brausepulver
brausepulver on Hacker News
It's a custom model that's on par with Maia 3 in terms of policy but estimates a lot more than that (e.g. difficulty).
I think the purpose of their method is more to discourage hallucination when reasoning from context rather than from memory.
That said, I couldn't find any evaluations in the report targeting that specifically. They evaluate on MC for hallucination and look about comparable to Qwen3.5 35B-A3B there.
Does this give sensible analysis if you don't record your thinking out loud?
I've been using Elogram (https://elogram.gg/, made by a friend), which gives interpretability by showing how difficulty of a position changes with elo.
As far as I understand:
1) it's very fast (they claim 40-200x faster than frontier models [1], would roughly line up with it doing diffusion)
2) each answer carries a calibrated probability (ie. frequency of outcome is close to predicted)
Another point being that it doesn't reason, hence designed for "System One" tasks.
I wonder if in continuous control with discrete actions (eg. their DOOM demo) it can make sense to blend answer by confidence instead of taking the argmax.
[1] https://typesafe.ai/blog/introducing-system-one-models-and-j...
You need to separate memory capacity and bandwidth. Looping decreases memory capacity/FLOP but not bytes loaded/FLOP, since weights need to be loaded again for the 2nd pass. Plus (depending on the method used) capacity required for KV will be that of the equivalent unlooped model (44 blocks) and KV is typically larger than weights at long context.
What LLM-specific hardware improvements should one expect? Seems to me that LLM inference is simple architecturally (matmul et al) so most scaling in hardware should come from general improvements (memory BW, packaging, interconnect, power).
Consider that a lot of the resistance to just existing is external expectations. I feel like I should always be doing something because I'm pressured to, or that small things bother me because I feel I need to perform. Being content to exist has to do with becoming aware of expectations and not letting them take over your life, I think. Might be why meditation doesn't work for some, as it's a rather brute-force way of doing this.