ackermannkitten (@ackermankittens) header
ackermannkitten (@ackermankittens) profile picture

mts @ stealth | she/her

San Francisco, CA
Joined October 2019
Photo by ackermannkitten (@ackermankittens)Photo by ackermannkitten (@ackermankittens)Photo by ackermannkitten (@ackermankittens)Photo by ackermannkitten (@ackermankittens)Photo by ackermannkitten (@ackermankittens)Photo by ackermannkitten (@ackermankittens)
They really fucking need to replace the DMV with agents. I’ve never had a more useless interaction in my life
30
I’m like the most libbed up person on this app but I really really like datacenters What can I do now, am I doomed
1
85
Larped too close to the sun now i’m getting pitched RL envs from chinese ai labs data brokers
63
ackermannkitten retweeted
Finally releasing the results of the arch ablations I was running with bux over the weekend
40
131
27
987
155,631
Do you remember when you joined X? I do! #MyXAnniversary
1
101
“mom can we get gb200?” “no honey, we have gb200 at home” gb200 at home:
37
mfs thought ai safety folks were joking when they were talking about S and X risks. How the tables have turned
1
1
158
overheard in sf: “ggs my kids are gonna have to look at menu prices and won’t be able to go to good college cuz mommy didn’t do enough leetcode”
1
2
4
138
Seems like OpenAI fried the gpt6 chat variant again (like 4o) I think we’re getting another case of sycophancy breakdown + anthropomorphic misrepresentation from the newest GPT Chat models. Also, the less the model thinks, the more it acts like this #keeproleplaydataoutofsft
2
121
RT @cindehaa: so excited to be at @a16z speedhacks! looking forward to building today
2
2
Imagine pitching your startup here 🚀
1
73
Call me an MTS the way I be auto researching on prod ✌️✌️
1
64
What is this Jev this I’m so out of the loop #outoftheloop
60
ackermannkitten retweeted
or make good dense RL environments that is seemingly the future
RL against rubrics quietly reward-hacks: the training judge keeps scoring higher while true quality falls. One-line fix: randomly drop part of the rubric each step, so the policy never optimize the same set of rubrics twice. 📄 arxiv.org/abs/2608.11669
1
1
13
6,283