☆ Yσɠƚԋσʂ ☆
- 770 Posts
- 772 Comments
@[email protected] just ran across this model, and it seems to work a lot better than the other ones I’ve tried locally. Seems to be faster as well. One thing I noticed is that it helps to set temperature (which controls randomness) and Top P (which affects variety of output) values to 0 to keep it more focused.
- •
- 1d
- •
about as much of a death ray as the sun on a mild afternoon https://restservice.epri.com/publicdownload/000000003002029069/0/Product
The intensity of the waves is very low in absolute terms, so they’re not harmful.
Microwave beaming—using radio-frequency phased array antennas with intensity levels below mid-day sun-light—is deemed less harmful, with potential physiological effects manageable through thermoregulation.
https://restservice.epri.com/publicdownload/000000003002029069/0/Product
presumably in a similar way to this https://ntrs.nasa.gov/citations/19760009531
- •
- www.scmp.com
- •
- 4d
- •
the key bit
This represents a potentially significant shift in AI deployment. While traditional AI infrastructure typically relies on multiple Nvidia GPUs consuming several kilowatts of power, the Mac Studio draws less than 200 watts during inference. This efficiency gap suggests the AI industry may need to rethink assumptions about infrastructure requirements for top-tier model performance.
a good explanation of why that is https://americanaffairsjournal.org/2021/08/the-value-of-nothing-capital-versus-growth/
The reality is that capitalism is already visibly failing today, and we see mass civil unrest growing across the western world as a result. It’s possible that bandaid solutions like UBI may be attempted, but it’s pretty clear that there would need to be major restructuring of economic fundamentals going forward.
There’s a whole range of 9000S, 9020, and 9100 of chips now, with 9100 being 6nm. It’s clear and steady progress on display here. Meanwhile, there’s really nowhere to go past 1nm chips using silicon substrate. So, it’s not like western foundries have no path forward now.
There are two paths towards improving performance going forward. First is to start using new substrates the way China is doing with carbon nanotube based chips. This requires phenomenal level of investment that can only really be done at state level. Another path is to improve chip designs the way Apple did with M series. And these aren’t mutually exclusive obviously as better chip designs will benefit from faster substrates as well.
It’s weird to claim there’s no actual change when the change is very visible. China is now making their own chips domestically that are only a generation or two behind the bleeding edge. Also, why does it matter whether they’re subsidizing chip production or not?
The visible progress that you’re asking for will happen when all the pieces of the puzzle come together. China has to develop performant RISCV based chip designs that’s what XiangShan project is doing. They also need to physically build the EUV machines, which is what this article is talking about. Then they will start pumping out chips that are competitive with bleeding edge TSMC chips.
You can look at how other industries like rail, electric vehicles, clean energy, and so on developed in China previously. It’s always the same pattern where there’s a few years of build up, and then there’s an explosion of this tech on a scale nobody has seen before.
Chinese scientists developed a chip using carbon nanotubes and a ternary logic system for faster, more energy-efficient computing than traditional silicon chips. CNTs, made from rolled-up sheets of graphene, offer superior electrical characteristics and ultra-thin structure, making them a promising material for next-generation semiconductors. Other advantages include higher carrier mobility, lower power consumption, and the potential for even smaller transistor sizes.
It’s true for me. I generally don’t read through the think part. I make the query, do something else, and then come back to see what the actual output it. Overall, I find it gives me way better answers than I got with the version of R1 I was able to get running locally. Turns out the settings do matter though.
Yeah mine does not do this, here are the toggles I have on mine which might make a difference
<think>
Alright, let me figure out which number is bigger between 9.21 and 9.1999999999. Hmm, okay. Both numbers start with 9. so the whole number part is the same. The difference must be in the decimal parts.
First, I’ll write them down to compare digit by digit after the decimal point:
-
9.21 is the same as 9.2100000000 if we extend it to match the same number of decimal places.
-
9.1999999999 has more 9s in its decimal places.
Starting from the first decimal digit:
- The tenths place: both have 2 and 1 respectively. Wait, no—hold on. Let me check again.
Wait a second, maybe I messed up. Let’s parse each number correctly:
For 9.21:
- Tenths place (first after decimal): 2
- Hundredths place: 1 The rest are zeros beyond that if we need more places.
For 9.1999999999:
- Tenths place: 1
- Then, the hundredths is 9, followed by all those 9s up to the tenth decimal digit?
Wait, actually let me clarify the positions properly. Let’s write both numbers with enough decimals:
9.21 can be written as 9.2100000000
9.1999999999 is already given.
Comparing digit by digit after the decimal point:
- Tenths place: 2 vs. 1 → Here, 9.21 has a higher tenths digit (2 > 1).
Since the first differing digit at the tenths place is already larger for 9.21, there’s no need to look further into the other decimal places because even if all subsequent digits in 9.199… are 9s, they can’t overcome the difference in the tenths place. For example:
The first number has 0.2 in tenths vs the second having only 0.1. The rest of the decimals add up to less than 0.01 for the second number (since it’s 0.09 + 0.009 etc., which sums to 0.09 repeating, approaching but never reaching 0.1).
Therefore, even with all those trailing 9s in 9.199…, its value is still less than 9.2 (since it’s like 9.1 plus almost 0.1 but not quite), so 9.21 is larger. </think>
The number 9.21 is larger than 9.1999999999.
Here’s why:
- Compare the tenths place (first digit after the decimal):
- 9.21 has a 2 in the tenths place.
- 9.1999999999 has a 1 in the tenths place.
Since 2 > 1, 9.21 is already larger at this stage. Even though 9.1999999999 continues with many 9s afterward, they cannot overcome the difference caused by having only 1 in the tenths place compared to the 2 in 9.21.
Final Answer:
\boxed{9.21}
Well that’s interesting because I got something completely different locally
<think>
Okay, let me figure out how many times the letter "r" appears in the word "strawberry." First, I'll write down the word to visualize it better: S-T-R-A-W-B-E-R-R-Y.
Now, I'll go through each letter one by one. Starting with S, T – that's two letters without an R. The third letter is R, so that's one. Then A, W, B, E – those don't have Rs. Next comes another R, making it two. After that, there's another R, bringing the count to three. Finally, the last letters are Y.
Wait, let me double-check because sometimes I might miscount. Let me break it down again:
S (1), T (2), R (3) – first R here. Then A (4), W (5), B (6), E (7). Next is R again (8) – that's the second R. Another R comes after (9th position?), so third R, and then Y (10).
Hmm, maybe I confused the positions. Let me spell it out with numbers:
1. S
2. T
3. R (1st R)
4. A
5. W
6. B
7. E
8. R (2nd R)
9. R (3rd R)
10. Y
Yes, so the letters at positions 3, 8, and 9 are Rs. That totals three times. Wait, does "strawberry" have two or three Rs? Let me confirm by spelling it again: S-T-R-A-W-B-E-R-R-Y. Between the B and E, then after that, it's R-R-Y. So there are three Rs total.
</think>
The letter “r” appears **3 times** in the word "strawberry."
Here’s the breakdown:
S T **R** A W B E **R** **R** Y
Count ’em: 1 (third letter), 2 (eighth letter), and 3 (ninth letter). 🍓
can grab it here
I find it absolutely wild how quickly we went from needing a full blown data centre to run models of this scale to being able to run them on a laptop.
I mean what’s he saying is pure bullshit because we have no idea what it’s going to take to make AGI right now. It’s pretty clear that what he actually wants is to just work people harder for less pay. Even if what he said was true, the solution would be simply to hire more people. The oligarchs keeps trying create a fake labor shortage narrative here to justify more exploitation.
Indeed, the whole panic over people not needing chips because AI got more efficient was misguided. All it means is that it’s more accessible now, so more people will be running AI models locally and they’ll buy chips for that. Companies like OpenAI who were trying to make a business model of selling access to their AI as a service are looking to be only the big losers in all this. If this tech gets efficient enough that you can run large models locally, then there are going to be very few cases where people need to use a service, and even when they do, nobody is going to pay high subscription fees now. Interestingly, Apple seems to have bet right because they seem to have anticipated running AI models locally and started targeting their hardware towards that.
thanks, I spit my coffee 🤣