scuppernong

https://en.wikipedia.org/wiki/Werner_Herzog_Eats_His_Shoe closest thing

so 20x was only for 5hr but it was 10x weekly? that's nuts

Ultra is replacing Max 20x, but only includes 10x usage. So this is just a barely obfuscated downgrade.

Don't care for the style of this article

one thing you could do is run it against FrontierHarness eval and see how it stacks up?

Did not realize that the model of computation for all of the banner computational complexity results from last week was "exact complex arithmetic." Is this and/or "exact real arithmetic" a common premise for papers in this field? My assumption as an outsider was that people mostly care about things equivalent to Turing machines.

are you serious? this is inane, the "modified" gemini response is totally rewritten from the original (which pangram caught) in a completely different style. this is evidence of nothing.

any evidence for that? genuinely interested. all the evidence I've seen is that Pangram has a very low false negative rate.

only addresses it in a magical thinking "lines on a graph mean that tomorrow Claude will be so entertaining it'll make everyone on earth die in a stupor Infinite Jest style" sense. capabilities have increased while writing has either stagnated or gotten worse and more impenetrable. if you think quality of writing is going to fall to the bitter lesson that's fine you just actually have to make that argument, and how it squares with the fact that AI seem to prefer their own dross to human writing, and that RLHF is increasingly being replaced by RLAIF.

people replying to this seem to be unable to abstain from strawmanning that I am denying the rate of progress. I am not. 6 months ago they were good for an occasional technical lemma and now they can solve major open problems. The writing has only gotten worse (the papers in the big drop are completely unreadable, even to experts in the appropriate fields). If you're going to respond to a comment try to respond to what it's actually saying.

Pangram says mostly human

Doesn't address my point at all and I did not dismiss AI progress.

"AI models will surely get better at writing "enjoyable proofs,"" why? Why is that surely true? they've increased in all other capacities at shocking rates while still writing awful, slippery, turgid prose. Very silly to assume that this will just go away.

i think you still don't understand what it means. there's nothing personal about it. the point you pick along the frontier is what's personal to you and your needs. the frontier itself is not.

https://orionfeedback.org/d/13108-megathread-orion-memory-is... open issue since January. They should open source macOS too, they don't have the personnel to develop this.

not really what it means. also the Pareto frontier is literally drawn in what I linked

https://frontierharness.org/ allegedly this is on the Pareto frontier, though I don't know how good of a benchmark this really is. it seems to focus on one-shot type tasks, whereas the real utility of one harness over another seems to make itself known in long running tasks.

also this is a very limited static snapshot with one model as backend, I wish there were more consistently refreshed and diversified harness benchmarks.

if you're paying API prices, you probably already know this. everyone else is using a subscription which is massively subsidized rel API prices. or am I missing a third case?

Austin doesn't crack the top 100 (!) list of densest cities in America on Wikipedia. What are you talking about?

the charts on maki.sh and in the README don't seem to agree. what's the subtlety?

I wish we could use just the frontend of omp harness-agnostically, like the provider switching, stats dashboard, subscription pooling etc. are excellent features, but it doesn't seem inconceivable that we can have all that with a swappable "actual" harness. I've tried to make omp more pi-like by lazy loading most of the tools rather than dumping them into system prompt. haven't benchmarked this yet.

meta-commentary like this, then, is surely the work of a third-rate mind

this is not a rumor (the allegation, anyway), it's reported in the new york times

i'm sure you consult your attorney every time you agree to terms and conditions

it's a quote from twin peaks if that matters

christ

yes, any options that are all upsides with no downsides are already part of the status quo

Some of these point arrangements superficially resemble Chladni figures (https://chalkdustmagazine.com/regulars/on-the-cover/cover-ch...) coming from the vibrations of a square drum.

Orthogonally, I wonder if these arrangements are generalizable to give lower bounds for N = n^2 + 1

"When we learn how this curve was obtained that might change." IF they tell us. AFAIK Anthropic never released the reasoning chain for the Jacobian conjecture counterexample, and they might not release anything for this either.