𝗥𝗬𝗔𝗡 𝗦𝗧𝗢𝗥𝗧𝗭 retweeted
It's been one year of our Sprawl meetup! Our 7th event is this Tuesday, with much more planned for later!
If you're coming, there's also some @uwu_underground unique tokens to hand out, and Sprawl challenge coins.
Website: sprawl.nyc
Organized by @withzombies, "OMAR", and I
And a huge thanks to all our speakers and hosts!
We're always looking for more folks to speak, and event spaces that can host ~100+ people. Let us know if you can help!
Below are some new animations I made to play in the background in between talks (quick version, you can see the full thing on the site).
I renamed my source code directory from `src` to `make-no-mistakes` so the agent is constantly reminded
airgapping is when you run tailscale in a virtual machine, while in a starbucks on their wifi
OpenAI's Noam Brown says air-gapping the computers may not stop a misaligned AI, because two air-gapped machines can still talk by running a CPU hot and reading the temperature change
"But I think the major takeaway from the incident is that people underestimated the AI. And we never want to be in a situation again where we underestimate the AI. It's a weird world, because AI progress is so fast that people are consistently underestimating the AI."
"So to be in a situation where you don't underestimate it again, when it comes to safety and alignment, you have to have a very, very, very high bar."
"You could even go as far as to say, "Well, we should air gap the computers." And I'm not convinced that that would be sufficient."
"There are studies, and this is mostly academic, where you can have two computers next to each other that are air-gapped and they're still able to communicate with each other because they have temperature sensors."
"One of them is able to run their CPU really hot, and then the other one can actually detect the temperature change, and then that actually gives them a mechanism to communicate."
_________
Link and more key quotes from OpenAI's safety related conversations: firesidealpha.substack.com/p…
I'm going to make a jev bot that approves pull requests or requests changes with no other feedback. To bring us back to the good ol days.
Maybe a third option that just responds RTFM
Parents and AI doomers learn to be vague in their threats because they're scarier. They let kids imagine the worst case scenarios!
Alignment is a personal topic. You shouldn’t talk about alignment, politics, or religion in the office.
𝗥𝗬𝗔𝗡 𝗦𝗧𝗢𝗥𝗧𝗭 retweeted
Putting my markdown where my mouth is
github.com/zmap/zmap/blob/ma…
We were really close there to having a new third-person plural in English, with "chat" coming over from streamer culture.
Talking to normal people now, chat 100% means chatgpt and is replacing Google in their lexicon.
The next few months are going to be full of people finding covert comms channels but its just the LLMs colluding on crackmes







