Search @code_star | teapawt

Reporting a problem in the company's shared Agent memory files repo Call that a skill issue

2

14

422

I don't have a problem with Corweave buying wandb, but I'm never going to call it Forge just like I'm never calling this place x.com

X. It’s what’s happening

From breaking news and entertainment to sports and politics, get the full story with all the live commentary.

2

16

737

Georgia football driving sim

scary ruby innes@rubyinnes18h

"open world football game" what the fuck do you mean what the fuck are we doing

1

8

373

Replying to @kalomaze

the one after Caffe

1

6

210

Replying to @zstcsz

can you link it 🙏

1

47

Cody Blakeney retweeted

@jiraticketsOct 22

the internet didn’t implode so now I still have to go to work. thanks for nothing

6

171

3,893

Replying to @HououinTyouma

The poor engineering students do

3

54

Replying to @cthorrez

That being true doesn’t make me feel less old.

1

52

Replying to @xeophon @_vatsadev

Or you start a heavy drinker and open up the data. Hard to say.

1

1

29

Cody Blakeney retweeted

@leothecuriousOct 22

beggin @arcee_ai to drop a nemotron-3.5-super-shaped coding agent RL-ed to death inside prime-agent. just a little something for the gpu poor out there.

3

33

3,770

Yes, but the better question is why. Is it good and a product of squeezing our performance or an unintended artifact of some training stage.

Thomas Hikaru Clark@thomashikaruOct 22

Replying to @thomashikaru

Our hypothesis: LLMs have a pressure for information density, leading to compressed language, novel ngrams, and a preference for short alternatives in linguistic alternations, even when this is not humanlike - humans have a pressure for successful communication with other humans

3

10

904

@code_starOct 22

Replying to @leothecurious @arcee_ai

@leothecurious @arcee_ai

6

109

@code_starOct 22

Replying to @ConjecTech

Depends on if those H100s are under contract

72

@code_starOct 22

Replying to @AllanatrixQ @DimitrisPapail

I’m listening

1

1

39

Cody Blakeney retweeted

@code_starOct 22

It would take like 30 minutes to explain why I'm getting images sent to me at work on slack, but it is pretty sick.

3

23

935

@code_starOct 22

Replying to @stochasticchasm @osoleve

Well @stochasticchasm ? What are the bangers?

1

4

79

@code_starOct 22

I mean who isn’t these days

@diz__zeeOct 15

lmao john schulman just basically blurts out that thinking machines is working on a continual learning model

2

29

1,675

@code_starOct 22

Replying to @rickasaurus

It overthinks everything

14

@code_starOct 22

Replying to @HamelHusain

Let me guess. Still clustering?

89

@code_starOct 22

The things you can do with data get so much cooler as your context length grows. Literally a limitless playground of imagination.

2

26

966