⚙︎⎈⏤ Building systems one product at a time ⏤⎈⚙︎
/dev/null
Joined April 2018
- Tweets9K
- Following1.7K
- Followers640
- Likes5.7K
This is strange.
Why is everyone just discovering that certain kinds of "protests" can be destructive?
This is available on opencode, btw.
Ohh, Gemini, you lazy genius (if only they could fix the laziness)
Gemini 4 Argon from @Google on ARC-AGI (Verified):
- ARC-AGI-3: 97.5%, $4.8K (provider adapter harness), 49.8%, $5.8K (standard harness)
- ARC-AGI-2: 91.3%, $0.32/task
- ARC-AGI-1: 98.5%, $0.16/task
Google DeepMind is the second frontier AI lab to score above 95% on ARC-AGI-3.
Surprisingly, I haven't been able to find any official Arc-AGI score for Muse models.
Meta Muse Spark Benchmarks:
89.5% on GPQA
42.5% on ARC AGI 2
50.4% on HLE
77.4% on SWE
52% on SWE PRO
I feel like this is more of a panic release from meta because if Claude MYTHOS released yesterday it would be extremely embarrassing that Claude Mythos beats Metas Muse SWE benchmark with the SWE PRO score 💀
That said this is a solid release and puts them back in the race considering they’re using Claude like crazy
Learning all the different ways software is changing.
I just made a tiny cli to help me wirelessly cast my MacBook screen to my hisense tv.
In the past I'd have to pay for some extra software or hardware,
As it won't be worth the effort to make this bespoke thing.
If you think about it,
fine-tuning an LLM and parenting are just different versions of the same game.
Learning how to train AI might actually be the ultimate cheat code for raising super kids.
Which is why I'm intentionally building a "village"
“It takes a village to raise a child.”
We killed the village. No more leaving the kid at the neighbour’s house.
We killed the large family. No more grandparents, aunts, and uncles around to help raise the kids.
We killed the stay at home parent. Raising kids became a paid service.
One by one, we removed every support system that made raising children easier.
Then we wondered why people stopped wanting children.
We didn’t just kill the village.
We killed the desire to raise a child.
A healthy society needs conservatives as much as radicals,
Perhaps much more conservatives.
99%+ of ideas that radicals propose are harmful,
And a disproportionately large population of radicals basically ensure a tsunami of harmful bad ideas that kills off the society.
Now reading "The Lessons Of History" by Will & Ariel Durant.
Tobi Lütke recommended it in a YouTube video.
It hits different to get a book recommendation and go looking for it only to find out you've had it all these while.
Daemon-Core retweeted
Bending Spoons is building an operating system for software companies. They acquire products with existing users, brands and cash flow, then run them through an increasingly powerful machine for building and operating software. The company itself is the product. I’m very interested to see how far this model can go.
“People who compare Bending Spoons to private equity have a simplistic, superficial view of the world.”
3 main differences between Bending Spoons and private equity:
1. They buy to hold: “We have never sold a material business. We buy to hold and operate forever.”
2. They deeply transform the businesses they acquire, “sometimes beyond recognition.”
3. They integrate them under a shared platform and operating system, with a core team of “Spooners” handling R&D, marketing, and operations.
“People who compare Bending Spoons to private equity have a simplistic, superficial view of the world.”
“None of this bears any resemblance to what private equity does.”
“Those are funds that buy to sell after, say, 5 years. They intervene maybe on costs or price, but I've never seen PE reinvent a product or rebuild the org, or rebuild the technological infrastructure. And they generally don't integrate the businesses together under a shared platform because they don't have a platform, and even if they did, they need to sell them piecemeal. So if you integrate them, you can't sell them, or at least it would be much more difficult to sell them.”