Yes it just collapses eventually — never stabilizes.
The training process is flawed, I suspect it has to do with the fact that some weights blow up over time, you can see in “weights” tab.
But at around 4K avg score you should see it solve the env almost every time.
Just a demo :) optimized for speed over stability.
Reward structure: Step: -1 Dot: +100 Win: +1000
so ~4k is max theoretical score on 6x6.
In projecting ARC challenge progress with a naive regression from the latest cycle of improvement (from 34% to 54%), it seems that a plausible estimate as to when the 85% target will be reached is sometime between late 2025 & mid 2026.
Supposing ARC challenge target is reached in the coming years, does this update your model of 'AI risk'? // Would this cause you to consider your article on 'The implausibility of intelligence explosion' to be outdated?
I cannot comment specifically on CHEETAS, but what I can say is that USG developing in house software solutions almost always produces a disastrous product that goes over budget and has extreme maintenance overhead.
To see why, you can simply ask yourself: do you think that the unelected officials overseeing government agencies that embark on enterprise software development projects have sufficient expertise and enterprise software project management experience to be able to do this well?
Furthermore, do you think that the quality of engineers that the NHS or DoD can attract with less than half of the compensation of an actual software company stands a chance at developing something good in house?
It’s unfortunately almost impossible for these projects to go right.
It varies by agency — either something built in house (very bad) or built by a company that knows how to acquire government contracts, of which there are few - the set of which frankly always has worse tech than Palantir. If product efficacy is not absolutely critical, the acquisition process will be driven by nepotism or other forms of corruption.
As an example for the second case in DoD space, there’s Advana.
I somewhat follow, but it seems shares have privileges that cannot be synthesized in the same way that dividends and value can. For example, if the firm votes for a new CEO, these shares should have voting power, but B cannot fulfill this obligation to A, so how can these shares be resold to multiple buyers?