kirillzubovsky

Is this basically saying: assuming we have working Qbit computers, and we hook them up to a network, this is the system to do your work across the network?

Fascinating that we didn't have to wait too long. Apple announced M5 this morning. Does it compare though?

> So in theory, there’s an expectation that they will diligence the company to make sure they aren’t buying snake oil. In practice, what, are you kidding?

Brilliant. If you can create that kind of leverage, all the power to you!

Google hasn't touched Google Finance in a thousand years, and then this. Looks amazing. It integrates Gemini to answer questions.

This is interesting because on one hand, there's nothing wrong with doing this research, and they might as well. On the other, I think we are putting too much emphasis on what has been.

Sure, we had these mammoth, and these fancy birds, and the dinosaurs. So? It's gone. Let's look at the future. let's figure out what we need now (EVs, Rockets, open Internet...etc).

I am just always surprised by how much emphasis we put on bringing things from the dead, instead of actively elevating the living.

This is the only command I use nowadays: "claude --dangerously-skip-permissions"

I have about 25 agents for different tasks, and sometimes I dispatch them to do their individual work, but that usually happens at the beginning, when I build the first scaffold.

For example, I have agents that setup a DB in certain way, or write a logger in a specific way, I have a test agent that writes them, and a test agent that executes ..etc.

However, for the day-to-day, outside of major ground up builds, straight up Claude.

Sending better prompts to Claude adds more value than everything else, in my experience.

While I can see how these agentic systems could improve accuracy and scalability (I've dabbled into the space before), I also cannot help but to wonder if LLM providers will soon roll these features into their native offerings. There's no way Grok/OpenAI...etc won't be doing everything in their power to one-up each other, and this is one of the areas. Smart RAG might become a way to augment providers that don't have the power to compete with the biggest players.

Great job! I bet so many of us (self included) had this nagging need to do this, but you actually followed through. Kudos!

Yeah. I've been coding with AI a bunch lately, and MCPs sound like a good cool way forward, but having to setup a new iteration for each tool is still a process .... glad to see Zapier take care of it.

Bryan mentioned they've got Zapier Agent too, which can take care of automating choosing the integrations, but I've not played with it yet (https://x.com/bryanhelmig/status/1904220766847066225).

p.s. you'll see a million opinions on how to improve it, but this is perfect. don't overcomplicate it. Apple Keyboard, split in half, is literally all there need to be and nothing more. It's perfect!

Yes. Shut up and take my money! This is exactly what I've been looking for and couldn't find. Seriously, can I just give you money and take the prototype right now?

By the way, if you want to see a proper growth calculator, Trevor Blackwell made one many many years ago. https://growth.tlb.org

Different LLMs respond to requests slightly differently. So if I say - "here's a log of all the errors I got, can you help me solve it?" - you will get different suggestions than if provided more constraints first. It helps to split the logs and ask to solve one problem at a time, rather than expect it to solve all of the problems at once. So it's easy to just ask for help, but you get better results by helping the LLM with extract directives first. That's one example.

If you ask o1 vs Grok to write something, they have very different styles. Grok is chill and concise, o1 is professory and kind of dull. But, each has its advantage, so it makes sense to give o1 something to make it better, then feed to Grok to make it more fun. Things like that.

I talked to Cursor, and Grok, and ChatGPT, at lot.

It may not exist right now, but we can strive towards it. I believe that in a few years there will be an AI, or AIs, that will work completely autonomously. They will not only browser files, documents, and do research, but they will exist on their own, synthesizing information across organizations. That's going to be the 1000x improvements I am thinking about.

I wrote about it: https://news.ycombinator.com/item?id=42701691

I've been relying on something similar for years, a stripped down custom css library with just the styles I use, and nothing more. It made a lot of sense in the last few years, but honestly, I think it's not going to matter going forward.

"Hey Cursor, make the corners rounded, border thick, and make it glow..." That's css of the future. How it's done, where it's compiled, how big it is... most of that won't matter anymore.

Sure, size will matter to some extend, but what if we could just recompile Tailwind on export and only include classes we used?

Even then, it’s a weak question that simply asked the candidate to imagine some reasons why this company is the one, while in reality it’s just whoever willing to hire you, stack ranked by some criteria like money and suffering. So from an engineering stand point, if everyone knows it’s a pointless game, why do it.

This would’ve been a beautiful question if everyone only applied to one job, and this was a chance to tell the future you’d like to see and how you, the candidate, would build this future. But is that ever the case in practice?

It’s all a game.

From what I've seen, a lot of people are indeed living a lie, but they are still lonely. The lie just helps to pretend like everything is a-okay.

I will leave you with Sting, Englishman in New York: "Be yourself, no matter what they say."

While DHH clearly has an agenda, I think this is a great reminder that so does everyone else. People most often give feedback in light of their own needs, wants, and experiences. Just as it is vital to be curious and to test assumptions in programming, the same applies to many other things in business and life. This is just a simple reminder based on a programming-friendly concept.

They prefer term "domain investors." Honestly, there are a few that figured out how to make money doing this, and there is a whole bunch more that bought into the idea, but have never made anything out of it.

If you are curious, I did some calculus on what it takes to make good money in domain investing, and it's not pretty. https://smartynames.com/blog/business/NTJmOWIxNzAt

You will make a small fortune investing in domain space, if you start with a very large fortune.

Hi, I am the guy who did the research. I haven't done enough analysis to see if DGA domains are skewing the sample, or more like which way they were doing it. It could be that all those domains are dormant and don't have DNS, but it could also be they are hosting a bunch of advertisement. It's a whole separate project that requires building out a more sophisticated scraper.

As per the conclusion, well, forgive me for trying to entice the reader to try the product :) Always Be Selling, right?

We did the research without trying to sell anything; it was just interesting. I'd do more, but it takes a while, and I am tired of this space, for the time being at least.

ps. It also takes forever to get the data. I had a local Clojure script running of my macbook pro, doing 10 parallel queues at a time, for what seems like days on end. At some point, my ISP (or something in the chain) suspended my access to a bunch of websites. ooops!

Hi, this is UPS. Your packages was the wherehouse due to an error in the shipping address. Please contact our customer service immediately at http://scams4you.xyz

yup. precisely the topic of an hour long discussion I had with a friend yesterday.

here are top 2 problems I see with this tax in domaining:

1- All of the TLDs are owned by a handful of companies, and it's not in their interest to create a more competitive model. They don't really care who owns a domain, as long as someone's paying for it. In fact, they like squatters and encourage it. You should see how many domains are auto-registered by bots. I'll write about that more in the future, but for every TLD that claims "millions" of registered domains, a large portion of those are just unused junk. The registrar though is getting paid.

2- Land tax is not in the business interest of a business. As a domain becomes one of the key pillars of a business, I wouldn't want anyone to have the ability to take it from me, which is how it works (from my understanding) under the value tax. However expensive, it is cheaper to pay large sum up-front, and know you have the domain forever.

Land tax is one of those things that are good in theory, but in practice will be very hard to implement.

Thanks, you are right, domain investors mostly take risks in arbitraging something they are able to acquire faster than others and don't exactly produce value in the same way that you would, while say creating a game. Of course, don't mention that to the domain investors, as it would not go well.

I would say many of them think of themselves as real estate investors, where they buy up cheap pastures today, in hopes of building the next Manhattan on it tomorrow.

Indeed, domain utilization would be a lot better if they were a lot more expensive. That's partially why some new TLDs sell you a domain for 99 cents the first year, and then raise prices to $50 for the next. Assuming you took a year and built something valuable, the price to keep it goes up.

That said, even those TLDs have tens of thousands of domains (more on that later), which are registered and unused. Investors are willing to take their bets, even if it costs a lot more to maintain the bag.

I am a familiar with a few theories on raising the prices and introducing "taxes," for holding domains, and a friend and I have had numerous discussions on the subject, but so far, in my opinion, those are theories that have too many unrealistic expectations of the real world. There's a solution somewhere out there, but we are not there yet.

Thanks, I will give it a try. I am going to build a cascading approach where I will use inhouse tools to check first, and then when necessary or unclear, you other tools to verify. This would come in handy!

That's a pretty neat use of AI for a subset of use cases. I like it. I just asked it "Why does JavaScript keep crashing", with no particular details, and it was smart enough to show me how console.log() works in order to try and debug this unknown error. It feels good, like asking a friend for help.

I am curious, how do you decide on what kind of content goes in the links bar? It doesn't seem be just news, or just links. I am having hard time figuring out when to resort to the links, vs just using the AI response.

In the long run I will, but for the launch it seemed a better option to go with an API. Less chance for errors, and keeps the product more focused.

Someone else here made a suggestion to update colors, and did some tweaking. Can you see if it got better? Also, do you have examples of websites that did a good job with colorblindness? I am not sure how to test it , given that I can see colors alright.

I love how it just said "DONT" to a request to do something it shouldn't.

Thank you, this is great news! I am definitely try and package all the interesting features into a paid plan and see how it performs. It doesn't cost a lot per request, but now that I've had 160,000 requests in 12 hours, it's not trivial. I'll update the comments and/or post again once new features are up!