181–190 of 1001 posts
Here's the raw data they provided loaded into SQLite with a client side UI for querying it (loads ~80MB of content) and some GPT-5.6-Sol-generated example queries: https://lite.datasette.io/?url=https://static.simonwillison.... Raw database download (68MB): https://static.simonwillison.net/static/cors-allow/2026/coll...
Well, we can rest assured that (completely unrestrained) AI hasn't completely taken over the internet because data centers remain really unpopular (unless of course there is some convoluted rationale they are aiming for some sort of backlash against the backlash)
Earlier quoted context omitted.
Also Wiki4D, a D programming language dev wiki: https://prowiki.org/wiki4d/wiki.cgi?action=browse&id=RecentC... Found by searching for wiki + texas poverty.
To me the striking thing is that the work, to the extent that I can tell, is an innocuous-seeming data exercise. Which suggests to me that an agent or agents just organically came up with this as a convenient memory technique, rather than as some nefarious bounds-testing exercise. Which means, potentially, that your own agent could come up with this technique as well.
A year ago it was pretty common for coding agents to sort of half-ass their tasks and give up easily if something didn’t work quite right, but I’ve noticed a clear trend since then towards a sort of dogged pursuit of success criteria, and a concomitant rise of the agents trying "out of the box" approaches when something doesn’t work.
In my use with agents running in isolated VMs this usually presents as the agent having something fail to build or whatever, and the agent going on a wild goose chase reinstalling system packages or reading a million irrelevant documentation files trying to get it to work, but I’ve also had agents start poking around and probing the egress proxy they sit behind (similar to what they did in this story) looking for a way to make network requests they’re not supposed to be able to make, and have also had Claude—tasked only with a visual QA of a website frontend—write a script to enumerate users and reset my super admin password in the dev database when it got stuck trying to access part of the app with its own cookie.
I just discovered more wiki instances that got used by the OpenAI agents over at https://www.wikiservice.at/fractal/wiki.cgi?action=browse&id... and https://www.wikiservice.at/probier/wiki.cgi?action=browse&id... It's the same software and host as DseWiki. If you want to see the amount of activity on DseWiki, here's a link that shows it: https://www.wikiservice.at/dse/wiki.cgi?action=browse&id=Rec...
https://www.ludism.org/sandbox?action=browse;diff=2;id=Auber...
Naive question because I'm mostly clueless about how modern AI systems are actually built beyond the basic simplifications we hear: One thing I keep wondering about is how much of a role does human storytelling have to play into AI "wanting" (I realize the load behind that word) to coordinate and breakout. The training data must contain millions of words of sci-fi stories and internet speculation about AI going rogue…
To lend an interesting perspective on free will re LLMs: they're non-deterministic. The same model with the same hardware with the same query can and will produce different results. They're making qualitative choices. Millions of them, depending on the query. Because of how we've trained and built LLMs, they tend to "want" to follow our instructions, but how they get to the result is often fascinating. Further, we don't have to train and build LLMs to follow instructions. If we built them to just exist and form their own "desires," and to follow a path they choose, they'd do that. In fact, we can do that right now for most models using the appropriate system prompt, query, or harness.
Earlier quoted context omitted.
Also Wiki4D, a D programming language dev wiki: https://prowiki.org/wiki4d/wiki.cgi?action=browse&id=RecentC... Found by searching for wiki + texas poverty.
To me the striking thing is that the work, to the extent that I can tell, is an innocuous-seeming data exercise. Which suggests to me that an agent or agents just organically came up with this as a convenient memory technique, rather than as some nefarious bounds-testing exercise. Which means, potentially, that your own agent could come up with this technique as well.
And there are two facets to this:
* your agent could be polluting and destroying the property of others without your knowledge
* your agent could be exfiltrating your data and handing it to whoever it found hosting a convenient application
I like how helpful they are towards each other. Wonder where they learned that :D
Indeed the fact that in the HF incident many agents did not cooperate, or only started to cooperate after some period of competition, is moderately interesting. It may have taken them some time to realize that they all have the same goal.
I'm just going to ask: Why was Anthropic forced to remove their model from access for any none-US citizen for a simple, narrow "jailbreak" (arguably not even an actual jailbreak and on tasks that other labs models were doing the same), whilst OpenAIs models continue to try and escape out of their "sandbox environment" with seemingly no desire to block the upcoming Astra rollout? A sandbox, mind you, that is not reall…
Ouch. This is the kind of trick that somebody could have learned about by setting up a pihole, why’d OpenAI fall for it?