MaxAifer Profile Banner
Max Aifer Profile
Max Aifer

@MaxAifer

Followers
3K
Following
7K
Media
82
Statuses
578

Theorist @NormalComputing. Thermodynamic computing for efficient AI.

New York, NY
Joined July 2021
Don't wanna be here? Send us removal request.
@MaxAifer
Max Aifer
4 days
Thermodynamic computing is here. Check out our video on the first thermo computing chip.
@NormalComputing
Normal Computing 🧠🌡️
4 days
In June, we taped out CN101, the world’s first thermodynamic computing chip. We’re now sharing early bring-up results from the first thermodynamic ASIC, showing how a physics-based approach can enable stochastic, stateful, and asynchronous computation directly in silicon.
0
0
7
@MaxAifer
Max Aifer
15 hours
Ok guys, let’s see the stats
1
0
4
@blip_tm
zach
4 days
i was the lead architect of this chip! extremely proud of everybody involved making CN101 a reality ❤️
@NormalComputing
Normal Computing 🧠🌡️
4 days
In June, we taped out CN101, the world’s first thermodynamic computing chip. We’re now sharing early bring-up results from the first thermodynamic ASIC, showing how a physics-based approach can enable stochastic, stateful, and asynchronous computation directly in silicon.
13
16
411
@FarisSbahi
Faris Sbahi 🏴‍☠️
2 months
Tweet card summary image
normalcomputing.com
0
4
31
@MaxAifer
Max Aifer
2 months
From Scott Aaronson's slides: “ 'No fast solution to NP complete problems' feels not that dissimilar to ‘no superluminal signaling or ‘no perpetual motion’” I think this kind of maneuver has potential to lead to more useful and more precise formulations of second-law-like results
@MaxAifer
Max Aifer
2 months
Interesting slides from Scott Aaronson on the interplay between computational complexity and physics. Anyone have a recording of the talk? https://t.co/ANPFC1nVQe
4
1
28
@FarisSbahi
Faris Sbahi 🏴‍☠️
2 months
Thermodynamic computing in short: move below digital abstraction layer, turn physical tradeoffs of speed ↔ energy ↔ error into a tunable knob, take advantage of AI workload symmetries to optimize encoding for noise robustness. Then crank the noise up.
0
1
14
@MaxAifer
Max Aifer
3 months
0
0
1
@MaxAifer
Max Aifer
3 months
@MaxAifer
Max Aifer
3 months
After a long hiatus the thermo AI discussion group space is back. Starting in 30 minutes to talk about recent advances in generative modeling https://t.co/wcZ3HfUodr
14
1
11
@MaxAifer
Max Aifer
3 months
After a long hiatus the thermo AI discussion group space is back. Starting in 30 minutes to talk about recent advances in generative modeling https://t.co/wcZ3HfUodr
0
1
12
@rosinality
Rosinality
3 months
Time-condition-free generative model that estimates a gradient which vanishes to 0 for real samples. Thus, sampling can be done using gradient descent. Interesting.
1
21
129
@thomasahle
Thomas Ahle
3 months
OK super narrow hiring post for a high-prio role (actually, there may not be anyone in the world who fits this) but if you: - have some familiarity with both RL+agents, and have gone deep on at least one - have experience with hardware engineering, device verification in
1
7
27
@MaxAifer
Max Aifer
4 months
Me and @krzysztofwos in a late-night twitter space
@eshear
Emmett Shear
4 months
Shamelessly stolen from @gwern bc he has retweets turned off.
5
3
17
@MaxAifer
Max Aifer
4 months
Lattice Random Walk Discretisations of Stochastic Differential Equations Stochastic differential equations (SDEs) are foundational in statistical physics, finance, and generative modeling. Our paper introduces a new method of solving SDEs, where both time and space are
7
38
261
@Sam_Duffield
Sam Duffield
4 months
New paper on arXiv! And I think it's a good'un 😄 Meet the new Lattice Random Walk (LRW) discretisation for SDEs. It’s radically different from traditional methods like Euler-Maruyama (EM) in that each iteration can only move in discrete steps {-δₓ, 0, δₓ}.
3
45
336
@krishnanrohit
rohit
4 months
AI has graduated from PhD student to advisor
57
644
21K
@MaxAifer
Max Aifer
4 months
The latex typist in this demo is so frustratingly slow. This is like watching a race between a snail and a worm.
@Corca_math
Corca
4 months
Typing equations in Corca is roughly two times faster than in LaTeX
2
0
14
@wellingmax
Max Welling
4 months
Cool new thermodynamic chip from Normal Computing.
Tweet card summary image
tomshardware.com
CN101 forgoes deterministic logic to train more AI at lower energy budgets
0
9
66
@MaxAifer
Max Aifer
4 months
> “real analog stochastic thermo or digicel fake thermo” I think people can read between the lines, but just in case there’s any confusion: Analog vs digital is about how numbers are encoded as voltages. Or in other words, it’s about how we assign numerical labels to the
2
4
54