:38 PM
....yet to be found? I don't think so. At least the papers above provide exactly these mechanisms.
Wait ….deriving “functional networks” is not the same as mechanistic wiring.
February 10, 2025 at 9:58 PM
Wait ….deriving “functional networks” is not the same as mechanistic wiring.
enormous interconnection is not required to have confounders ...
enormous interconnection is a correlation you are latching on to :-)
enormous interconnection is a correlation you are latching on to :-)
February 10, 2025 at 8:56 PM
enormous interconnection is not required to have confounders ...
enormous interconnection is a correlation you are latching on to :-)
enormous interconnection is a correlation you are latching on to :-)
Fun fact: I sat on this paper for months before submitting because I was terrified of dealing with the review process. But then the reviews surprised me in a positive way....
I like this comment particularly because I drew most of the figures! :-)
I like this comment particularly because I drew most of the figures! :-)
February 7, 2025 at 8:00 PM
Fun fact: I sat on this paper for months before submitting because I was terrified of dealing with the review process. But then the reviews surprised me in a positive way....
I like this comment particularly because I drew most of the figures! :-)
I like this comment particularly because I drew most of the figures! :-)
darn I sinned against it…😬
November 23, 2024 at 11:52 PM
darn I sinned against it…😬
@davidchalmers.bsky.social is on bluesky. Follow him and tell him not to leave a vacuum in philosophical thought #AGIComics
November 23, 2024 at 6:47 PM
@davidchalmers.bsky.social is on bluesky. Follow him and tell him not to leave a vacuum in philosophical thought #AGIComics
Amidst all the arguments, its important to remember science is all about love … #AGIComics
November 21, 2024 at 6:30 AM
Amidst all the arguments, its important to remember science is all about love … #AGIComics
heck, I can even give you a spiking neuron implementation if you want.
November 20, 2024 at 7:40 PM
heck, I can even give you a spiking neuron implementation if you want.
this is a picture from Jay McLellan's paper......connectionist or not? Maybe not according to the new standards...
November 20, 2024 at 5:19 AM
this is a picture from Jay McLellan's paper......connectionist or not? Maybe not according to the new standards...
For example, looks me what is meant here is fitting the data.
November 19, 2024 at 11:46 PM
For example, looks me what is meant here is fitting the data.