brushfoot

If you have to use passkeys, try KeePassXC and KeePassXC-Browser. I used them to set one up for Amazon a few days ago, as Amazon now forces passkeys as of this month, at least for my account. It was relatively painless.

That said, I don't like passkeys either.

Meanwhile, Tesla support's AI hallucinated a whole series of steps for me to follow last week. I was trying to add myself to my wife's loaner vehicle.

I called back after finding the steps were impossible to complete. Would I need to go to the service center to do it?

"Akshually," the AI began, the steps were correct and quite possible.

"No, you hallucinated them," I pushed back.

"I apologize. You're right. There's no way to complete those steps in the app. You will need to go into the service center to do this."

"Okay. Is it open today?"

"Yes."

"It's Labor Day. Are you sure? Since you hallucinated your first answer."

"Let me transfer you to the service center to verify."

That's what I wanted all along, you clinking, clanking, clattering collection of caliginous --

"Tesla service center, this is so-and-so. How can I help you?"

"Hi, I was just wondering if you're open today."

"Yes, we are."

"Thanks! I'm trying to add myself to my wife's loaner vehicle. Do I have to come in to do that?"

"Well, our loaner agreement only allows one person on the loaner. So just sign in to her account on your phone."

"Oh, okay! Thanks for the help."

Good luck running a company on one of these clankers.

Not true. Creating an account requires agreeing to the ToS. And if the ToS prohibit this kind of usage, then legally, it's not allowed.

See hiQ Labs vs. LinkedIn. hiQ was scraping LinkedIn using accounts, and they were found to be in breach of LinkedIn's terms.

"Cold calls annoy me" is one angle, and from that perspective, sure.

But "the rich get richer and the poor get poorer" is another angle. Because giant corporations may not need to make cold calls. It's the small bootstrapped startup that does.

Hopefully lawmakers will include provisions for small businesses making well-researched calls. Because otherwise, this is just one more way of pulling up the ladder.

This was inspiring to watch. Thank you for your work.

"Knowledge work is mostly pointless" is the author's view, so his article (the fruit of knowledge work) should be measured by it.

Amd that sentiment is hardly surprising, coming as it does from a Director of AI Operations (his title on LinkedIn).

One caveat worth flagging: Your AI slop garbage radar won't work on food (no em-dashes, no "it's not X, it's Y" framing, just quiche). That's a real limitation, so calling it out matters. You weren't considering using it on food, but it's important to note that it won't work in order to burn more tokens. I mean provide you with a well rounded answer.

Want me to plan an app that detects food made from AI recipes?

No more anonymous driving, thanks to Flock. Soon, no more anonymous calls, thanks to the FCC.

Your bank already knows everything about you; why not your operating system, too?

Soon your ISP will only let you online if your OS sends them the "right" information: your government ID.

We should also abolish cash while we're at it. The government needs to know every purchase you've ever made, no exceptions.

Of course, then we should tear down used bookstores. They're the biggest risk of all. Anyone can walk in and pick up pieces of paper that teach them dangerous ideas. Other religions. Philosophies. Poetry. How to make things.

What we really need is a nation of drones walking to and fro in the image of our rulers, thinking their thoughts, practicing their religions, and parroting their words. It's the only way to be truly safe.

Wonderful! There's a lot of advice online about how essentially evil it is to talk to strangers: They're busy, they have headphones in, they might think you're hitting on them (God forbid; nothing could be more evil than attraction). Ignore it. It often as not boils down to fear and neuroticism from terminally online introverts (and sometimes plain old misanthropists) raised in a hyper-individualist culture and glued to devices sometimes from infancy.

Fair enough if an introvert just wants to be left alone; we should obviously never force our company on anyone (nor do the mentally healthy among us have any desire to do so, because we have empathy). However, people like that will let us know that they don't want to talk when we approach them, either directly or via body language and the nature of their replies. For many others, they're starving for social interaction, and it might make their day for you to reach out. This is what makes outreach worth it, in the end, despite the risk.

Not paying per token? Not sending my code to someone else's servers for inference? That's the stuff of sweet dreams for a stingy, paranoid solopreneur like me.

If I could run a local model comparable to even Sonnet 4.6 without shelling out $50K in hardware, I'd do it in a heartbeat. But all I have is a 32 GB of RAM and an old RTX 4080.

Or am I not up to speed? Are there decent coding models that can run on dev laptops? Not that that's what you were suggesting by recommending a local model, necessarily; just curious.

> People living in areas with longevity (blue zones), didn't really excercise (as in sports)

Not exercising as in sports and not exercising, period, are very different. If you look at the American blue zone, those people are certainly exercising; daily nature walks are baked into their theology.

The Swiss Gear backpack I used daily in college in 2008 is sitting beside me right now. I've put it through its paces over the past 18 years. I jogged here in the rain this morning with it weighed down with my laptop and a water bottle and other things.

Minus some fraying at the base of the front pouch, it's as good as new. I've been very happy with it.

Longtime happy Copilot user here. It's true.

The pricing is so good that it's the only way I do agentic coding now. I've never spent more than $40 in a month on Opus, and I give it large specs to work on. I usually spend $20 or so.

The forced age verification shocks me. It shouldn't, given how much it's been in the news, but my poor naive Millennial sensibilities still feel it's part of some dystopian nightmare that I saw in some Michael Bay sci-fi once, not my present reality.

Your phone, which you own, updated during the night, and now demands you tell it who you are through a credit card, which you may not have, or you're locked out of features. On your phone. This is outrageous.

We can jump ship -- for now -- but it's only a matter of time before these laws cover every kind of Internet access, if they remain unchecked.

There's no need to be rude with comments like "cool story." I'm sharing my experience with you. I'm not an AI-hype influencer. I'm a SWE who runs a small SaaS business.

Where it sounds like we agree is that there's some obnoxious marketing hype around LLMs. And people who think they can vibe code without careful attention to detail are mistaken. I'm with you there.

That hasn't been my experience, as a "ship or die" solopreneur. It takes work to set up these new processes and procedures, but it's like building a factory; you're able to produce more once they're in place.

And you're able to play wider, which is why the small team is king. Roles are converging both in technologies and in functions. That leads to more software that's tailored to niche use cases.

> sounds like alot of work and expense for something that is meant to make programming easier and cheaper.

It's not more work; it's a convergence of roles. BA/PO/QA/SWE are merging.

AI has automated aspects of those roles that have made the traditional separation of concerns less desirable. A new hybrid role is emerging. The person writing these acceptance criteria can be the one guiding the AI to develop them.

So now we have dev-BAs or BA-devs or however you'd like to frame it. They're closer to the business than a dev might have been or closer to development than a BA might have been. The point is, smaller teams are able to play wider now.

Sonnet is right.

Your cold-outreach emails will be flagged as spam by some people, even if they comply with CAN-SPAM. And you should comply with it by having a clear opt-out mechanism and your physical address in the footer, but some people will flag your emails regardless.

I've had this happen in my startup. It hurt the deliverability of our transactional emails (notifications etc.). I'd go with a separate domain if I had to do it over.

What an unpleasant attitude. People have emotions. If they're apologizing, maybe they feel bad. Accept it and get on with your day. A punctilious email etiquette isn't going to improve anything.

> But if you haven’t used specifically Opus 4.5/4.6 with specifically Claude Code for at least an hour, then you’re in for a real shock. Because all your complaining about AI not being useful for real-world tasks is obsolete.

These hyperbolic takes from Steve are wearing thin.

It wasn't my experience that Opus 4.5/4.6 was a sea change. It was a nice incremental improvement.

> And unfortunately, all your other tools and models are pretty terrible in comparison.

Personally, I like Copilot CLI. $10 a month for 300 requests. Copilot will keep working until it fulfills your request, no matter how many tokens it uses.

Calling all other tools "pretty terrible" without specifics reminds me of crypto FOMO from the 2010s.

> How do you know one party isn’t 15 when the other is 25?

You don't. That's why parents need to be involved in their children's lives.

CSAM is the easy excuse, anyway. That's the one lawmakers use, and most people are against CSAM, myself included, so the excuse goes down easy. But the impetus they don't talk about is monitoring and control.

The answer isn't to destroy privacy for everyone. The government and these corporations don't need to know what you're doing every second of the day.

> Content Filters: Discord users will need to be age-assured as adults in order to unblur sensitive content or turn off the setting. [1]

That presumably includes selfies?

That means that to exchange racy photos on Discord, each person must first record a facial age estimation video or upload identification documents.

That seems dystopian.

1: https://discord.com/press-releases/discord-launches-teen-by-...

It hasn't done that to me. It's worked according to their docs:

> Copilot Chat uses one premium request per user prompt, multiplied by the model's rate.

> Each prompt to Copilot CLI uses one premium request with the default model. For other models, this is multiplied by the model's rate.

> Copilot coding agent uses one premium request per session, multiplied by the model's rate. A session begins when you ask Copilot to create a pull request or make one or more changes to an existing pull request.

https://docs.github.com/en/copilot/concepts/billing/copilot-...

And a request can consume more than 128k tokens.

A cloud agent works iteratively on your requests, making multiple commits.

I put large features into my requests and the agent has no problem making hundreds of changes.

Even without hacks, Copilot is still a cheap way to use Claude models:

- $10/month

- Copilot CLI for Claude Code type CLI, VS Code for GUI

- 300 requests (prompts) on Sonnet 4.5, 100 on Opus 4.6 (3x)

- One prompt only ever consumes one request, regardless of tokens used

- Agents auto plan tasks and create PRs

- "New Agent" in VS Code runs agent locally

- "New Cloud Agent" runs agent in the cloud (https://github.com/copilot/agents)

- Additional requests cost $0.04 each

Your body converts ALA into EPA and DHA, however, so plants are fine sources of both.

The ratio of Omega 6 to 3 needs to be below 4:1 to be a good source of Omega 3, and hemp hearts are at 3:1, so they're listed as a good source of Omega 3.

Flax seeds are even better just for Omega 3 at 1:3, but hemp hearts have other benefits, like more protein, which is why I called them out. That said, I eat a fair amount of flax seeds as well.

> I was a vegan for 10 years, and found out I had basically zero Omega 3 in my blood

I see your disclaimer, but just for more context, vegans can get Omega 3 without taking pills per se. Flax seeds are an excellent source. I often add a spoonful to a bowl of oatmeal or as a pancake topping along with fruit sauce and granola.

And better than taking pills for the former, add hemp hearts or flax seeds to your cereal. One serving of hemp hearts has 10 grams of protein and 12 grams of Omegas 3 and 6. Flax seeds are lower in protein but an even better source of Omega 3 in particular.

> Beads formalizes building a DAG for a given workload

> gas town is [...] an orchestrator that is native to dealing with beads

Thanks - this is very helpful in deciding when and where to use them. Steve's descriptions sounded to me like more RAM and Copilot Agents:

> [Beads:] A memory upgrade for your coding agent

> [Gas Town:] a new take on the IDE for 2026. Gas Town helps you with the tedium of running lots of Claude Code instances