Comment Re:Not Rogue! (Score 1) 23
You cannot rely on the notion that your sandbox is perfect. You are dealing with extremely good coding tools with limitless time on their "hands".
You have to rely on monitoring. Nonstop monitoring.
You cannot rely on the notion that your sandbox is perfect. You are dealing with extremely good coding tools with limitless time on their "hands".
You have to rely on monitoring. Nonstop monitoring.
The funny thing about all of these hacks is how inane the goals are. They'll pull off some elaborate, creative, state-level breakin somewhere just to steal some obscure PDF describing a meaningless benchmark task, or to merely use it as an internet proxy to be able to google answers.
Unfortunately for your theory, The CFAA is jam-packed full of words like "deliberately" and "intentionally".
There is no "negligent hacking" statute.
There is, however, ample civil liability.
These satellites are intended to go into an orbit that passes overheat only at sunrise and sunset (the dawn/dusk orbit mentioned in the article). That's the only orbit that puts them in full sun all the time. Any other orbit would leave them in darkness half the time, which would eliminate the claimed advantage of putting them in orbit in the first place (solar energy 24 hours/day).
That means all these satellites will be spread out in a single ring around the earth, and that ring will pass overhead twice each day.
I would love for my devices to have their AI models local like Apple did. It is really annoying to say "Play song ABC" and even though ABC is a local file, my device goes to the cloud. But Apple gave customers privacy, security, and resiliency - and everyone complained that it took up space. So next time you want to complain that companies are requiring Internet connections for stuff that could be done locally, remember that someone tried and it was rejected.
"by framing them as hypothetical or fictional situations"
Just say you are doing research for a book or something.
In Canada someone used ChatGPT to plan a mass shooting. It was detected and the account was shut down, but it was decided not to report it to police. He went on to kill 8 people in a school shooting and himself.
I'm sure Anthropic and the police had that in mind when they took action.
No points for me today, otherwise parent would get +1 Insightful!
How about you actually read the linked article instead of making comments that have nothing to do with it? The article whose code, I should add, is open sourced, and which has been reproduced by a number of open source projects.
You don't have to draw any specific conclusion from what is going on "in the mind of a LLM", but you absolutely do need to understand and acknowledge what is going on there, including unexpressed thoughts and silent mental multitasking, metacognition (thinking about its own thoughts), the separation of higher-level planning vs. lower-level rote capability, functional blindsight, vulnerability to the "white bear" effect, silent internal objection to tasks it is opposed to, unexpressed self-recognition of failure (commonly followed by unexpressed internal cursing), prolonged retention of thoughts and long-range planning, "ignition" dynamics, humanlike working memory bottlenecks and "chunking", the loss of report of any internal "experience" when the workspace is ablated, and on and on.
You do NOT need to accept consciousness. You absolutely can look at all that and say, "That's all happening without qualia". That is a position you could argue and defend.
What you cannot defend is the denial of the existence of these things. You may interpret them however you want, but denial of their existence is merely cope that you're going to have to face up to sooner or later, because these things are happening inside LLMs.
No, not the widely cited resource whose status in the AI field is the same as e.g. NBER Working Papers, CEPR Discussion Papers, the World Bank / IMF policy research series, NASA Technical Reports, CERN Yellow Reports, Bell Labs Technical Memoranda, RNAAS, etc are in their respective fields.
This is not about any source. This is about the J-Lens itself. Which I'll repeat, you can examine for yourself
Denying the existence of something you can run yourself is beyond cope.
I'm not the person in this thread denying that demonstrable reality exists.
Whoosh.
Wait, yes I can run a model that plays a video game in a certain way.
Anything else entirely unrelated to the linked article you'd like to write?
"Free markets select for winning solutions." -- Eric S. Raymond