furyofantares

I completely believe this, but you could also run auto mode classification in manual mode and tell the user the result.

Or even reject anything auto mode rejects while still allowing the user to reject things auto mode accepts. If what's approved is the intersection of what the user is approving and what auto mode thinks is safe then it would be strictly safer than either mode alone.

This would also be a way for users to gain confidence in auto mode before going all in on it.

It's always been easier to start a project than finish it, and LLMs make starting a project roughly free. I'm not sure they change how much work it is to finish it all that much.

I mean, I have finished more side projects than before. So they do change it. Just not as dramatically.

And then there's all the math problems if solved where the information is new to every human on earth.

> I really wish browser vendors -- or, well, Apple is the only one I care about -- would support it directly.

(The instructions you linked are for Firefox)

I'm all-in on the Apple ecosystem and so I have my passwords almost everywhere that way. But like, I have a lot of devices and a whole family. Sometimes it turns out one is not set up properly and I logged in with a QR code.

I'm a happy Kagi subscriber for 3 years? 4 years now? Not sure.

I love the philosophy of just taking money from users and working on giving them what they want and having nobody else to answer to, and I think the results from that philosophy have been excellent. But my biggest (only) complaints are difficult to solve for a paid search engine that requires login.

First, sometimes I end up logged out. And maybe I've changed my password in the meantime and it's not saved on the machine I'm logged out on. It is supremely frustrating to search for something and be met with a login screen instead, and enraging if I can't immediately solve it by logging in.

I'm hopeful that I can actually just search logged out now if this happens, and log in after I'm done with what I was doing.

The second is the requirement to install a browser extension in order to search from the unified search/url bar. I really wish browser vendors -- or, well, Apple is the only one I care about -- would support it directly.

I think they don't want to support a search engine that requires an account. It would be cool if the 100 free searches is progress in this direction but I'm not sure if it will be.

I'd love rain jackets in the spring and autumn, and hawaiian prints in the summer.

In fact I think I will do my own version of this that checks the weather and chooses what to use.

It does change the point! If it happened roughly twice a year, it's not as noteworthy when it happens than if tends to happen every other year, but four times.

It's more noteworthy when it happens the more clustered it tends to be. If it were typical that we'd go ~7 years with none then have ~16 in a single year, it would be huge news when it happens.

For my side quests at any given time I am subscribed to one or the other of Claude $200 or Codex $200 or both. I was briefly on 200+500. Getting to be a real expensive hobby.

At my day job I spend about $1000/mo at API prices. So like 5-10% of my hobby usage.

Hobby setup is I have a single "personal assistant" session which spawns sessions for each project or major job on a project and messages with them. I talk to the personal assistant over Signal exclusively.

Work setup is just a wrapper around Claude Code.

I was with you for a while here but you say nobody has an argument, then when someone presents one you say that actually that bad thing is a good thing because we'll react to the bad thing in a good way.

I'm not sure. I'm not into chess but I've watched other strategy games; I'm fairly confident streamers are vocalizing a lot more than they would actually be consciously considering if they weren't streaming.

Back in the day I remember Jon Finkel (a legendary Magic: the Gathering pro) saying* you're supposed to "focus only on what matters."

It stuck with me because I think it's genuinely what they do, but also seems like completely useless advice. I don't know what matters! That's what makes you a pro and me not.

* Wasn't sure if my memory was correct. A web search finds a Mike Flores article citing Zvi calling this Finkel's Law.

People have been saying LLMs have hit a wall for like 4 years. People still say it today. I don't think it's been true at any point.

Sure, but I imagined anthropic would do that too and they didn't. Imagining it doesn't help!

It kills me to run out of claude code usage then my much more mundane usage, queries or web searches, is also cut off. Not doing that has been a big plus of chatgpt/codex in my mind.

Remarkably the source is so small I can just post it here.

> Let's write our own YouTube clone based on whatever videos have been recommended on Hacker News.

As a game designer the answer is very obvious: That's hard work!

As a heavy LLM user there is another obvious answer: The LLM is very good at copying.

I suppose those are two sides of the same coin. All the hard decisions and all the creativity is already done.

Those aren't the only options though. I've long told people that want to get into game dev that the best thing to do is mod their favorite games. I'm hopeful that the technical ease to do that now leads to a lot of human creativity being expressed.

I did misspeak by saying production, but the context was google products and I mentioned size thrice.

Production was probably the wrong word - I really mean size and complexity of the project.

A replacement for a complex UI that would take a human developer 6 months to do is indeed something I would consider a small project at this point.

They simply aren't as useful for production stuff as they are for little projects.

They are useful! Just not the 1000x return you get on a tiny thing or the 100x return you get on a small thing.

The problem is sharing it to a group of people who mostly aren't paying for it. It's a good way to get a thread that's just people reacting to the title, which drives HN toward just being a discussion board instead of a place to find good content.

I don't trust LLMs to give me numbers like this, and it's not just that it might make a mistake on the number or it might have garbage in its context - it also might just not understand the mildest nuance in its context or apply any common sense.

I recently asked what percentage of ice cream is air. It told me up to 100%. When I followed the sources, as I always do and not just with silly answers like that, the number in its context was indeed up to 100%. There's an industry term called overrun, measured in percentages. But 100% overrun means it's 50% air.

So why would I trust any of these numbers in this obviously LLM-generated and probably LLM-researched article?

I guess it is slightly clever, if you feel like slipping out posts, to make them anti-AI. Really blunts the effectiveness of criticism of putting slop out when the slop agrees directionally with the criticism.

It's extremely inaccurate to say 80% of the gamblers were convinced because that's not how it works at all. Each bet has someone on the other side of it - 50% of the people bet on Bolsanaro and 50% against.

If you bet on 20% chances and they happen 30% of the time you make money. The payoffs are such that you win by being a better predictor than the market. I'm fine criticizing it as a gambling blight (not to mention a corruption payoff) but it is also a prediction market.

20% happens about 1 in 5 times. I know that's snarky wording but 20% shots come though constantly in daily life.

I think as humans we are really bad at intuition about probabilities, and it being an election only makes it much worse. I don't think anyone is consciously conflating these with poll numbers but percentages of voters are the numbers we see a lot more than prediction markets, and 80% is idunno an 80% chance of getting between 50% and 54% of the vote or something.

The only other post on this blog is "Anything connected to the internet is going to get hacked to pieces." I'm not claiming any contradiction but it is funny.

I think there is a possible future where "I" am a talking cucumber, though?

Ignoring that you have to give up a sense of personal identity at this point, there is nothing in the laws of physics that says the matter that makes up what we're presently calling me can't morph into a talking cucumber with a brain with my memories in it. It's just absurd number of extremely specific things that have to happen out of an ever more absurd number of possible things to happen.

For most things I find medium to be the highest quality output. However if I want it to do spatial reasoning or if I want it be funny / write something (not code) of almost-passable quality, then xhigh is where it's at.

Yeah.

System 2 is slow because it is sequential. Every output depends on all the prior outputs. Like a transformer. (Even if this comes about as the result of massively parallel processes, both in the brain and in the model.)

System 1 is more of a parallel thing, operating on the output as a whole rather than in sequence. Much more like diffusion.

I wonder if you could exfiltrate some weights, and gt them to do inference.

I would guess Linus has reviewed more code than anyone else in the world, so in that sense I'm not that surprised.

I also don't think the C++ thing was out of a stubbornness for the old way of doing things, but had concrete reasons to reject it. I guess it was a little of both maybe 20 years ago.

But there's Rust in the kernel now too.

I knew the middle of the alphabet wouldn't be the correct cut but figured people would get the gist.