nate

I just had a maddening convo with Amazon's AI https://share.zight.com/o0udw54W (i had mentioned before that in 5 minutes it would be time to get my refund according to some other policy message they sent me). A convo before this Amazon's bot didn't even recognize the reply the forced me to give from their button. I clicked "Entire package is missing". and they replied "Couldn't understand your response". It's a brutal, antagonistic experience. The kicker is how Amazon keeps saying "we're passionate about customer experience". You were Amazon. You were. But you've given that up.

The silver lining is that the pendulum will swing. It's like all thee independent bookstores thriving again. Eventually enough of us will revolt hard with our dollars. And move back towards businesses that aren't employing all these bots they stick in front of us. We'll get there.

this is why I feel like we need some kind of "consortium" or government effort to be like "yo, llms, you need to honor some kind of source markup to give us people you mention more significant boost"? like if you mention my article, you better also show my ad partner?

ugh. yeah. the tragedy of the commons

Personally kinda pumped for things like this. I dig good smelling stuff, but I'm allergic to so much of it. The stuff at Henry Rose is hypoallergenic and seems to work better for my skin. But nice to see more tech in this industry.

I've got a half thought about concept that maybe we need a concept like AMP back. I hated AMP. I'm glad it's dead. But you could use it to define things that you were at least advised that it would be shown in the google ui and carousel. I feel like we need a guarantee from the LLMs that if we provide some kind of meta data in our source material you'll honor stuff from it. Like show our advertisers so we get some revenue still from you showing our content on your LLM site.

Totally vibed version of this:

``` { "version": "https://agent-source.org/v1", "canonical_url": "https://ninjasandrobots.com/the-cone", "title": "The Real Reason Nobody Moved the Cone", "source_name": "Ninjas and Robots", "author": "Nathan Kontny", "summary": "An essay about embarrassment, public action, and why obvious fixes go undone.", "preferred_citation": "Ninjas and Robots", "source_card": { "headline": "The Real Reason Nobody Moved the Cone", "description": "People avoid obvious public actions not because they are lazy, but because being seen trying is embarrassing.", "image": "https://ninjasandrobots.com/images/cone-card.jpg", "cta": "Read the full essay" }, "allowed_excerpt": { "max_chars": 500, "preferred_excerpt": "People often avoid obvious public action because embarrassment feels more immediate than danger." }, "commercial_terms": { "ads_allowed": true, "sponsor_card_url": "https://ninjasandrobots.com/.well-known/sponsor-card.json", "licensing_contact": "hello@ninjasandrobots.com" } } ```

But something to get our original source honored better in the LLM. Maybe if one of the LLMs do this, we'd give it more loyalty? Maybe the government needs to compel this kind of behavior? No idea. It does suck though our content is just turned into AI's own tokens and we're left with a tiny "source" link if we're lucky.

I'm actually surprised how much now I'm reaching for Apple Intelligence as a thing to play and build on top of because of its freeness :) I have it summarizing articles for me, a task I thought I'd only want at a minimum Claude Sonnet doing, but alas, I'm not caring as much as I thought about Claude's much better quality over Apple's on device models version. For non anecdotal evidence, I saw people balking at the price of having to put more tokens/credits towards using AlliHat (the Safari extension I have out there for Claude). And so all I did was put Apple Intelligence as an alternative into it, and my conversion rate has tripled. Still measuring this out but I'm becoming more bullish on just using the free tokens we get from our apple devices.

This brings back all this nostalgia. I used to be all linux everywhere I could. The CD linux loaders on random machines work would make me use with work. Linux distros you'd get in a book from Borders. :) Loved it all. But then I had to edit video and images in a 24 hour film festival. And the pain. It just couldn't work constitently. Had to find someone with a mac to get it done. I know these days are so different with better image and video editors and many years of improvements. But still kind of shy from adopting linux again as a daily driver. Too stuck on Apple and OSX now

I've been fooling with the Apple Foundation model for AlliHat, so you can chat with it from a Safari sidebar instead of just Claude. It's passible for some basic things like summarizing a page. But it really reminds me of Claude from like 3 years ago. I was trying to get it to generate synonyms for me and it would only generate about 10 with some duplicates. And when I asked for more, it said it would be a waste of resources to generate more. It has some kind of "act responsible" thing that Claude seemed to have. I also asked it to help me come up with synonyms for the game Pimantle, and it decided Pimantle was related to the adult industry and no matter how many times I said "it's just a game" or "I think you've misunderstood", it was stuck on not helping me with anything related to adult websites. And recommended I should play Wordle instead.

All of this being said, it seems Claude gave up this "constitution" it used to train on? I remember trying to get it to help me code some video editing tools, and it was convinced I was pirating videos and so wouldn't help me anymore in that session.

This makes me nostalgic for platforms like https://unfuddle.com. That was the old days of other providers with subversion and git.

"how you can so authoritatively state this" => because that is the exact order of events :) A happened. Then B happened. i didn't say A caused B. just like we're all discussing here in this thread. just another datapoint that we are sharing here where it seems like there could be a causation not just correlation. but i didn't authoritatively state anything other than I know what happened on one date, and then what happened on another date.

"I think you'll find that taking care of someone" => I know you were writing this generically. And I'm just replying to this for the sake of all of us who do actually know what it's like taking care of someone.

But yeah. Holy shit this is hard. I've been doing this too. Had to move my mom and dad to a place a block from me when my mom was going through her final few months with Alzheimers. That was so hard. So gross. And then now with this descent of my dads. You are catching me fresh from yet another aorta aneurism surgery of his last week. This is bananas. Just endless worry, driving, appointments, cleaning, pills, macgyvering the endless broken down things in his life: the tv, the remote, the blood pressure monitor.

OMG. I see you. I feel you. :) This is a rough part of life y'all.

We probably all have anecdotal evidence here, but my father is a perfect example of being no longer employed and a ton of stuff declining. Yes, cognitively, but a lot of health. We're talking not just your "career". He was a commercial real estate agent. But in his 80s he was working at Menards as a greeter and stocker. And it kept him busy. Getting out of the house. Figuring things out. Meeting and talking to people. Walking. Talking. Scheduling things. He'd even tell us that if he stopped, things would just descend. And he was so right.

He had to stop to help take more care of my mom, and quickly, he just fell out of all these things. Cognitively. Health. Ability to do anything decision wise or to better himself just tanked.

Sample size of 1. A ton of confounding variables. But definitely wasn't his choice to stop working at a place because of health. The poor health came after being forced to quit.

Does make me worry about "taking it easy" when I get older whatever that means :)

"online live reloading apps" => trying to get my head around this workflow. so the disk is shared across these? so do you still have the problem of say running a "main" version of an app, and it's weird experimental version of that same app? because they still have to live in different folders/worktrees? that's where I get stuck a little trying to enable things like this for others. right now, I've got people a system we can spin up N "vms". but it's not persistent storage if the vm goes away. it's whatever version exists in their GitHub branch. hopefully if they hack the vm app they commit and push back to the repo.

I only recently realized how much I like using Cloudflare more than AWS :) R2 (their version of S3) is no exception. Much more pleasant figuring out how to use and configure it in Cloudflare than the craziness inside AWS.

Do you guys geek out like me about EDC/multitools? Pretty happy with this new mini flagship. Wish Victorinox would iterate/innovate on their stuff like NextTool does. SAK innovation is "removing a blade". NextTool is fooling with inventing better tiny scissors.

Yeah, it's funny how many times I basically made the same damn thing just fine tuning a half inch wider, or seam allowance.

I also can't believe how tedious cutting fabric is. Even for a tiny project like this it was such a pain in the ass. Even with nice circular cutters and mats and rulers. I'm now tempted to get a cricut 4 to make the cutting easier.

Taught myself to use a sewing machine. Then I made my own EDC wallet thing. Basically a zipper pouch that can fit a lot of things while keep them as spread out in my front pocket.

I've got a version of this now in my front pocket for like 9 months: https://share.zight.com/wbu487ew Yes, it's big, but it's the most comfortable from of a big wallet.

It's funny though. I can't help feel the pull to try and make the hobby a business. But then it probably becomes unfun. But my brain just can't not think that way.

Ah. That makes sense. Is this something where you do it once and you are done? Or is it something you re-finetune based on performance or reviews you get back from the client. i.e. Client doesn't like something so you go back for another cycle of

Also, is this something that's a pain in the ass to manage multiple versions of the model? One (maybe more in draft mode) for each client?

the morning after the launch i just randomly went onto their livestream and one of the astronauts was asking mission control for help on also using the gopros and iPhone cameras. i guess they have some. and he was struggling at getting a properly exposed photo with those. he said they were coming out super over exposed. but the D5 was working nominally. mission control said they'd get back to them about ideas on adjusting the gopros and iPhones. but it was funny to hear they're trying "new" tech and struggling with it up in space, and that 2005 D5 is still the champ :)

Similarly, I feel like book publishers are about to become a thriving business soon again. With any book being most likely just a bot creation, trusting "Random House" sounds like a thing more of us will start paying attention to to make sure we're buying a human made thing.

Are you asking about the 3 body problem version of this? Spoiler alert: The folks doing the eradicating aren't spending much time/energy/anything on eradicating. It's one large missile through space.

I think the gist is: sure, we humans can't conceive of getting to anyone else in the universe in any timescale, but if we can keep ourselves from destroying ourselves, we'll eventually figure it out. And we'll spread. And we'll kill everything that isn't us in the process as we've done as explorers on this planet.

So really in 3BP: it's inexpensive to eradicate. But insanely expensive to possibly get the intention wrong of any other civilization you encounter. They might kill you.

(again, this is just my interpretation of what 3BP said)

i am absolutely on the fence here. I do like the ai cleanup of my rambling can do. but yes, i'm tempted to just leave it rambly, misspelled, etc. i find myself swearing more in my writing, just to give it more signal that: yeah, this probably aint an ai talking (writing) like this to you :) and yes, caps, barely.

sorry. i didn't mean to say that's the only thing this agent is doing is screenshotting. just that it was a thing my agent is doing which has this neat property. i also have a host of other things going on when it does need to grab and understand the contents of the page. the screenshot is used in conjunction with the html to navigate and find things. but it's also doing things this particular test tries (hidden divs, aria=hidden, etc.). also tries to message the model about what's trusted and untrusted.

but the big thing I have in here is simply a cross domain check. if the domain is about to be navigated away from, we alert the user to changing domains. this is all in a browser context too so a browsers csrf protection is also being relied on. but its the cross domain navigation i'm really worried about. and trying to make sure i've gotten super hardened. but this is the trickiest part in a browser admittedly. i feel like browsers are going to need a new "non-origin" kind of flow that knows an agent is browsing and does something like blocking and confirming natively.

I'm about to launch an agent I made. Got an A+. One big reason it did so well though, right or wrong, is the agent screenshots sites and uses those to interpret what the hell is going on. So obviously removes the secret injections you can't see visibly. But also has some nice properties of understanding the structure of the page after it's rendered and messed with javascript wise. e.g. "Click on an article" makes more sense from the image than traversing the page content looking for random links to click. Of course, it's kinda slow :)

author obviously isn't wrong. it's easy to fall into this trap. and it does take willpower to get out of it. and the AI (christ i'm going to sound like they paid me) can actually be a tool to get there.

i was working for months on an entity resolution system at work. i inherited the basic algo of it: Locality Sensitive Hashing. Basically breaking up a word into little chunks and comparing the chunk fingerprints to see which strings matched(ish). But it was slow, blew up memory constraints, and full of false negatives (didn't find matches).

of course i had claude seek through this looking to help me and it would find things. and would have solutions super fast to things that I couldn't immediately comprehend how it got there in its diff.

but here's a few things that helped me get on top of lazy mode. Basically, use Claude in slow mode. Not lazy mode:

1. everyone wants one shot solutions. but instead do the opposite. just focus on fixing one small step at a time. so you have time to grok what the frig just happened. 2. instead of asking claude for code immediately, ask for more architectural thoughts. not claude "plans". but choices. "claude, this sql model is slow. and grows out of our memory box. what options are on the table to fix this." and now go back and forth getting the pros and cons of the fixes. don't just ask "make this faster". Of course this is the slower way to work with Claude. But it will get you to a solution you more deeply understand and avoid the hallucinations where it decides "oh just add where 1!=1 to your sql and it will be super fast". 3. sign yourself up to explain what you just built. not just get through a code review. but now you are going to have a lunch and learn to teach others how these algorithms or code you just wrote work. you better believe you are going to force yourself to internalize the stuff claude came up with easily. i gave multiple presentations all over our company and to our acquirers how this complicated thing worked. I HAD TO UNDERSTAND. There's no way I could show up and be like "i have no idea why we wrote that algorithm that way". 4. get claude to teach it to you over and over and over again. if you spot a thing you don't really know yet, like what the hell is is this algorithm doing. make it show you in agonizingly slow detail how the concept works. didn't sink in, do it again. and again. ask it for the 5 year old explanation. yes, we have a super smart, over confident and naive engineer here, but we also have a teacher we can berate with questions who never tires of trying to teach us something, not matter how stupid we can be or sound.

Were there some lazy moments where I felt like I wasn't thinking. Yes. But using Claude in slow mode I've learned the space of entity resolution faster and more thoroughly than I could have without it and feel like I actually, personally invented here within it.

Haven't moved for years, but yeah same over here. Darksky data seemed perfect and now no matter what source of data I use in places like Carrot or the ios weather app gives me the accuracy Darksky had. Is it just climate change? I have no idea, but I agree, accuracy seems lost now without Darksky proper.

I know there’s a lot of Tesla/Elon hate here. I’m not denying any of it. I’m just sharing a genuinely strange experience I wasn’t expecting.

We needed a car again. Sold ours a year ago and got by with Uber, rentals, taxis. Life changed a bit and we needed something more predictable. I was planning to buy something used and boring and didn’t really care what.

My wife asked, “What about an EV?” We can’t charge in our rental garage, but there’s a Tesla Supercharger literally across the street. Took a Tesla test drive mostly out of curiosity.

And… I drove maybe 1% of that drive. The rest was on full self driving (FSD).

Fast forward, I now own a Tesla, and about 99% of my driving is on FSD.

Important context: when we picked it up, it was still on v13. It immediately made an illegal turn and scared some pedestrians in a crosswalk. So yes, I get the concern and skepticism. I had it too.

Then v14.2 landed.

Whatever they changed in that release feels real. It’s not just incremental. It feels like a different system. Elon says “we finally cracked it” (and probably says that all the time), so take that with a grain of salt, but with my very small sample size… it kind of looks like they might have.

Two moments that really stuck with me:

While self-driving, the car clearly anticipated a bus making a massive wide turn into our lane and hung way back until the maneuver was complete. It saw that developing long before I did.

At ~70 mph, I was mid lane-change with my blinker on when a driver towing a large trailer decided to drift into the same lane without checking their blind spot. The Tesla instantly aborted the lane change and smoothly moved back, avoiding what would’ve been a nasty accident. No panic, no hard braking, no drama.

I know this probably sounds like shilling. I’m not interested in the politics and don’t want to defend any of that. But it genuinely feels like stepping into the future, and honestly a much safer way to drive.

I want Rivian, Waymo, whoever to nail this too. I hope they do. But right now, Tesla seems to actually have something that crossed a line from “demo” to “wow, this is real.”

I didn’t expect to come away thinking that. But here we are.

Didn't forget. Just don't think it makes sense for these things to try and do both jobs. Slides that work as documents are bad presentations. Slides that work as presentations are useless documents. Even Slideshare's own description of itself isn't "for people that missed the original presentation here's your missing thing".

Its: "Slideshare is the presentation-sharing platform for anyone looking for slide inspiration, to showcase their knowledge, or to build on their own ideas."

So for people to: 1) get inspired building their own deck? 2) "Showcase knowledge" whatever that really means. 3) "Build on their own ideas" => get a bullet point or graph you could use?

No one is learning how to do anything from Slideshare because you missed a presentation. Instead, you're coming to this place to read blogs and actual long form content or watching youtube videos.

My dad is 85 and this article hits hard about what he fights going on in his body. What sucks is how much of a downward, self reinforcing spiral it all is. It's so hard to see the curbs to walk over or how to get to a thing himself, so he just naturally chooses to do fewer and fewer things. Watching TV is safer and kinder and becomes the default to anything. Which just makes his brain less and less stimulated and active, and you can imagine the drag that adds to keep figuring out life.

But like the empathy found in this article, it's caused me to be incredibly more patient with anyone struggling to walk in front of me on a crowded or narrow sidewalk.

Aging is rough. Thank you to everyone working on accessibility and aging related tech and science.