atonse

During one of the x threads where Mitchell was (legitimately) complaining about Github, there were a couple replies suggesting that GitHub should hire him to be their CEO.

And I remember seeing that and thinking "huh... not at all a bad idea."

There is a specific kind of leader that can turn such ships around, and they are strong in their convictions, and aren't just "managers", but visionaries coupled with strong execution and power to attract talent.

I think a new GitHub will emerge and when it's just right, will grow like wildfire (like OpenClaw, or even GitHub itself did during the SVN and SourceForge era). And many are already trying to be that new GitHub.

But it’s hardly industrialized right?

So is that a fair comparison?

My problem isn’t that the models aren’t good. I’ve got that down and opus has been so great since last fall.

My problem is that ever since about a month ago, the token usage has gotten out of control and I’m hitting $200/mo max weekly limits sooner when I used the $100/month max for months without ever hitting a weekly limit.

I’ve thought the same. Because the main thing a financial advisor does is have the knowledge of different financial instruments and pair it with your situation right?

An LLM would do that extremely well but can also do it more often. not once a year appointments. You could have active portfolio management for a negligible fee.

I would love this. I’ve built software to manage my business and personal finances and am using hacks right now (activity csvs for personal, quickbooks transaction api for business).

In an ideal world I’d move it all to plaid to help analyze finances, cc spend, etc.

I’m happy to hear you’re working on a hobbyist product.

In this case, the creator has explained that this is all read only.

So what’s the problem?

Thank you so much for actually sharing these technical details. Shows you know THIS website’s audience.

And the thought put into security at every level gives me more confidence in the overall tool.

I’ve tried to build this myself (mvp for myself was just downloading statement PDFs manually and having Claude setting up ledger for plain text accounting, thinking I’ll eventually hookup plaid)

I’m mostly curious about how people work with plaid. Do you need a certain threshold of users to get started? Because I’d love to get a plaid account just for my finances. I’m not interested in building a product like this, just want to connect my personal and business accounts to a clean API.

Honestly, I have zero issues with legalizing marijuana (I'm not an expert on the effects), but I just don't like how the smell really travels and overwhelms local areas nowadays. Fair or not, I think it smells stronger than cigarette smoke (which smells more like a neutral smoke maybe?) so has a higher annoyance factor.

So over time, I've gotten more in the camp of "completely ok with the gummies being legal, not so sure about the smoking part anymore" - anyone else feel that way?

I was an early user of conductor and used it a lot (like from maybe oct to Jan). But then there was some bug where maybe it wouldn’t release file descriptors or something where my laptop needed to be rebooted twice a day. So I stopped using it months ago.

But I’ve tried to reinstall it since and it just gets stuck in a weird infinite loop.

I liked conductor though. Hope you are able to fix those bugs and I can try again in a few weeks.

So to save the idea of $300 (logo design with "local" talent is never $300, it is only that cheap if you offshore it), they tried to ruin a business that presumably employs multiple LOCAL people full time (way more than $300) with 1 star reviews to "punish it"

This is an internet mob at its worst. Not an example of anything to emulate, in my opinion.

Except we can’t discount the fact that Jobs chose Cook as his successor. So there’s something Jobs clearly saw there, past being “diametrically opposed” to Jobs’ product obsession. Maybe Jobs felt there were enough product people.

Eh I don't see how this makes any sense. It's a huge corporation built on a legacy app that's just been near impossible to modernize despite their best efforts, what's the benefit?

My guess is that Atlassian is getting ready to just ditch Rovo and make a big push to embed Claude maybe?

No the bad faith part comes from assuming that the output is low quality, and that just because I get _feedback_ in five minutes (read again what I said) it somehow implies that I spent 5 minutes on it and then moved on, never to revisit.

I think you like the other person is assuming that 5 minutes = low quality. Instead of thinking "5 mins means you can make 8-10 iterations in an hour" or "5 minutes making the front end look pretty good means I can spend more time on the backend"

There are many good faith ways to interpret this.

The obvious bad faith part of your argument is assuming that it's "low quality output." Another is using a blanket negative and dismissive term like slopper, without taking a chance to actually see the work output (at least in my case).

You also clearly misread what I said. I didn't say I spent 5 minutes prompting an LLM. I say the ability to get FEEDBACK (a revision) in 5 minutes is amazing. And I stand by that. That allows me to do 20 more revisions and do in a couple of hours what would take two weeks.

You seem to be romanticizing the concept of grunt work – that for something to have value or be of good quality, you have to put in some sort of minimum amount of time on it, and it has to be tedious. It's the same concept that nobody can make a good quality piece of furniture unless they used a hand saw and spoke sweet nothings to the tree before it was cut.

There are ways to do things quicker while preserving quality. I had already left a caveat saying that for the 5% of people that really want to push web design forward, totally, go ahead. But for the rest of us (including those of us who have lived and breathed code and engineering principles for decades), these tools are phenomenal for iterating quickly.

Anyway, the term builder is more about separating the goals from a vanilla "programmer" - even though i've programmed my whole life, it's always been in service of an outcome. And the outcome is almost never "good code for the sake of good code" - it has to serve a real outcome in the real world.

By the way, lots of good designers are also using coding agents now, so you can keep romanticizing grunt work while most of the market moves on.

Yeah fair point. I have had a couple of conversations (ingesting a pretty complex domain and creating about 42 high fidelity tailwind mockups with ui.sh).

And this particular set of things has context routinely hit 350-450k before I compact.

That's likely what it is? I think this particular work stream is eating a lot of tokens.

Earlier this week (before Open 4.7 hit), I just turned off 1m context and had it grow a lot slower.

I also have it on high all the time. Medium was starting to feel like it was making the occasional bad decisions and also forgetting things more.

Would you like to attempt a more good faith interpretation on what I meant, and address that (you can even imagine doing this in front a user/client and iterating in minutes with them, ultimately getting even better outcomes), instead of inventing the most un-generous interpretation of what I said, that I'm just adding AI slop?

Just yesterday I was happy to have gotten my weekly limit reset [1]. And although I've been doing a lot of mockup work (so a lot of HTML getting written), I think the 1M token stuff is absolutely eating up tokens like CRAZY.

I'm already at 27% of my weekly limit in ONE DAY.

https://news.ycombinator.com/item?id=47799256

Tools like Figma are for an era (and persona) who still wants to have all the various knobs and dials to dial in exactly what they want. And that is one way of working if, like you said people are trying to be more thoughtful and know exactly what they want.

But for the other 95% of people, being able to just say "ok can you make it look more modern" and have 4 variants in 5 mins, (like me) Figma will lose users like me.

But then again I was never a "designer" – more a builder.

Thank you, I should RTFA next time.

I've been spending the last two days building a large number of mockups for a new product. Literally the last two days.

I'm wondering how i can CONTINUE that in this design thing, can i import something? Because they show it the other way... you can start and edit, and then export to claude code.

Until then, I guess it's back to just using CC

Wonder what would happen if we unleashed Karpathy’s autoresearch on the pelican bicycle test. And had it read back the image to judge it.

Oh maybe it might continue to iterate on the existing drawing?

With the bank example, I thought your comment had some anti KYC language so I mixed it up with another response, sorry for the confusion.

I actually kind of agree with you in some principle, IF we had no choice. Like the only reason I can say “you can choose not to purchase this product” is because that is true today, thanks to competition from commercial and open source models.

But I’d be right there with you on “someone needs to force these companies to do ____” if they were quasi monopolies and citizens needed to use their technology in some form (we see this with certain patents around cell phone tech for example)

Well I thought maybe Anthropic read this because my weekly limit (which I just hit, 24 hours before it resets), was just set back to 0.

But they're doing it for everyone (Max, Teams, etc). I guess I'm not a special snowflake! Let's hope the usage limits are a bit more forgiving here.

Not sure where the younger people thing came from, but I'm 45 and have been working in this industry since 1999. But even when I was in my 20s, I don't remember considering that I had a "right" to do something with a company's product before they've sold it to me.

In fact, I would say the idea of entitlement and use of words like "rights" when you're talking about a company's policies and terms of use (of which you are perfectly fine to not participate. rights have nothing to do with anything here. you're free to just not use these tools) feels more like a stereotypical "young" person's argument that sees everything through moralistic and "rights" based principles.

If you don't want to sign these documents, don't. This is true of pretty much every single private transaction, from employment, to anything else. It is your choice. If you don't want to give your ID to get a bank account, don't. Keep the cash in your mattress or bitcoin instead.

Regarding "legit" - there are absolutely "legit" actors and not so "legit" actors, we can apply common sense here. I'm sure we can both come up with edge cases (this is an internet argument after all), but common cases are a good place to start.

I've been using up way more tokens in the past 10 days with 4.6 1M context.

So I've grown wary of how Anthropic is measuring token use. I had to force the non-1M halfway through the week because I was tearing through my weekly limit (this is the second week in a row where that's happened, whereas I never came CLOSE to hitting my weekly limit even when I was in the $100 max plan).

So something is definitely off. and if they're saying this model uses MORE tokens, I'm getting more nervous.

This seems reasonable to me. The legit security firms won't have a problem doing this, just like other vendors (like Apple, who can give you special iOS builds for security analysis).

If anyone has a better idea on how to _pragmatically_ do this, I'm all ears.

I used it for a bit in Jan. And found it to be a much worse version of Claude Code.

But I'm exploring setting up Hermes from scratch so my family can interact with it in a group chat.

I'm running half my company with Nanoclaw. Same idea, and has some benefits, but I live in CC all day so it's marginal (except for the fact that my laptop has to be on)

This is a really cool way to actually educate people about taxes and government spending.

It's crazy that our interest payments are so high. I remember when Clinton actually balanced the budget (no deficit), I was a teenager and couldn't care less. But I only a few years ago started to understand how much that sounds like Sci-Fi in this day and age.

I still love Claude and nothing but a ton of respect for Boris and the team building such a phenomenal product.

That said, I feel that things started to feel a bit off usage-wise after the introduction of 1M context.

I'd personally be happy to disable it and go back to auto-compacting because that seems to have been the happy medium.

Judging by the fact that almost nobody in the mainstream talked about this until a week leading up to the mission, and that it’s been 10+ years in the making, I doubt it’s some vanity thing.

I don’t see how anything as substantive like this can be seen as “vanity” (unless you mean to count that as a bonus).

It’s amazing to see NASA doing newer great things (Webb, Mars probes, all have been incredibly cool too, but manned stuff always hits a different note). Yes they’re way more expensive than SpaceX, I get all that. But it’s nice to see something so overwhelmingly positive and a true example of human ingenuity, collaboration, and bravery, that we need a lot more of that to remind us these days of the positive times we live in.

And the fact that we did this 50 years ago, at least to me, means I appreciate even more how we got it done with that age’s technology and knowledge the first time.