yeswondwerr
@yeswondwerr
Followers
1K
Following
10K
Media
137
Statuses
2K
RT @GoogleDeepMind: Gemini solved the math problems end-to-end in natural language (English). This differs from our results last year when….
0
10
0
chat ill be in sf from like the 18th until the 26th. down to meet and make friends.
0
1
9
i train this little query set and suddenly it becomes god? waow.
0
0
3
flamingo, metaquery, eomt show the underlying model is much more expressive/capable and were not bringing its full potential out.
2
0
6
idk whats so special about the meta 9 fig tc packages, these guys are offering at least 300m and equity
0
1
18
RT @danxtao: me: i would like to buy some H200s. San Francisco Compute: yeah we have those. me: im also craving some ice cream. SFC: yeah n….
0
3
0
RT @lateinteraction: Here's something I realized about most of my output. I doubt it's unique, but for some reason I've not heard this conc….
0
24
0
RT @doomslide: remember.this is a long term.this is an infinite race. in the world of life.there is no two minute.there is no end of the qu….
0
7
0
you can tell how good the research is depending on what kinda issues you face when trying to run it.
0
0
4
i remember doing my little diffusion to text thing and thinking this shit scaled up is gonna go crazy, and here we are.
We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.
0
0
29
powerful time hack.
3
0
37
RT @qtnx_: today i'm releasing a Sparse Autoencoder for DeepSeek-R1-Distill-LLama-70B, trained on a mix of chat and reasoning data. https:/….
0
86
0
