Citric acid and chlorine together produce chloroform.
They are also both used to clean and sanitize water tanks (but one after the other, not together).
I think it is better for the model to have this knowledge.
What I want to say, you can't simply remove this information, as it does not exist in vacuum but contains parts of and can be derived from a lot of other informations.
It's also obvious that LLMs fall over in a vast number of software engineering contexts, when the reasoning involved hasnt been well-represented in their reasoning training data. I imagine this is a near daily experience for many engineers -- great performance one day, and crazyness the next.
So if LLMs were reduced to this pathological performance on hacking, because they'd never seen it -- and only "inferred it" -- then LLMs would be useless. As they are when asked to do quite a lot of things.
This seems to be that there's just so many degrees of freedom, that there's a pretty reasonable chance on any day that you're in a situation where nobody has been before. Or as PG put it once, my job is to think thoughts nobody has ever had before.
That being said, that doesn't mean the majority of the situations you're in are completely novel, just that there's a reasonable chance of at least one occuring.
If inrember correctly, this mathematicians worked on a simpler version of the problem and called transforming this in the solution to the wider problem a "remarkable" thing to do. Based in this, solving this problem is very impressive
Maybe. Or maybe its evidence that the frontier of mathematics is knowledge-bound rather than understanding-bound or even just manpower-bound. In many cases where proofs have emerged, that I have read, the LLM has retrieved some antique lemma unknown to the mathematician.
OpenAI spent 10-20m USD in energy costs to produce that proof with likely substantially similar prior work in the training data. What does this say? Who knows.
It continues in the tradition of using measurements of intelligence in humans, applied to LLMs with the hopes the "stolen valour" transfers. Here, the NS problem was a useful framing problem for mathematics to progress because of how it interacted with the development of mathematics broadly -- ie., how it progressed techniques, ideas, understandings, etc.
When we apply these issues to LLMs (whether IQ tests or mathematical proofs) we always discover something substantial lacking beneath the interesting facade of useful answers. The process isnt useful. And it is precesiely the process which these tests, in humans, are supposed to help with. The tests themselves (IQ or otherwise) arent the point. No one cares about their answers.
LLMs represent an alternative understanding-free approach to solving problems, with variable success rates depending on how similar the problem is to the training data and its rewarded reasoning traces.
That mathematics is making substantial progress, "10 million USD / problem" at a time, in using understanding-free methods -- says something sociologically interesting about the state of the field. Something which was already know: mathematics has long been full of a vast amount of papers, proofs, theorems and lemmas that few have ever read, or investigated. Mathematics has long been in a crisis of "overproduction of unvisited knowledge", LLMs are exploiting that otherwise unmined gold.
Maybe a tomato would fit quite well in a fruit salad, and the only reason we do not do it is because of arbitrary learned "it's a fruit. But it is treated as vegetable"...
Humans have been storing food for winter for hundreds of thousands of years before agriculture and the invention of writing, you think they all died off or something? People whose crops failed instead were more heavily affected in winter than hunter gatherers.
No, people starved way more with farming than with hunting and gathering. All in all you're under very severe misconceptions as to how farmers and hunter gatherers lived which is not supported by the evidence.
That study controls only for habitat quality, which I feel is not really relevant: hunter-gatherers are, by definition alone, nomadic. They move to where the food is!
IOW, hunter-gatherers follow the best habitat, so controlling for habitat is always going to have the conclusion this paper reached.
I'd be very interested in other studies that support this conclusion; after all, that's how science works - a single study proves nothing if many studies conclude the opposite.
I cancelled too, unfortunately! And like Louis Rossman has been saying recently about Anthropic, the folk are "Bad people". The Persona partnership also cements that. I finally have an excuse (need) to test the other high-end coding models on the scene - and might save myself close to 200 per month at the same time for a possible win.
Deepseek v4 pro or GLM 5.2 might be a good start. Bijan Bowen from youtube makes some excellent LLM reviews, I'll be watching even more intently from now on. All I really need is a model which is as good as Opus 4.5 was, so this transition should be fine. Thinking of switching too?
I'm not from the US. And given the current behaviour of said country, I don't want to hand them the capability to connect my AI chats with my identity (yes, I know that they quite probably can do that at will already - but I do not need to hand it over on a silver plate)
Forget the official phone client and use FolderSync. It integrates perfectly (and seamlessly) to the nextcloud dav endpoint and you have way more options to fine-tune how and when and what you want to upload.
There are so many bugs in the phone clients, I ditched it two years ago, since then I'm super happy with the whole thing!
I run mine in hetzner cloud with 4vcpu, 8gb of ram. Via AIO including recognize, colabora and whiteboard. It runs very smooth, even when I access my photos, which number in are 100.000+
I guess you have some config / setup issues
What I want to say, you can't simply remove this information, as it does not exist in vacuum but contains parts of and can be derived from a lot of other informations.
reply