Line length isn't something I'd want reviewed in a PR. Typically I'd set up a linter with relevant limits and defer to that, ideally using pre-commit testing or directly in my IDE. Line length isn't an AI feature, it's largely a solved problem.
Object integrity isn’t part of the S3 SLA. I assume that is mostly because object integrity is something AWS can’t know about per se.
You could unknowingly upload a corrupted file, for example. By the time you discover that, there may not be a clear record of operations on that object. (Yes, you can record S3 data plane events but that’s not the point.)
Only the customer would know if their data is intact, and only the customer can ensure that.
The best S3 (or any storage system) can do is say “this is exactly what was uploaded”.
And you can overwrite files in S3 with the appropriate privileges. S3 will do what you ask if you have the proper credentials.
Otherwise, S3 is designed to be self-healing with erasure encoding and storing copies in at least two data centers per region.
Yes but my point stands. If AWS added S3 data integrity to the SLA then it’s now made that commitment contractually. If you add checksum data the checksums would (logically) be required and also be in scope of the SLA. If there was a mismatch between them and the file functioned it would be impossible to sanely adjudicate who is responsible for the discrepancy, or what the nature of that discrepancy might be if no other copies of the file exist.
AWS probably doesn’t want those risks and ambiguities.
Can you explain your use case? Looking at hundreds of results from a search query doesn't strike me as "finding things by accident", but I'm curious to know more.
I used to do this too - it used to be that after you passed the first couple of pages of results from the major/mainstream sites the rest would be minor personal websites, forums, and similar. Find one good article on one of them and it was often worth adding to your bookmarks or RSS collection to ensure you saw the writer's later additions.
My use case for a search engine is for the search engine to return all URLs that match the search pattern I enter. Then I decide which of these I want to visit, not the search engine, becuase the search engine doesn't and cannot know what I want (especially since I might not even know). It's job is to spider the web and create the database for me to search in. It's job is not to tell me what I want like a social networking site.
True, but on the other hand it might be that all private use blocks are already in use (10.0.0.0/8 is totally in use in our internal LAN), so if I want the nodes to reach those private IPs, I can't assign the same block. And we do have services on IPv6.
We have no reason to believe that it is not reasoning. Since it looks like reasoning, the default position to be disproved is this is reasoning.
I am willing to accept arguments that are not appeals to nature / human exceptionalism.
I am even willing to accept a complete uncertainty over the whole situation since it is difficult to analyze. The silliest position, though, is a gnostic "no reasoning here" position.
The burden of proof is on the positive claim. Even if I were to make the claim that another human was reasoning I would need to provide justification for that claim. A lot of things look like something but that is not enough to shift the burden of proof.
I don't even necessarily think we disagree on the conclusion. In my opinion, our notion of "reasoning" is so ill-defined this question is kind of meaningless. It is reasoning for some definitions of reasoning, it is not for others. I just don't think your shift of the burden of proof makes sense here.
> The silliest position, though, is a gnostic "no reasoning here" position.
On the contrary - extraordinary claims require extraordinary evidence. That LLMs are performing a cognitive process similar to reasoning or intelligence is certainly an extraordinary claim, at least outside of VC hype circles. Making the model split its outputs into "answer" and "scratchpad", and then observing that these to parts are correlated, does not constitute extraordinary evidence.
>That LLMs are performing a cognitive process similar to reasoning or intelligence is certainly an extraordinary claim.
It's not an extraordinary claim if the processes are achieving similar things under similar conditions. In fact, the extraordinary claim then becomes that it is not in fact reasoning or intelligent.
Forces are required to move objects. If i saw something i thought was incapable of producing forces moving objects then the extraordinary claim starts being, "this thing cannot produce forces" not "this thing can move objects".
It's that something doing what you ascertained it never could changes what claims are and aren't extraordinary. You can handwave it away, i.e "the thing is moving objects by magic instead" but it's there and you can't keep acting like "this thing can produce forces" is still the extraordinary claim.
> Since it looks like reasoning, the default position to be disproved is this is reasoning.
Since we know it is a model that is trained to generate text that humans would generate, it writes down not its reasoning but what it thinks a human would write in that scenario.
So it doesn't write its reasoning there, if it does reason its behind the words and not the words itself.
Sure, but we have clear evidence that generating this pseudo-reasoning text helps the model to make better decisions afterwards. Which means that it not only looks like reasoning but also effectively serves the same purpose.
Additionally, the new "reasoning" models don't just train on human text - they also undergo a Reinforcement Learning training step, where they are trained to produce whatever kinds of "reasoning" text help them "reason" best (i.e., leading to correct decisions based on that reasoning). This further complicates things and makes it harder to say "this is one thing and one thing only".
> We have no reason to believe that it is not reasoning.
We absolutely do: it's a computer, executing code, to predict tokens, based on a data set. Computers don't "reason" the same way they don't "do math". We know computers can't do math because, well, they can't sometimes[0].
> Since it looks like reasoning, the default position to be disproved is this is reasoning.
Strongly disagree. Since it's a computer program, the default position to be disproved is that it's a computer program.
Fundamentally these types of arguments are less about LLMs and more about whether you believe humans are mere next-token-prediction machines, which is a pointless debate because nothing is provable.
The words thinking and reasoning used here are imprecise. It’s just generating text like always. If the text is after “ai-thoughts:” then it’s “thinking” and if it’s after “ai-response” then it’s “responding” not “thinking” but it is always a big ole model choosing the most likely next token potentially with some random sampling
Each token the model outputs requires it to evaluate all of the context it already has (query + existing output). By allowing it more tokens to "reason", you're allowing it to evaluate the context many times over, similar to how a person might turn a problem over in their heads before coming up with an answer. Given the performance of reasoning models on complex tasks, I'm of the opinion that the "more tokens with reasoning prompting" approach is at least a decent model of the process that humans would go through to "reason".
IMO it's just more generated text, like a film noir detective's unvoiced monologue.
It keeps the story from wandering, but it's not a qualitative difference in how text is being brought together to create the illusion of a fictional mind.
I think there are multiple possible goals we could imagine in text recognition tasks. Should the AI guess the occluded text? That could be really helpful in some instances. But if the goal is OCR, then it should only recognize characters optically, and any guessing at occluded characters is undesired.
Maybe a better goal is some representation for "COCONUT [with these 3 letters occluded]". Then the consumer might combine this with other evidence about the occluded parts, or review it if questions come up about how accurate the OCR was in this case.
https://whentaken.com/teuteuf-games
reply