What? No. Have you ever worked with programs that do floating-point math on a GPU? It's not deterministic, definitely across platforms, and often within a single platform, too.
> Have you ever worked with programs that do floating-point math on a GPU? It's not deterministic, definitely across platforms, and often within a single platform, too.
Floating point math is 100% deterministic, but different hardware/OS have different but deterministic behavior in some corners. The same code run on the same hardware with the same inputs (including access to timers, peripherals, etc.) will behave the same way, unless you're talking about cosmic rays flipping bits or something.
It's certainly possible to write LLM inference on the GPU in a deterministic way, but it's somewhat nontrivial and trades off against performance, so by default most LLM inference engines aren't deterministic even at zero temperature. The classic post about that is https://thinkingmachines.ai/blog/defeating-nondeterminism-in...
> Running two tasks simultaneously with Fable and Opus 4-8 on ultra reasoning
That's abnormally heavy usage for Pro plans which don't include a whole lot of usage to begin with. Opus is generally too much for them but you can get a lot of mileage out of Sonnet.
simonw's pelicans probably wouldn't get posted in response to a request for a more quantitative analysis.
You and others are right though, that there's potentially interesting or enjoyable stuff in there (maybe I should have lead with that?). It's just a large volume of it is not useful in response to a question specifically looking for more quantitative or detailed usage analysis.
I agree with you that labs are benefiting from those outputs but I'm skeptical that labs are purposefully training the models to produce those outputs.
Raw pre-training data includes plenty of conversations between professional builders and some of those include estimates.
I believe the outputs are a training coincidence with consequences that are opportunitistic for the labs.
Insincere apologies ought to be mocked to shit but this apology seemed well-meant. (I know you're not mocking them and the last sentence is actually something Claude would say.)
I post this angry comment because LLMs are colonizing the language we use for creating an earnest and genuine tone in online discussion and I sometimes wonder if the suspicion surrounding LLM-ish language is worse for the health of our online spaces than the LLM slop itself. Thinking about it, I don't think it is; and it would be impossible to measure anyway.
I want more of this. Trees using coordinated cell transpiration to control the weather is so fictional but so possible. It's the kind of thing that makes Earth so cool. What do you read? Anything digestible to a curious layman with ~20 minute reading sessions on the train rides?
I can't speak to this exact scenario, but also fascinated by time scale / thinking / I am reading Greg Bears Eon at the moment. Super interesting ideas on space/time travel, not exactly related but enjoying it so thought I would share!
Oof that's hard to answer. I edit Wikipedia pages of botany-related topics so I'm usually reading stuff that's NOT 20-minute bites. I also have a particular interest in parts of nature that break the, imo, false dichotomy between "abiotic" and "biotic" (incl. aeroplankton, mycorrhizal fungal networks, aeonophiles, niche construction, soil ecological succession, etc)
Actually recently I've mostly been listening to lectures by some scientists I follow:
I'm also a big fan of Suzanne Simard's research on "mother trees". She wrote a book I've yet to read called Finding the Mother Tree that also has an audiobook available. But she also regularly does talks
A book that kicked off the popular interest in mycorrhizae is The Hidden Life of Trees by Peter Wohlleben which is also quite digestible. RadioLab also had a great episode about it https://radiolab.org/podcast/from-tree-to-shining-tree
And here are some of my favorite publication that sometimes cover these topics:
Well, in C++ the constructor must return a value of its class type - you can't return an Option<T> from a constructor on T, for example, and since constructors are the canonical way to construct an object, it creates stylistic and idiomatic friction when you start using free functions to create a Maybe<T> instead of constructors.
> in a highly controlled and predictable environment
Why this constraint? A common sentiment I see online (sorry, to group you in) is "[tool] will be capable, actually, but only in a context that trivializes its usefulness."
I think modern post-training like RLVR + inference-time output token scaling can _probably_ scale so the agents can solve any computable task, even when placed in noisy or misconfigured environments. But it won't be economical for a long while. But it already seems largely capable of that today.
Probably not. The active parameter set may change from token to token, based on my understanding of MoE, so you'd be streaming (at the worst case, unlikely for a real scenario but frames the problem) 49B parameters from SSD for every output token...
reply