MrDunham

And yes, I need to optimize (and am), but they're already getting hundreds from little me. I even started going towards the CI doing browser walks, code tests, AI rework, etc. It saved me from having another dev machine.

Great stuff, powerful as all heck, and once you see the power it was—for me—impossible NOT to think of 6 other uses and blow through the free CI tier.

The challenge I've had is I tell it to do {thing}, it does {otherThing} after getting distracted. Then I get annoyed (let's not mention how I probably half-assed the instructions and wouldn't expect a senior human to be able to succeed).

For me, it was a CI/CD issue with our two person startup. I bypass CI/CD often because it was built to catch the AIs. Damn thing went chasing rabbits. Later that day I talk to my cofounder, who says: I have to go chase down this very important CI/CD issue!

Turns out both humans and AIs get distracted relatively easily.

I find that if I think of my AIs less like (deterministic) software and more like leading actually employees that I both get better output and curse (a lot) less.

LLMs _were_ trained on human writing, so it makes sense to me that they tend to act human-like... for better and worse. So yeah, they do dumb stuff, and so do people.

And even with mobile dictation/notetakers, there's something that screams respect when someone writes actual notes down by hand.

Big big deal indeed, thanks for sharing.

Seems very appropos.

Same regarding your comment... I agree, the minimum QC does feel like it notched back a bit.

Now the big (BIG) caveat is that I used Claude Code on my Max 20x plan from within VS Code. I have a fairly decent harness that I'd built and was sure to prompt it to run several subagents, including one that grounded walking times with Google Maps directly.

I'd say this is FAR beyond what the average person would do ("Hey Siri, plan me a trip to Prague") but also it shows that the models can do it with the right harness and guidelines. This wasn't that hard for me to do, so it seems to be more of a feature buildout ("the travel expert" AI) with a few markdown files than anything.

All told: web search for grounding times/locations, map grounding for walking paths and times, an adversarial agent to keep the model(s) honest, and a little bit of prompting and you've got a really great travel planner.

In short: the average person won't do this, but if I can build it in a few hours any of the 100% of people working at Apple/OpenAI/Anthropic who are smarter than me can build it and bake it into Siri (or ChatGPT, Claude, etc).

It would take ~5000 years at the current annual rate of animal cases to match the number of human cases just 40 years ago.

That's The Great Pyramid of Giza ago time... PLUS the amount of time since Michelangelo, Leonardo da Vinci, and Raphael roamed the earth.

The cool thing is that at a few hundred, one could theoretically* round up all (known) animal cases left. That's truly incredible work getting to this point if you think about it.

* Yes, geopolitical issues, geography, and plenty of other reasons might make this somewhat impossible... but the fact that we can actively picture a few hundred animals in our brains means that it's a very attainable goal.

It's also crazy how much Mother Theresa's quote rings true, even in reverse ("If I look at the mass, I will never act. If I look at the one, I will.") When I initially read 3.5M cases, I thought "wow, that's a lot", and somehow the 445 animal cases in Cameroon felt (at first) more real and similarly "a lot".

No comment other than interesting how our human brains work and distort how numbers "feel".

Once my rational brain kicked in, realized that's over 5,000 years for the current number of animal cases to match the former number of human cases. The future is awesome.

My main use case for OpenAI/ChatGPT at this point is realtime voice chats.

OpenAI has done a pretty great job w/ realtime (their realtime API is pretty fantastic out of the box... not perfect, but pretty fantastic and dead simple setup). I can have what feels like a legitimate conversation with AI and it's downright magical feeling.

That said, the output is created by OpenAI models so it's... not my favorite.

I sometimes use ChatGPT realtime to think through/work through a problem/idea, have it create a detailed summary, then upload that summary to Claude to let 4.5 Opus rewrite/audit and come up with a better final output.

But actually hosted on https://www.deepmyst.com/ with no forwarding from the Apex domain to www so it looks like the website is down.

Otherwise excited to deep dive into this as this is a variant of how we do development and seems to work great when the AI fights each other.

Strongly disagree that they're terrible at asking questions.

They're terrible at asking questions unless you ask them to... at which point they ask good, sometimes fantastic questions.

All my major prompts now have some sort of "IMPORTANT: before you begin you must ask X clarifying questions. Ask them one at a time, then reevaluate the next question based on the response"

X is typically 2–5, which I find DRASTICALLY improves output.

"Thank you for flying Delta? I'd fly a kite if it was $11 cheaper"

I couldn't find the comedian, but the truth in it hits.

Side note: if I recall correctly Delta listened to their customers a decade+ back, gave more leg room, then nearly went bankrupt because no one wanted to pay more for the service.

Nearly all of my "agents" are required to ask at least three clarifying questions before they're allowed to do anything (code, write a PRD, write an email newsletter, etc)

Force it to ask one at a time and it's event better, though not as step-function VS if it went off your initial ask.

I think the reason is exactly what you state @7thpower: it takes a lot of thinking to really provide enough context and direction to an LLM, especially (in my opinion) because they're so cheap and require no social capital cost (vs asking a colleague / employee—where if you have them work for a week just to throw away all their work it's a very non-zero cost).

I preferred downshifting VS braking, personally

I say lucky because they were such good people with such a great mission. Hans (founder) and Christian (co-founder) were really, really fun to get to spend ~10 weeks with.

The new CEO is fairly recent so I can't vouch either way for him. Hans and Christian were an absolute joy with incredible hearts.

I seriously HATE magic links. My email inbox is barely better a social network's time suck. Lots of urgent, little important, wrecks any flow I had.

Forcing me into my inbox is highly likely to cause me to forget about the reason I was there (to get into your app). Or, at best, it slows me way down and nearly always breaks my flow.

Perhaps this is acceptable for the security boost (?) for the average user, but man, when I get forced into magic links I sometimes just abandon the app altogether.

Disclaimer: 1. I have/pay for a password manager, which helps with the forgotten password problem a lot. It also allows me to have extremely hard-to-crack passwords.

Would suspect that number is much, much higher now.

* The Hacker Fair reverse job fair at the Hacker Dojo. #2 was "the CIA got hacked". Proud of that one.

"predestination", pretty sure parent meant "pre-detonation"

A.k.a. Autoignition aka "it goes boom before you planned on it"

Only adding this as it's a pretty crucial word for understanding the comment.

Thanks for the clarification

Perhaps not for everyone but I certainly enjoyed having it be more thoughtful than me essentially clicking the buy button for her. She did, too.

But the vibe... he really, really nailed the beachy vibe (even despise being an incredibly astute businessman)

Posted while drinking a (third) margarita in honor of Jimmy Buffett.

In case you get paywalled

The I stumbled onto this article[1] while looking for evidence to cite. It appears that I've been grossly mistaken.

[1] https://highways.dot.gov/public-roads/mayjune-2000/one-mile-...

Eg 1/3 cup kernels, fill same cup halfway (1/6 cup), add flavacol to the oil in the measuring cup & stir, mix with kernels in a saucepan over heat. Love life

Source: I started getting fat of popcorn every day and am typically considered skinny/fit. Then I read the label and got sad.

Admittedly, I do many things wrong. But this is one I've done well and could be helpful for those struggling with the above ("meets ALL of their criteria")

My wife and I are far apart politically... and our marriage is something I (and I think, we) cherish.

When dating I struggled with finding someone who met ALL my criteria. In the course of it someone taught me to sit down and select your three (and ONLY three) "must-have" criteria. All other things are then negotiable.

For me, I wanted someone who was smart, who shared my religious beliefs, and who was supportive of my entrepreneurial plans/journey.

(Side note, I cheated and said I also wanted to be physically attracted to them.)

Fast forward to me meeting my wife. There are a good deal of things we disagree on — politics being towards the top. Had I let that get in the way and looked for a laundry list of must-haves I would never have married her, would never have had our two incredible children , and might possibly either still be looking or have given up on my criteria and settled.

This trick (pick 3 "non negotiables", let the rest be negotiable) served me extremely well in finding a dog after meeting ~100 (before having criteria), in my wedding (open bar, all my friends can come, no shoehorning of food by the venue), and a few other cases.

I can only speculate on why it works so well. It likely works because it forced me to really list what was crucial and to be more flexible on things I'd otherwise list as crucial.

Either way, if this helps one person to simplify, focus, and be flexible enough to find a mate theme it was worth it. Hope it helps you.

And happy Father's Day to all you other fathers out there.