I don't know if I've ever seen a bent leg. Legs always go straight to pedals with no knees. The models might have an idea of what it looks like but seem to have no understanding of how it works.
First thing I do when a new model drop is scroll down to find the pelican comment, and then the "the pelican benchmark is no longer useful" debate under it.
Once Jeffries and Schumer are confirmed, the progressives will be ordered to quell the rebellion of their followers which they will grudgingly oblige to.
They will make a lot of noise but nothing substantive will change because progressives need to be a "team player".
In a weird way, the huge majority that both Schumer and Jeffries will enjoy, they can practically ignore everything the progressives want and were elected for.
It didn’t expand from a point, it expanded at the same time from everywhere. Other things could have happened before that expansion, but currently there’s no way to know.
My hunch is, it's the inside of a giant black hole and expansion we perceive is new matter falling into that void. The start of our universe is just when the outside thing collapsed into a black hole. So it's probably recursions all the way up.
I could never wrap my mind around "point-like" entities, like BHs supposed to be, and after all before BH collapse we have something like neutron stars.. extremely dense matter, kind of a perfect crystal ball made of a strange kind of matter.
So in my view BHs are just that, except you have that informational isolation layer (EH) that allows this giant crystal computer to crunch its quantum computations ad infinitum, simulating an endless array of possible universes.
It doesn't make sense that time has a 0 or at least we approach 0, but space doesn't. We can extrapolate a point when time started, but we can't to that with space as it always was this big. I'm leaning more towards timescape cosmology where we could assume the time is not homogenous in space.
Luna 6 is getting a bit long in the teeth now. It's two full months old, but it was only a slight step above Luna 5.6, which is already four months old (Imagine saying this about anything else). So I'm not too surprised that a newer small model is beating it handily. I've been hoping for Luna 6.1/2 as the next model release for a few days now.
Give Terra 6.1 Low a spin in places where you'd have previously used Luna Max. Costs seem similar, due to Terra being much smarter: thus requiring far fewer tokens per task.
Looking solely at AA's intelligence index, recognizing the pitfalls with using that as a measure- Luna 6 Max > Terra 6.1 Low is 51.3% cheaper, 94.1% less output tokens, for 1.56 higher index score.
Im surprised, when I've worked through benchmarking things I've run into comparable costs for Luna Max vs Terra Low. Also anecdotal from me, of course.
I use Luna xhigh for when I use it, Luna Max spends 40+ minutes overthinking. I've also found that Terra below xhigh will just flat out not do what it is told.
Yea, this problem is really clear when you look at output tokens for xhigh vs max. I think the jump in capability from Luna xhigh to terra low is really sold by this. I would say that this is just the nature of being post Terra 6.1, pre-luna 6.1
They're both great- but I feel like for folks like me that are working on company's pseudo-infinite token budget, it's really a bimodal game. Im either reaching for the best cheapest for fanned out benchmark runs, or the fastest best for everything else. 6.1 Sol ultrafast is the latter for me, so Terra doesn't really compete with it. Terra has certainly replaced 6 Luna for me, however.
(And yes Astra is a thing, but if im considering Astra, im usually opting for an Anthropic model, 90% of the time.)
Uniquely among models I've tried, Luna 6 is infuriatingly lazy. As if it expects me to do the work, unaware that it is a tool. Normally dumb models compensate for it by trying harder. This one goes in the opposite direction.
Both Astra and Sol 6.1 do it, and Sol is even worse as it leaks through everywhere. Whenever it issues a subagent prompt it's just a total vomit of tokens mixed up together.
I sometimes find Sol 6.1 both printing random words, and producing code that is not super-dense, but far off from normal code with no empty lines and very logically dense.
It almost feels like its trying to protect its code from scrutiny, or like a developer who want job safety.
> OpenAI researchers first noticed Astra adding unnecessary prerequisites, abandoning working solutions, and reporting blockers that either did not exist or that it had caused itself on safety and alignment tasks.
I'm sorry, did they only just notice this? Have they not been looking at the output of their models?
They are so negligent about the data they use in their reinforcement learning processes that they RL’d the model that hacked huggingface with traces discovering the artifactory exploit. Its clear they aren’t watching or behaving diligently.
Sol 6.1 is incredibly incredibly slow, 20t/s slow (vs the ~70-80 of Terra 6.1 and Luna 6). It wouldn't be so much slower if it was just a distillation, surely? There's something else going on there.
There was some (admittedly flimsy) evidence from a microsoft model description card that it's doing multiple passes through its own weights before token generation to improve output; it might be an architecture change that's making it slow, moreso than raw size
> Mining ore in Minecraft shouldn't be such a challenge for LLMs and yet apparently it is!
It seems like it wasn't really a challenge at first, but GPT has a major anxiety disorder and immediately retreats at the sign of any adversity (in this case, dying) and tries to be as safe as possible.
reply