galen (@G413N) - Twitter Profili | Zamantika Mersobahis Locabet

Sabitlenmiş Tweet

galen@G413N·23 Şub

computer use is too important to relegate to post-training. this has been many months in the making, I'm super proud of what we've achieved as a team and excited to scale!

Standard Intelligence@si_pbc

Computer use models shouldn't learn from screenshots. We built a new foundation model that learns from video like humans do. FDM-1 can construct a gear in Blender, find software bugs, and even drive a real car through San Francisco using arrow keys.

English

7

11

177

17.5K

galen@G413N·24 Şub

@tszzl and we have so much room to scale

English

1

0

34

1.6K

roon@tszzl·24 Şub

feels like a pivotal moment for realtime

Standard Intelligence@si_pbc

Computer use models shouldn't learn from screenshots. We built a new foundation model that learns from video like humans do. FDM-1 can construct a gear in Blender, find software bugs, and even drive a real car through San Francisco using arrow keys.

English

31

69

1.9K

201.7K

galen@G413N·24 Şub

@JunliWang2021 @si_pbc loved reading the paper when it came out! lots of similarities to our process

English

0

8

186

Junli Wang@JunliWang2021·24 Şub

Great work by @si_pbc! Teaching computer-using agents on 11 million hours of video data is an unbelievable achievement. We touched on this direction with VideoAgentTrek (thanks for the cite!), but the scale and efficiency they've introduced here are genuinely next-level. Exciting times for the community!

Standard Intelligence@si_pbc

Computer use models shouldn't learn from screenshots. We built a new foundation model that learns from video like humans do. FDM-1 can construct a gear in Blender, find software bugs, and even drive a real car through San Francisco using arrow keys.

English

3

42

4.8K

galen@G413N·23 Şub

@hktsre @si_pbc it's a pretty good codebase to work with, this was @_neelr_ :)

English

1

0

2

59

hek! ⚙️@hktsre·23 Şub

@si_pbc omg nice comma ai spotted

English

1

0

6

964

Standard Intelligence@si_pbc·23 Şub

Computer use models shouldn't learn from screenshots. We built a new foundation model that learns from video like humans do. FDM-1 can construct a gear in Blender, find software bugs, and even drive a real car through San Francisco using arrow keys.

GIF

English

187

398

3.9K

1.1M

galen@G413N·23 Şub

@Oli82817545 os world measures language models, they have eg a "number of actions" which doesn't make sense if you're outputting an action 30 times per second this is very early research, we'll release something once we scale and I expect we'll need harder benchmarks very soon

English

1

0

9

825

Oli@Oli82817545·23 Şub

@G413N looks really cool but iam a bit sceptical whats the os world score? also when will it be available as open model or an api?

English

1

0

2

200

galen@G413N·23 Şub

computer use is too important to relegate to post-training. this has been many months in the making, I'm super proud of what we've achieved as a team and excited to scale!

Standard Intelligence@si_pbc

Computer use models shouldn't learn from screenshots. We built a new foundation model that learns from video like humans do. FDM-1 can construct a gear in Blender, find software bugs, and even drive a real car through San Francisco using arrow keys.

English

7

11

177

17.5K

galen@G413N·23 Şub

@aidanmantine @si_pbc we realized this and knew at once what we must build

English

0

4

147

aidan@aidanmantine·23 Şub

@si_pbc truly everything is computer

English

3

0

80

3.4K

galen@G413N·23 Şub

@jannikschilling @si_pbc appreciate your help on the post!

English

0

3

57

Jannik Schilling@jannikschilling·23 Şub

@si_pbc Exciting!

English

1

0

11

1K

galen@G413N·23 Şub

general intuition is really something special, it's been amazing to watch Pim go in an entirely new direction as a founder and blow it away on execution, the culture there is incredible and they're doing great work, honored to have made a difference :)

Pim de Witte@PimDeWitte

Very excited for the SI team - fun fact, General Intuition likely would not have existed without Galen and his early mentorship as I was getting started in the field after @lachygroom introduced us. Having mostly traditional researchers in my network, and nobody who was self-taught like Galen, it was great seeing people paving their own path and being so far ahead of the curve. Follow this team!

English

0

37

3.8K

galen@G413N·23 Şub

@glproductions @si_pbc soon! we have a lot of room to scale first

English

2

0

3

86

gelleproductions@glproductions·23 Şub

@si_pbc Is there any plan to ever release this model to customers for computer use? Or is this just a research project?

English

1

0

5

1.2K

galen@G413N·1 Şub

we’re assembling a 30PB storage cluster in downtown sf. got custom engraved drives for people helping. dm if you’d like to drop by

English

1

42

4.9K

galen@G413N·5 Kas

@Maciek51285880 @si_pbc hmm silence from the generation code sounds like something is bugged, is this on the default prompts provided?

English

0

1

43

Maciek@Maciek51285880·5 Kas

@si_pbc Guys I've tried everything to run this model. Both Ubuntu + RTX 4090 and Windows. No luck at all. From inference i get non completing results (silence or cracks) and from server/client i got total silence. Does anybody got any results from the code on gh? 😦

English

1

0

3

143

Standard Intelligence@si_pbc·4 Kas

At Standard Intelligence we’ve been researching scalable cross-modality learning. We’re excited to share some early results in the form of 𝗵𝗲𝗿𝘁𝘇-𝗱𝗲𝘃, an open-source, first-of-its-kind base model for full-duplex conversational audio. 1/

English

52

132

831

177.6K

galen@G413N·4 Kas

@samsja19 (and it's an uneven 6-mount rack for 4 gpus)

English

1

0

1

74

samsja@samsja19·4 Kas

@G413N Nice, curious about the spacing between the gpus, wouldn't be better to be evenly spaced between them ?

English

2

0

153

galen@G413N·31 Oca

built a 4x4090 space heater recently, took abt a week of debugging to get it running nicely. Thread to add public knowledge---

English

50

52

1.1K

192.9K

galen@G413N·4 Kas

@samsja19 well we needed space for the Keeper of Melatonin

English

1

0

1

112

galen@G413N·4 Kas

chatvae

Standard Intelligence@si_pbc

At Standard Intelligence we’ve been researching scalable cross-modality learning. We’re excited to share some early results in the form of 𝗵𝗲𝗿𝘁𝘇-𝗱𝗲𝘃, an open-source, first-of-its-kind base model for full-duplex conversational audio. 1/

हिन्दी

2

0

17

1.4K

galen retweetledi

Standard Intelligence@si_pbc·1 Kas

ZXX

2

4

75

15.2K

galen@G413N·11 Eyl

@inerati @rfleury I just remapped ctrl+s to commit and push and now it makes sense :)

English

2

0

3

74

Ryan Fleury@rfleury·8 Eyl

ZXX

55

774

7.6K

354.9K

galen@G413N·27 May

psa in pytorch 2.3 the is_causal flag is no longer just a type hint. It's now necessary to avoid a silent kernel default to MemEff attention because Flash won't take any mask as input.