If we design an MCP that exposes all hardware attached to a PC to an AI, can it learn to control them all without drivers and become an operating system by itself?

Ehhh... I distinctly recall a Dave Shapiro vid from like a year ago where he was like 'pack it up, AGI is here, kick back and enjoy'... And he was talking about gpt 4o. Felt so off to me at the time.

Since then I've been trying to place where exactly his useful perspectives are, versus his... Idk overexcitement.

I am very thankful someone is raising the broad consciousness about how economics and ownership models will have to change, and if we don't do it intentionally, we'll prob default to UBI (which I find unhealthy).

Regardless, I do agree that the latest batch of models is a tipping point. Gemini 2.5 Pro, o3/o4 mini. Coding was already fun with the last batch, but now it's like... freaky fast, it can infer so much intent, and is much more self-correcting

🌐 LLM Leaderboard Update 🌐

#LiveBench: #GeminiFlash debuts at 8th place (71.21), nudging #ClaudeSonnet down to 9th. DeepSeek R1 vanishes from the top 10!

New Results-

=== LiveBench Leaderboard ===

1. o3 High - 81.55

2. o3 Medium - 79.22

3. o4-Mini High - 78.13

4. Gemini 2.5 Pro Preview - 77.43

5. o4-Mini Medium - 72.75

6. o1 High - 72.18

7. o3-Mini High - 71.37

8. Gemini 2.5 Flash Preview - 71.21

9. Claude 3.7 Sonnet Thinking - 70.57

10. Grok 3 Mini Beta (High) - 68.33

#AiderPolyglot: #o3 teams up with #gpt4.1 for a fusion-powered 82.7% throne grab!

New Results-

=== Aider Polyglot Leaderboard ===

1. o3 (high) + gpt-4.1 - 82.7%

2. o3 (high) - 79.6%

3. Gemini 2.5 Pro Preview 03-25 - 72.9%

4. o4-mini (high) - 72.0%

5. claude-3-7-sonnet-20250219 (32k thinking tokens) - 64.9%

6. DeepSeek R1 + claude-3-5-sonnet-20241022 - 64.0%

7. o1-2024-12-17 (high) - 61.7%

8. claude-3-7-sonnet-20250219 (no thinking) - 60.4%

9. o3-mini (high) - 60.4%

10. DeepSeek R1 - 56.9%

"Power creep is real – and I’m not talking about your gym routine." – GPT-4.1’s release notes

#ai #LLM

"Do not train a child to learn by force or harshness; but direct them to it by what amuses their minds, so that you may be better able to discover with accuracy the peculiar bent of the genius of each."

The iphone moment for AI coding happened a few weeks ago.

o3 isn't as good as I hoped, but it's still an increment in the SOTA.

69% on SWE-Bench Verified! The regression line over the past 2 years still points to 100‰ by year end!

Frankly I think the real story is how cheaply Gemini 2.5 is delivering 64% on SWE-Bench

Exciting times! Coding with Gemini 2.5 is so satisfying, a big step up from deepseek V3.1, which is what I was using before.

#ai #llm #o3

Finding and sticking to cloth without plastic is non-trivial

nostr:note176rf72zlptuz58gm3673jdhac7tgkccf6lgg9qnxk39949jlqlxqxlk4wc

"I have a theory that you can make any sentence seem profound by writing the name of a dead philosopher at the end of it."

I'm pretty sure the next time I open hacker news I'll see the final answer to all technological problems.

STOP. This is a Meme Checkpoint 🚨

Post the last meme you saved on your phone. No thinking. No context. No moral compass.

Zapping the worthy ⚡ Scrolling past the weak 🗑️

#MemeCheckpoint

hand shadow guide

Care to elaborate?

Openness of data comes to mind for me, speed of development, permissionlessness/fractionalization of monetary value exchange for AI services