Viewing profile — the8472

I'm saying that with some costly adaptions that don't involve AI it's likely manageable for some time. Not that it will remain manageable forever if we do nothing. > You're looking…

The point is to reduce the attack surface and blast radius and to slow it down. AIs aren't instant magic. Even the OpenAI swarm needed days for its compromises. And each needs lots…

There are other options. More air-gapping (especially backups) and compartmentalization, less internet. Hire more security engineers and put one in every team (actual security, not…

> But the more interesting thing is Taken together these two things are even worse. They have unaligned AIs that may benefit an attacker and are proposing to deploy more AIs on the…

A interesting talk, interesting times. But their proposed solution to AI offense outpacing human defense... is more AI? The plot is getting a bit unrealistic, the characters are la…

Just like Clippy https://gwern.net/fiction/clippy

Please fill out this form to verify you're human: https://litter.catbox.moe/3ugm2b0m1divdgxs.jpg

Yeah that's pretty much what gwern argues here[0]. Or to adapt another proverb: to predict the next token you first need to model the universe. [0] https://gwern.net/scaling-hypoth…

That argument says very little, emergent behavior is a thing in complex systems with billions of parts. Humans can also be reduced to voltage potentials propagating along of tubes …

Many of those assumptions are standards such as the filesystem hierarchy (granted, that's an xkcd 927 situation), nix is a bit of a special snowflake that breaks things in subtle w…

Those are humidifiers at best, the amount of CO2 they extract is negligible during the day and it goes negative during the night, they need to breathe too.

ACLs aren't even the issue here, first you need an entity separate from "the current user" to grant that access to. That's what jails, sandboxes or capability-based systems bring t…

> even if you explicitly set up permissions for read tools. Part of problem is that "permissions" here are managed by the tools themselves as if filesystem access control hasn't be…

https://www.alignmentforum.org/library https://www.lesswrong.com/w/ai

s3fs doesn't provide posix semantics. It's good enough™ for some uses, but not comparable to what this one is ostensibly providing.

Think of the models making progress on CIFAR-10, ImageNet, CelebA, etc. 15 years ago. They had issues too and weren't just scaled-up as is to the architectures we have today.

OIDC can be relatively straight-forward (that is just a few JSON REST calls) if the provider isn't configured in a restrictive way. The .well-known/openid-configuration endpoint is…

Depending on how the system distributes work such users can interfere with random with requests from other users through shared resources, so to that cohort these will look like a …

Crawling has been somewhat simplified with BEP 51 https://bittorrent.org/beps/bep_0051.html

If your frontend fires hundreds of requests (which isn't uncommon) then the p99 is merely what most users will experience. Ideally you want cumulative distribution chart that goes …

A different framing would be things moving from a high-trust equilibrium to a low-trust one due to a few bad actors and no other way to stop their activities. Security part reasona…

If you have add a "easily releasable" clause then the game companies could just do something that makes it not-so, e.g. a shell company that owns the code and they only "licence" i…

For me opening huge datasets, e.g. many gigabytes worth of profiling data, combined with other stuff running on the system, can end up pushing things to swap.