mrconter11

Hi! I put together a simple metric to track progress toward AR glasses that are good enough for everyday use, replacing your screens, wearing them all day, the whole thing. Curious what others think about this :)

What's different between this and all other 10s of different ones doing the same?

But safe-npm is not 90 days old yet.. :/

Hi! I created an algorithm to detect unused screen real estate and made a video browser that auto-positions itself there. Uses seed growth to find the biggest unused rectangular region every 0.1s. Repositions automatically when you rearrange windows. Would be fun to hear what you think :)

I created a calculator that scores your life on objective factors across 12 categories (career, health, relationships, sleep, exercise, mental health, finances, etc.).

The premise is that if you score high on most areas, you have few barriers to wanting to exist. More importantly, maintaining these behaviors demonstrates functional capacity. You can't score high if you're genuinely not functioning.

Each question is rated 0-10 where 5 is average. Z-score transformation converts ratings to population percentiles, so a 7/10 becomes 84th percentile. Final score is the arithmetic mean. All data stays local.

Would love feedback on whether anything is missing. I am also curious if you agree on the premise. :)

Hey everyone!

I've always found the Wilhelm Scream a bit intriguing, but there's no good centralized website for browsing and cataloging all its appearances. So I built one!

Anyone can easily add or edit entries. The goal is to document every Wilhelm Scream with timestamps, YouTube clips, and details for all movies and TV series.

Check it out and feel free to contribute! :)

Not a bad idea actually :)

The volume is intentionally set quite low. You will need to turn up your volume and listen carefully to distinguish the letters.

Isn't it ironic that it ended up being harder to get a computer to explicitly not create a photorealistic image of an elephant than to have create one?

You could flip it around like that. In this case I have chosen to have the "Released Date" as being when the benchmark was published and the "Solved Date" to be when an AI system had a human-level performance for that specific benchmark.

Author here! While working on h-matched.com (tracking time between benchmark release and AI achieving human-level performance), I just added the first negative datapoint - LongBench v2 was solved 22 days before its public release.

This wasn't entirely unexpected given the trend, but it raises fascinating questions about what happens next. The trend line approaching y=0 has been discussed before, but now we're in uncharted territory.

Mathematically, we can make some interesting observations about where this could go: 1. It won't flatten at zero (we've already crossed that) 2. It's unlikely to accelerate downward indefinitely (that would imply increasingly trivial benchmarks) 3. It cannot cross y=-x (that would mean benchmarks being solved before they're even conceived)

My hypothesis is that we'll see convergence toward y=-x as an asymptote. I'll be honest - I'm not entirely sure what a world operating at that boundary would even look like. Maybe others here have insights into what existence at that mathematical boundary would mean in practical terms?

Author here. I think our approach to AI benchmarks might be too human-centric. We keep creating harder and harder problems that humans can solve (like expert-level math in FrontierMath), using human intelligence as the gold standard.

But maybe we need simpler examples that demonstrate fundamentally different ways of processing information. The dice prediction isn't important - what matters is finding clean examples where all information is visible, but humans are cognitively limited in processing it, regardless of time or expertise.

It's about moving beyond human performance as our primary reference point for measuring AI capabilities.

Hi! Quick update to H-Matched, the website tracking AI's progress toward human-level performance. Since last post, I've added 6 new benchmarks (now 20 total) and made the visualization interactive! The site shows how AI's 'catch-up time' has dramatically shrunk - from 6+ years with ImageNet to just months now. Explore the timeline with release dates, solve dates, and links to papers. Would love to hear your thoughts and if there are any benchmarks I've missed!

Thank you for your reply. The time to human level is simply the time it took between the initial release of the website to when an AI system reached human level performance for that benchmark. :) I am in the process of adding sources for all "solved" dates... Here is for instance source for the Winograd challenge human level performance:

https://arxiv.org/pdf/1907.10641#:~:text=The%20best%20state%...).

:)

Hi! I wanted to share a website I made that tracks how quickly AI systems catch up to human-level performance on benchmarks. I noticed this 'catch-up time' has been shrinking dramatically - from taking 6+ years with ImageNet to just months with recent benchmarks. The site includes an interactive timeline of 14 major benchmarks with their release and solve dates, plus links to papers and source data.