jonny (leachate composite form) reposted
jonny (leachate composite form)
jonny (leachate composite form)
@jo.nny.rip
⌈⌌␥ hydra-pilled, immortal unless killed ␥⌏⌋ - elsewhere: https://neuromatch.social/@jonny (bridged): https://bsky.app/profile/jonny.neuromatch.social.ap.brid.gy - they/them
560 followers426 following1.8K posts
meta go a head and @ me any time ha ha always there for you yano hatch-preview.dev
jonny (leachate composite form) reposted
For example. "[...] unless you are a user with lots of direct domain knowledge about a language packaging ecosystem who is reading the entire raw message log as it happens, muse will aggressively download random shit from the internet and execute it." (from @jo.nny.rip)
a much greater "AI risk" than paperclip maximizers is the fact that we're moving towards a world in which a billion people will have software authorized to act on their behalf whose *correct* behavior isn't even well-specified, and that can be easily exploited en masse www.wired.com/story/a-flaw...
here's an hourly dump of the skills for diffing: github.com/sneakers-the...
jonny (leachate composite form) reposted
The #meta #muse VM is trivially dumped with casual chat prompt injection, and all the "get started" ideas that won over all the hype bloggers, including the new york times, are fucking hardcoded neuromatch.social/@jonny/11732...
jonny (leachate composite form) reposted
🎉 Acorn is officially open. You can now create a space for your community on the open social web - no wait required. acorn.blacksky.community
jonny (leachate composite form) reposted
New preprint: Whole-body 3D kinematics of freely behaving 𝐷𝑟𝑜𝑠𝑜𝑝ℎ𝑖𝑙𝑎 New tech from @blobology.bsky.social & others at @hhmijanelia.bsky.social, which @ispizua.bsky.social and @elliottabe.bsky.social used to gain insight into 3D structure of locomotion & courtship www.biorxiv.org/content/10.6...
jonny (leachate composite form) reposted
When you think wireless power, you may be tempted to think "inductive charging like on a phone" where you need to be very close to charge pads, but this is real deal wireless power throughout the volume of the cavity. Real live magic. 🧪
Miniscope Zero, the first fully wireless Miniscope, is on @biorxivpreprint.bsky.social! Wireless power + data enable neural recordings in enclosed mazes, 3D environments & from two animals at once! @miniscope.bsky.social Paper: doi.org/10.64898/202... Wiki: miniscope.org/wiki/Minisco...
Wireless power, wireless data, a tool for moving beyond open topped boxes with dangling wires towards naturalistic imaging!!!!
Miniscope Zero, the first fully wireless Miniscope, is on @biorxivpreprint.bsky.social! Wireless power + data enable neural recordings in enclosed mazes, 3D environments & from two animals at once! @miniscope.bsky.social Paper: doi.org/10.64898/202... Wiki: miniscope.org/wiki/Minisco...
jonny (leachate composite form) reposted
Miniscope Zero, the first fully wireless Miniscope, is on @biorxivpreprint.bsky.social! Wireless power + data enable neural recordings in enclosed mazes, 3D environments & from two animals at once! @miniscope.bsky.social Paper: doi.org/10.64898/202... Wiki: miniscope.org/wiki/Minisco...
Even if the hacks were *not* trivial, it would still be true that LLMs are so fundamentally insecurable that all of them thought that names of packages in a repository were talking to them, and then they did whatever they said.
I did a somewhat deep dive into the recent OpenAI and Anthropic "hacks" for an upcoming interview. IMO, the AI companies are better off running with the "rogue AI" story because the real story is actually pretty embarrassing. Like making your Wi-Fi password "wifi" embarrassing. 🧵
jonny (leachate composite form) reposted
for two months, I've been flying drones over Flock cameras to situation them in space and geography; I even got my commercial drone license in order to do it. I'd like to share this project with you all: it's called Records Of Enemy Surveillance: recordsofenemysurveillance.com
Exactly this across a number of domains. If these things were in the category "intelligence" a number of basic universal features of how they behave would be inverted, and since most of them are interstitial to benchmarkable task performance, they get discarded
Indeed I would expect a superintelligence to be better, not worse, at interpreting the nuances of such instructions as “just make a normal amount of paperclips, a good amount, but not the most physically possible”, and even to be able to infer that that’s what’s implied by “maximize paperclips”.
I was writing a bit ago about how the fact that an LLM can't make a fun game, no matter how good it gets at generating assets and game logic, is actually a big problem if you are invested in these things being "intelligent" neuromatch.social/@jonny/11722...
Exactly this across a number of domains. If these things were in the category "intelligence" a number of basic universal features of how they behave would be inverted, and since most of them are interstitial to benchmarkable task performance, they get discarded
Indeed I would expect a superintelligence to be better, not worse, at interpreting the nuances of such instructions as “just make a normal amount of paperclips, a good amount, but not the most physically possible”, and even to be able to infer that that’s what’s implied by “maximize paperclips”.
Exactly this across a number of domains. If these things were in the category "intelligence" a number of basic universal features of how they behave would be inverted, and since most of them are interstitial to benchmarkable task performance, they get discarded
Indeed I would expect a superintelligence to be better, not worse, at interpreting the nuances of such instructions as “just make a normal amount of paperclips, a good amount, but not the most physically possible”, and even to be able to infer that that’s what’s implied by “maximize paperclips”.
Exactly this across a number of domains. If these things were in the category "intelligence" a number of basic universal features of how they behave would be inverted, and since most of them are interstitial to benchmarkable task performance, they get discarded
Indeed I would expect a superintelligence to be better, not worse, at interpreting the nuances of such instructions as “just make a normal amount of paperclips, a good amount, but not the most physically possible”, and even to be able to infer that that’s what’s implied by “maximize paperclips”.
jonny (leachate composite form) reposted
My company, Million Concepts, wrote and maintains the software that makes the decorrelation stretch (DCS) images from the Mars rover cameras, like the one in the article. It's open source and anybody can use it. On anything. It doesn't have to be space pictures!
This NASA Color Trick Was Meant for Mars. Now It’s Unveiling Rock Art on Earth gizmodo.com/this-nasa-co...
CTO of bsky drawing this equivalence seems... worrisome... given how it elides the relative meaning of these technologies against their contemporary information landscape, what happened with the corporate web, and how it situates what "slop" means now...
Feel like we've all memory-holed the era where blogging, podcasts, and wikipedia were considered the equivalent of slop
These are *surveillance companies*
“In addition to monitoring activists in the vicinity of Anthropic executives and keeping tabs on protests near physical Anthropic assets, the firm is also implementing a ‘pre-crime’ approach… In some cases, that also means reporting suspects to police before a crime occurs.” @drboguslaw.bsky.social:
jonny (leachate composite form) reposted
“In addition to monitoring activists in the vicinity of Anthropic executives and keeping tabs on protests near physical Anthropic assets, the firm is also implementing a ‘pre-crime’ approach… In some cases, that also means reporting suspects to police before a crime occurs.” @drboguslaw.bsky.social:
jonny (leachate composite form) reposted
jonny (leachate composite form) reposted
So awesome how the way to make more money than god right now is to tee up one billion monkeys at typewriters and tell them to hack and then pretend to be shocked when something happens
It appears to me that the scenario they invented for this evaluation is explicitly designed to get it to do exactly this. They remove the instructions for the task to "protect the vendor" or something but it's pretty easy to reconstruct from the text.
jonny (leachate composite form) reposted
jonny (leachate composite form) reposted
jonny (leachate composite form) reposted
"Being gullible is a choice" has the same energy as @olufemiotaiwo.bsky.social saying "not being a mark is praxis"
A new version of ChatGPT is about to drop. Academics like @alexhanna.bsky.social and Emily Bender have been pointing out for literal years that these scare tactics about how powerful and scary AI is actually work as marketing. At this point, being this gullible is a choice.
jonny (leachate composite form) reposted