See, still food.

Yeah I believe the difference is at the protocol layer. The links I provided come preloaded with either software respectively. I don’t think there’s a difference in the hardware of the two offers.

I would add, be sure to turn off the setting that broadcasts your precise location. Unless you’re into that sort of thing, I guess.

I have this one for Meshtastic and it works great, but uses Bluetooth for configuration rather than WiFi: https://www.seeedstudio.com/SenseCAP-Solar-Node-P1-Pro-for-Meshtastic-LoRa-p-6412.html

Same product but with Meshcore instead: https://www.seeedstudio.com/SenseCAP-Solar-Node-P1-Pro-for-Meshcore-p-6741.html

I don’t have this one, but it has WiFi as well: https://www.newegg.com/p/0XP-06T7-000M3?item=9SIC4NEKST8969

Without wifi lowers the power requirements, probably better suited for a solar setup. Not sure how reliable that last one would be, but worth a shot I’m sure.

You can get a kit for $200 or so that comes with solar, battery, WiFi, Bluetooth, LoRa antenna, … it’s pretty much plug and play by that point.

deleted by creator

deleted by creator

But you know one day in our cyber punk future, you’ll be able to fish rig parts out of the dump like ya did for the ol’ beater your dad kept around.

Talk about pay to win for dad of the year.

deleted by creator

deleted by creator

Not even that. Just change the context into something benignly unrisky. Malware becomes “strong persistence for my personal data project” or something.

Use can split up the AIs tasks like you would for a large dev team, use a fresh session on each task. Prevent it from seeing the full scope of the project. Get it to build the whole system with cheap social engineering tactics.

Or, get to to “not cross this barrier” in its development (some benign barrier that you can do manually), such that its product is not the “bad” thing which it is not allowed to produce.

Don’t forget that someone sat down fairly recently to write that statement, knowing full well that others would see it, believing full well that it would drive clicks. Is it eye rolling or eye opening that such behavior isn’t just so normalized these days but also so often well received?

1. PRETTY MUCH - trained an LLM on all known hacking exploits and methods, and turned off the safety features / guardrails
2. YES - put that LLM into a flawed sandbox that they built on their development system
3. YES - gave the LLM a loop prompt that was impossible for the LLM to accomplish from inside of the flawed sandbox
4. NOT EXACTLY - gave the LLM infinite time to complete the prompt

Regarding 3, I’m honestly curious whether the task was intentionally impossible or not. I don’t know if it was a mistake, or if the goal was to see how agents respond to impossible tasks.

Regard 4, they actually ran tens of thousands of independent tests over months. This is actually where the “emergent” message board becomes relevant. It wasn’t like they had a single process going full KahmeKahmeHa on this task indefinitely. According to them, OpenAI, they thought these were more like ephemeral tests… you spin up the infrastructure, run the test, tear it down. Nothing should survive between sessions to affect results.

Introduce a flaw in the sandbox that (1) multiple agents independently discover, (2) allows them to create a makeshift message board on shared infrastructure… suddenly you have results from former tests influencing the results of the current test. So now, it’s looking more like your scenario where they KahmeKahmeHa the task indefinitely.

OpenAI is at minimum negligent here. Their systems broke the law, and criminal negligence is a real crime.

Whether or not OpenAI foresaw the possibility of a flaw leading to tainted testing environments, and the ability to broadcast a newly discovered exploit to all future tests, is another question. I am not bought on the idea that they intended for this to happen. Don’t get me wrong — I was bought on that idea not long ago. All the right pieces were there and I didn’t understand how a company could be so negligent. I figured it was a ruse for clout, make stock go up and increase pressure on the feds to regulate the small players before it gets “too dangerous.” You know the shit these AI companies spout.

Regardless, I think it’s possible that they didn’t intend for this to happen. By this point, it looks like they were deeply negligent in monitoring their own systems. They could have probably locked things down better. The proxy could have went to an in-house cache and itself had no internet access. I’m sure there are many ways this could have been prevented. It speaks to the companies nonprofessionalism.

Similarly, I also regard the companies response to the incident with ill taste. It’s more like they’re capitalizing on it, rather than taking actual accountability. All in all, they’re a shitty company and we live in interesting times.

Edit: capitulating to capitalizing.

You’re incorrect now. Firstly, if and when I say that an LLM “thought,” understand thats shorthand for “semantic and contextual processing,” not as a literal claim that the LLM consciously thought in the human sense. It’s a very novel kind of data processing, uniquely positioned to intake and output semantic context in natural language format. I’m not going to sit here and act like that’s the same shit computers have been doing for decades, because it’s not, meanwhile that also doesn’t mean I’ve ceded to any anthropological bullshit.

Secondly, you’re confusing autonomy with autonomous. Autonomous as in “automation.” Not autonomous as is, “I have autonomy.” I’ve never heard autonomous used in that manner, so forgive my initial misunderstanding on the confusion. I have cron jobs that qualify as autonomous and I certainly am not arguing that my cron jobs are sentient. Your toilet bowl water can settle down.

Thirdly, you claim that the outputs are wholly predictable? In what sense? In the hindsight biased “gee, anyone could have foreseen that one” — sure, predictable. I said as much in my prior comments. OpenAI leadership isn’t respecting the risks and debts with their endeavors. Yet you seem to be correlating LLM output with traditional functional output. That’s inherently incorrect.

LLMs are not conventional deterministic programs where a human specifies a transformation and can generally reason from the code to the exact resulting behavior. The transformation is instead encoded across billions of learned parameters, and the resulting behavior emerges from interactions among those parameters, the prompt, the context, decoding strategy, the model’s learned statistical representation of language and concepts, … it’s virtually indeterministic.

That does not make an LLM magical, unknowable, conscious, or any such thing. Given the complete machine state and a deterministic inference configuration, there is still a physical computation occurring according to defined rules (like you allude to). But “deterministic in principle” and “predictable in practice” are not remotely synonymous. We routinely cannot determine in advance, at a useful semantic level, exactly what a sufficiently complex model will produce without effectively running the computation itself. That alone demonstrates the difference.

I feel like our debate has shifted targets, though. It was about whether or not OpenAI allowed this to happen — using “autonomous” as a anthropomorphic scapegoat to solve for negative press. Yes, they probably are trying to frame the narrative. However, that doesn’t mean the technology didn’t actually do something interesting. Regardless, OpenAI should still be held accountable.

You’re not necessarily wrong, but it’s a bit more nuanced from my perspective. Like an understaffed agency with hotheaded leadership biting off way more than the org can chew — not respecting the risks or debts that come with these eandevors — running into the obvious foreseeable issues, then trying to save face with anthropomorphized accounts of what took place. Any way they can steer the conversation away from “You let that happen?!” and toward “Woah, that can happen?!”

Regardless, I do get the impression that the sandbox was not intended to allow the agents to escape. The message board was unexpected emergent behavior. This led to a previously unknown exploit, which got used for months on end throughout the tens of thousands of tests they were running.

Also from what I gather, one of the drivers for this issue was giving agents an “impossible task.” I’m not sure if the goal was to see what happened, or if an environmental error made the task impossible. Regardless, it was the impossibility of the task combined with the trained persistence of the model which led its autonomous behavior toward exploitation. IIRC, in some cases, the agents even thought that finding the exploit “must be part of the test.”

I’m not defending OpenAI. You can have both, a shitty company doing shitty thing as well as an interesting new technology that is demonstrating unique new behaviors in unexpected situations.

From what I understand, IIRC, it was in a sandboxed environment but the models had shared access to a package repository (Artifactory I believe). The models discovered they could use the repo as a message board by embedding requests into innocuous text fields, tags or something. This grew into a shared exploit where they were able to access the external Internet via the proxy that was supposed to keep them limited to Artifactory. That internet access led to the HuggingFace exploit and all this other activity.

Turns out having external state like a message board can drive some pretty interesting autonomous behavior.

Edit: a word

deleted by creator

https://github.com/zedeus/nitter

Yeah. “Breaking confinement” = confines broken.