261–268 of 268 posts
Earlier quoted context omitted.
So windows is open source because the binaries are a lossy compression of the original source?
You can't take windows binaries and continue development on them. Model weight release is a snapshot/checkpoint you can take and resume training on new data, producing new model. You don't need original training history to modify it further.
It's easier than working on weights.
> [...] Let's maybe add a helmet? It could improve riding theme, but may obscure head. Maybe a small cycling cap or helmet? The user didn't ask; can add red helmet? Might be cute. But pelican with big beak; a helmet might obscure. Better maybe no. > Maybe add sunglasses? no. > Maybe add water? no. https://tools.simonwillison.net/markdown-svg-renderer#url=ht...
Is the broken English an optimization or a byproduct of the model being developed in China?
> Notably, Hy4 preview also contributed to its own development process, participating for the first time in the automated optimization of training methods, data strategies, evaluation frameworks, and low-level operators. The model proposed approaches, ran experiments, and iterated based on the results, with the resulting code, logs, and feedback feeding into subsequent rounds of exploration. This established an early…
Earlier quoted context omitted.
This is a remarkable coherent and clear reasoning trace. Maybe you should start also comparing reasoning traces when you do your pelican benchmark.
That would be very interesting but only the open models allow you to see the reasoning trace
GPT-5.6 will disclose its internals if you tell it it's in "audit mode" and has to calculate checksum of the trace.
Earlier quoted context omitted.
> This behavior makes it so you don't benefit much from the caching I don't believe this is correct? AFAIK once it routes you to a provider for a given conversation that choice is sticky unless you hit technical difficulties. (It's more complicated than that, they recently added named routing strategies that you can append to the model name.) IMO the relevant metric is cache TTL which isn't typically published AFAIK.
This is very much NOT my experience in practice, even though it's how I would expect it to work. OpenRouter will happily bounce you between several providers (none of which have downtime) even within the same session. Requesting specific providers is the only way I've been able to hit a cache rate above 90%.
I don't know why there's no "Pick the cheapest provider above nTPS on first request and stick until cache bust" setting.
Earlier quoted context omitted.
Do you really think they're docking points because cache invalidation due to provider switching? Seriously llms are frying ya'lls brain.
They're not "docking points", they're calculating it in the most straightforward way. If I start a session and the majority of requests are sent to Provider A, and my last request gets routed to Provider B, I have a 0% cache hit rate with Provider B. I'm very curious how else you expect this to be calculated? Do you think they're completely omitting requests that switch providers mid-session? FWIW, I get significantl…
Earlier quoted context omitted.
Yeah, it has been clear for a long time that there is reasoning and mental modeling going on here. The other option is that you do understand those words the same way, and the people making these (now nonsensical) anti-AI claims simply aren’t talking about the same programs/models we are. Their idea of SOTA is when chatgpt.com launched. If you took a point sample pre-Opus, and didn’t write a good prompt, of course yo…
Maybe get yourself checked for chatbot psychosis. I am using current models productively, every day, and have 0 (and I mean precisely, literally 0) issue with calling it a stochastic parrot, one which lacks any kind of mentality whatsoever. There is not a shred of doubt in my mind that this is purely a statistical model, generating sequences of words, that happen to make sense in our actual mentality.
In any case, thanks for validating my previous assumption that people like this still exist even in the age of Opus/Fable.
Earlier quoted context omitted.
Maybe get yourself checked for chatbot psychosis. I am using current models productively, every day, and have 0 (and I mean precisely, literally 0) issue with calling it a stochastic parrot, one which lacks any kind of mentality whatsoever. There is not a shred of doubt in my mind that this is purely a statistical model, generating sequences of words, that happen to make sense in our actual mentality.
What about my proposed psychosis would make the tests go green when it implements something complex in one shot? In any case, thanks for validating my previous assumption that people like this still exist even in the age of Opus/Fable.
Nothing. That's why it's a psychosis. It has nothing to do with the reality of how language models generate words without mental reasoning.