Shachar Mirkin
@shacharmirkin.bsky.social
The impact of model size and dedicated hardware on inference energy consumption
MIAI Days Grenoble
MIAI Days Grenoble
June 20, 2025 at 8:27 AM
The impact of model size and dedicated hardware on inference energy consumption
MIAI Days Grenoble
MIAI Days Grenoble
Using VR and AI to prepare for natural and subsequent technological crises.
Population is modeled as multiple agents.
They use this system to run different scenrios and train local autorithies and emergency services.
Population is modeled as multiple agents.
They use this system to run different scenrios and train local autorithies and emergency services.
June 19, 2025 at 2:49 PM
Using VR and AI to prepare for natural and subsequent technological crises.
Population is modeled as multiple agents.
They use this system to run different scenrios and train local autorithies and emergency services.
Population is modeled as multiple agents.
They use this system to run different scenrios and train local autorithies and emergency services.
Attending MIAI Days 2025 @ Grenoble.
Will share a bit over here
Will share a bit over here
June 19, 2025 at 7:31 AM
Attending MIAI Days 2025 @ Grenoble.
Will share a bit over here
Will share a bit over here
Many people (me included) are seeing Invalid Notebook messages on GitHub lately, so I wrote down all the solutions (workarounds) that worked for me in this gist
gist.github.com/shacharmirki...
gist.github.com/shacharmirki...
April 18, 2025 at 12:17 PM
Many people (me included) are seeing Invalid Notebook messages on GitHub lately, so I wrote down all the solutions (workarounds) that worked for me in this gist
gist.github.com/shacharmirki...
gist.github.com/shacharmirki...
My son, Ofir Mirkin, is presenting today a poster about programmable inflatable panels (that's CS for physics) 🤩
March 27, 2025 at 3:57 PM
My son, Ofir Mirkin, is presenting today a poster about programmable inflatable panels (that's CS for physics) 🤩
Why are LLMs always getting the number of fingers wrong?
March 12, 2025 at 3:40 PM
Why are LLMs always getting the number of fingers wrong?
A math/physics problem: ⛷️
You ski down a slope and want to to gain speed. There's a little "hill" coming up, and you need to decide whether to continue on your steady slope or ski up the hill, to accelerate more on the way down the steeper slope >>
You ski down a slope and want to to gain speed. There's a little "hill" coming up, and you need to decide whether to continue on your steady slope or ski up the hill, to accelerate more on the way down the steeper slope >>
February 11, 2025 at 8:32 AM
A math/physics problem: ⛷️
You ski down a slope and want to to gain speed. There's a little "hill" coming up, and you need to decide whether to continue on your steady slope or ski up the hill, to accelerate more on the way down the steeper slope >>
You ski down a slope and want to to gain speed. There's a little "hill" coming up, and you need to decide whether to continue on your steady slope or ski up the hill, to accelerate more on the way down the steeper slope >>
>> Anthropomorphic features in AI: taxonomy >>
November 14, 2024 at 5:53 PM
>> Anthropomorphic features in AI: taxonomy >>
Human-robot interaction @ Naver Labs
Canfer Akbulut on anthropomorphism
[Oxford: "the attribution of human characteristics or behaviour to a god, animal, or object."]
[Picture is mine]
Canfer Akbulut on anthropomorphism
[Oxford: "the attribution of human characteristics or behaviour to a god, animal, or object."]
[Picture is mine]
November 14, 2024 at 5:53 PM
Human-robot interaction @ Naver Labs
Canfer Akbulut on anthropomorphism
[Oxford: "the attribution of human characteristics or behaviour to a god, animal, or object."]
[Picture is mine]
Canfer Akbulut on anthropomorphism
[Oxford: "the attribution of human characteristics or behaviour to a god, animal, or object."]
[Picture is mine]
HRI @ Naver Labs.
Simulating heart beat and breathing to help humans better interpret the robot's "emotion"
Simulating heart beat and breathing to help humans better interpret the robot's "emotion"
November 14, 2024 at 1:35 PM
HRI @ Naver Labs.
Simulating heart beat and breathing to help humans better interpret the robot's "emotion"
Simulating heart beat and breathing to help humans better interpret the robot's "emotion"
Human-robot interaction symposium @ Naver Labs:
A very interesting work about exoskeletons, detecting the amount to apply based on muscle signals
A very interesting work about exoskeletons, detecting the amount to apply based on muscle signals
November 14, 2024 at 1:33 PM
Human-robot interaction symposium @ Naver Labs:
A very interesting work about exoskeletons, detecting the amount to apply based on muscle signals
A very interesting work about exoskeletons, detecting the amount to apply based on muscle signals
Marta Romeo @ Naver Labs HRI:
Multi-party conversations are even more challenging
Multi-party conversations are even more challenging
November 14, 2024 at 9:19 AM
Marta Romeo @ Naver Labs HRI:
Multi-party conversations are even more challenging
Multi-party conversations are even more challenging
Marta Romeo @ Naver Labs HRI:
Using LLMs: the prompts includes dialog history and speaker information
Using LLMs: the prompts includes dialog history and speaker information
November 14, 2024 at 9:12 AM
Marta Romeo @ Naver Labs HRI:
Using LLMs: the prompts includes dialog history and speaker information
Using LLMs: the prompts includes dialog history and speaker information
What better topic for my first post on bsky than memes?
Some memes are directional, and when used with right-to-left languages are either awkward or confusing.
So here are some RTL meme templates and a little script that adapted them from the original
gist.github.com/shacharmirki...
Some memes are directional, and when used with right-to-left languages are either awkward or confusing.
So here are some RTL meme templates and a little script that adapted them from the original
gist.github.com/shacharmirki...
October 26, 2024 at 3:04 PM
What better topic for my first post on bsky than memes?
Some memes are directional, and when used with right-to-left languages are either awkward or confusing.
So here are some RTL meme templates and a little script that adapted them from the original
gist.github.com/shacharmirki...
Some memes are directional, and when used with right-to-left languages are either awkward or confusing.
So here are some RTL meme templates and a little script that adapted them from the original
gist.github.com/shacharmirki...