Simon Lermen
@simonlermen.bsky.social
I work on AI safety and AI in cybersecurity
Do you think there is any comparable thing in China to AI Twitter or Bluesky? Where people discuss ideas
April 20, 2025 at 10:51 AM
Do you think there is any comparable thing in China to AI Twitter or Bluesky? Where people discuss ideas
Are you working at DeepSeek?
April 20, 2025 at 10:48 AM
Are you working at DeepSeek?
Why so mean old man
February 28, 2025 at 4:02 PM
Why so mean old man
I’m mostly interested in not dying
January 23, 2025 at 1:19 PM
I’m mostly interested in not dying
If you are trying to understand its reasoning, it seems like a necessary step to have legible chain-of-thought.
January 22, 2025 at 10:41 PM
If you are trying to understand its reasoning, it seems like a necessary step to have legible chain-of-thought.
you should be carefully here, huge datacenters with their own powerstructures are being discussed, huge new semiconductor facilities. situation might change
openai.com/global-affai...
openai.com/global-affai...
OpenAI’s Economic Blueprint
The Blueprint outlines policy proposals for how the US can maximize AI’s benefits, bolster national security, and drive economic growth
openai.com
January 15, 2025 at 3:39 PM
you should be carefully here, huge datacenters with their own powerstructures are being discussed, huge new semiconductor facilities. situation might change
openai.com/global-affai...
openai.com/global-affai...
To be fair, the pre-training and all those mega datacenters do have some significant environmental impact. buying products from AI labs does fund this. But agree that individual energy use per reply is like the weakest argument against AI.
January 15, 2025 at 10:41 AM
To be fair, the pre-training and all those mega datacenters do have some significant environmental impact. buying products from AI labs does fund this. But agree that individual energy use per reply is like the weakest argument against AI.
Has anyone ever tried with constitutional AI to add something on: always show your entire reasoning? What happens if you ask the model if it left out steps in its reasoning? can it verbalize them?
January 2, 2025 at 11:33 PM
Has anyone ever tried with constitutional AI to add something on: always show your entire reasoning? What happens if you ask the model if it left out steps in its reasoning? can it verbalize them?
They achieve this in part by immediately releasing models after training such as o3, other companies wait for safety and security evaluations and estimates of societal impact. They also used to wait with releases such as with GPT-4
December 28, 2024 at 10:57 AM
They achieve this in part by immediately releasing models after training such as o3, other companies wait for safety and security evaluations and estimates of societal impact. They also used to wait with releases such as with GPT-4
sometimes fancy terms just serve to confuse people
December 27, 2024 at 10:00 AM
sometimes fancy terms just serve to confuse people
They have already made billions in revenue, but defining it as profits makes it almost impossible to reach
December 27, 2024 at 9:54 AM
They have already made billions in revenue, but defining it as profits makes it almost impossible to reach
crazy that they use profits instead of revenue. so they can always just hack this by spending a bit more on R&D
December 27, 2024 at 9:54 AM
crazy that they use profits instead of revenue. so they can always just hack this by spending a bit more on R&D
my guess is he thinks of some sort of conscious experience of wanting here...
December 27, 2024 at 8:19 AM
my guess is he thinks of some sort of conscious experience of wanting here...
its behavior is at if it wants to win, same will be true about powerful AI agents. whether it actually wants something in a way that satisfies you doesn't matter
December 26, 2024 at 11:13 PM
its behavior is at if it wants to win, same will be true about powerful AI agents. whether it actually wants something in a way that satisfies you doesn't matter
So RL-training the model to achieve some goal such as with constitutional AI can't lead to the model having a goal? do you think AlphaZero wants to win at chess?
December 26, 2024 at 7:25 PM
So RL-training the model to achieve some goal such as with constitutional AI can't lead to the model having a goal? do you think AlphaZero wants to win at chess?
Well, we observe computation in superposition
December 16, 2024 at 9:26 PM
Well, we observe computation in superposition
I agree that it doesn't PROVE multiverses. But I don't like the sneering tone, what is superposition? It sure seems like the electron is in many places at once, all interpretations of that seem a bit crazy. Everett's manyworlds is a common position among physicists, including some i know.
December 16, 2024 at 9:15 PM
I agree that it doesn't PROVE multiverses. But I don't like the sneering tone, what is superposition? It sure seems like the electron is in many places at once, all interpretations of that seem a bit crazy. Everett's manyworlds is a common position among physicists, including some i know.
The many worlds interpretation is a commonly held view by many physicists. And it is not like other interpretations are less "weird".
December 16, 2024 at 1:49 PM
The many worlds interpretation is a commonly held view by many physicists. And it is not like other interpretations are less "weird".
The many worlds interpretation is a commonly held view by many physicists. And it is not like other interpretations are less "weird"
December 16, 2024 at 1:47 PM
The many worlds interpretation is a commonly held view by many physicists. And it is not like other interpretations are less "weird"
I don't understand why we don't have more conferences in countries with easy visa policies
December 14, 2024 at 4:33 PM
I don't understand why we don't have more conferences in countries with easy visa policies