The dynamics of commercial companies and open source are completely different. Microsoft moving to Chromium was a business decision. They didn’t see the value in spending money on a niche browser that didn’t give them any leverage. People developing open source aren’t doing it for profit or market dominance.

Honestly, Firefox would be much better off without Mozilla. A donation model that would fund a small development team that could just focus on making a good browser would work just fine for this.

lol yeah any code I wrote a week ago might as well have been written by an alien

Indeed, and if it gets there then I imagine it will start outpacing proprietary architectures because the whole world will be contributing to it.

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.

Ultimately what matters is whether it gets the correct answer or not. It’s interesting that yours wasn’t able to do the strawberry test while mine did it with very short thinking cycle.

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:

1. 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

• https://ollama.com/library/qwq:32b
• https://huggingface.co/Qwen/QwQ-32B

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.

the joke is that bash syntax is terrible and you always forget how to do basic things in it after not touching it for a while

The most likely scenario is something similar to the post Soviet style collapse that followed USSR.

Gorbachev Introduced glasnost and perestroika to reform the Soviet system that inadvertently eroded the ideological and institutional foundations of the USSR, accelerating its collapse. Today, Trump is pursuing a similar, if ideologically inverted, disruption of the US institutions. Attacking the deep state, undermining trust in media and elections, and prioritizing loyalty over expertise. He’s enacting a purge of the permanent bureaucracy under the guise of draining the swamp, feeding off polarization and institutional distrust. These policies are eroding the foundation of the system paving the way to its collapse.

Soviet collapse followed as a result of a shock therapy with sudden price liberalization, fiscal austerity, and privatization that led to hyperinflation, economic instability, and the rise of an oligarchic class. Similarly, Trump is busy slashing regulations and cutting corporate taxes, fuelling short-term growth that deepens wealth inequality and corporate consolidation. Like Gorbachev, he’s ushering in a polarized economic landscape where faith in the system is rapidly dwindling among the public.

The decline in living standards is amplifying nationalism, in form of MAGA, and deepening cultural and regional divides in the US. Trump’s whole rhetoric is rooted in divisive politics. Just as Soviet republics turned inward post-glasnost, prioritizing local grievances over collective unity, so are states like Texas, Florida, and California are increasingly talking about breaking with the union. People like Musk are well positioned to target the remaining public services and industries for privatization.

The USSR collapsed abruptly, while the US might face a slower erosion of its institutional norms. The big difference here is that the Soviet Union was structurally more resilient to societal collapse compared to the United States.

USSR had a lot of redundancy in critical infrastructure such as public transit, people owned their homes, and food production was largely localized. This allowed communities to survive during systemic failures. Another big factor is that Soviet society emphasized collective welfare over individualism, fostering mutual aid networks and state-provided essentials like healthcare and education, which could buffer against collapse.

The US relies on fragile, privatized systems with just-in-time supply chains, and largely deregulated utilities. We already saw how this system buckled under the stress of the pandemic, and routinely fails to deal with natural disasters like the LA fires. America’s dependency on globalized trade coupled with hyper-individualism and lack of contingency planning, makes it prone to chaos in a collapse scenario. The profit efficiency driven model risks catastrophic failure under pressure.

I do nature photography

I don’t have any problem with AI myself. It’s a tool like any other. What we should be focusing on is promoting positive uses of this tech instead.

We have liberated Europe from fascism, but they will never forgive us for it

• Marshal Georgy Zhukov

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.

exactly right

lol quite possibly, although it seems like return to sanity might be starting to happen there

I find it’s very difficult to tell what the truth is at the time of reporting. As you point out, there are many different perspective, sometimes facts are omitted, or presented in a way that creates biases, and so on. Seeing many different perspectives can help find the ground truth because you can see what facts are being consistently reported across the spectrum.

However, what the actual truth is tends to clear up over time, and this is why I find that it’s really useful to look back and see how close the reporting from different sources was compared to what we now know with relative confidence to be true. This is how I evaluate what sources I tend to put more weight on compared to others. I also find it tends to be useful to follow the analysis along with the facts being reported. If somebody provides analysis that’s proven correct more often than not, then it’s an indicator that their reasoning on the subject is well informed.

As an example, a lot of people like Jeffrey Sachs and John Mearsheimer were dismissed at the start of the war because what they said didn’t align with the narrative. Now that the fog of propaganda is starting to clear, we can see that they were largely correct.

I’d rather see something similar to Ground News that compares media narratives to the actual facts. And especially one that goes back and examines which publications were shown to be more aligned with reality retroactively.

Transpilers are actually pretty popular in js land, Typescript is a good example. You can even transpile a really different syntax if you wanted to. For example, I use squint which lets me write Clojure syntax and produces js as output.