nate

I came here looking for this :) like someone has to be making this joke right. Or another direction of making the connection that there must be some life growing from the filth in a motel room

On the flip of this. For those getting started at their first speaking things, don't freak out when you look over the audience and feel like zero people are registering that you are even using real words :) . I've been on stage a lot: speaking, improv, plays, stuff. And there are countless times you'll actually be able to make some eye contact with the audiecnce if there aren't too bright of a stage light, and you will just see stone cold expressions staring back at you. And you will wonder if words are still coming out of your mouth. :) It happens. The human connection you get with a one on one encounter that your body kind of expects when you talk. Them nodding, or any expression whatsoever often goes completely absent in a speakers setting.

That's why "open with a joke" is so useful. It's not really for them! It's for you!. If you can hear a laugh from your audience, YOU start to chill out. Your body is like "ah. the mic is actually on, and I'm not having a stroke".

Another useful tip, if the scenario allows, try to hang out by the front row before your talk and chat someone up. That's who you want to then make eye contact with often during your talk. Their expression will be or at least seem to be warmer to you. And you'll feel some more calm looking at them than the random heads everywhere else.

I've installed multiple of these skills. but it seems to quickly revert to crappy writing. i've tried the adhd. the brain fried at the end of day. the "Concise" output from the harness itself. the most useful fix to me has been yelling at it "Speak English!! No jargon!!!" it goes back to more concise talking for a little while.

Fable 5.1 is better at this so far though. :(

Anyone have a theory why this even made it to this point? the switch was such obviously a bad idea. just corporate weirdness that no one there bothered to raise their hand and be like "uh, are we really doing this?" or was there a story here that anyone knows about?

Of course I echo the universal: Opus 5 sucks. But what also sucks is still using 4.8. Are you all seeing this? It's like the older models got dumber just before Fable and Opus 5 were coming out? I've heard the theory that it's because 4.8 is getting put on older hardware? And I imagine that just ratchets down reasoning time then possibly?

Sometimes I'm just trying to sus out if I'm truly seeing things these days or going a little nuts :)

right? i need more of these things in my life. the weird. not-claude designed sites.

"is not marketing. It is evidence". ugh.

I'm so confused how to feel about these articles. this one is clearly AI written. But blessed by a lawyer so we think the stuff in here is accurate with facts?

I've accidentally posted an AI article before that seemed just as this was, and the community flagged that to oblivion. Rightfully so I think?

Does Hacker News need a "report AI" and we can then hide the AI articles as a filter?

Yeah, the AI percentage usage thing is even a badge on the article which was a neat design touch too.

for sure. every day i come here hoping for something like this. something like the old milliondollarhomepage kind of things. i miss that stuff :)

I realize so much stuff comes and goes and comes and goes again. Sony's getting rid of physical media we just read this week. But I also think there's a new bubbling up trend of folks craving real stuff that's been curated. Especially in a real place that they can see other people at.

i also really wish, Apple would make it easier and maybe obvious to gate in the store instead. there's so many apps that look like they'll actually be free, but only after a complicated wizard do you end up with the "includes in-app purchase" label which really means: you have to purchase or get nothing. for allihat, i also am gating all functionality with a subscription (at least i don't have a sneaky dark pattern wizard), but i really wish i could just do this in the app store and not the app itself. would just be so much more obvious for users. (i think iOS apps do have this "quick subscribe" mode, but mac app store doesn't have this yet...)

We had this problem too at Inkling (W06, https://inklingmarkets.com). Classic problem to bump into. One thing to alleviate this was to just introduce a clean slate leaderboard at some time interval. Like a weekly leaderboard. Which seemed to help a lot bring back the competitiveness even though there were these all time leaders of course that were with us from the very beginning accumulating the most points. It's all what you choose to show folks.

And yes, it's hard to pull away things from those vocal early users of games. Like maybe ditch those overall leadboards you thought were so great at first. But it's obviously in the games long term best interest to not be completely beholden to the loud, early users if you made a mistake. I remember we also added game mechanics we had to cancel in other games we developed (Cityposh, S11) because they just gave a few people too much manipulative power. It sucked to make a few angry about it, but it was better for the majority of folks playing.

Yeah, i got duped. Sorry y'all. I talk about it here more now this morning: https://ninjasandrobots.com/paul-graham-flagged-for-ai-use

Will definitely now AI check for slop better before even posting. But was curious how automated and cheap I could make it. Isn't turning out that well yet. Also I put up a PR to remove silconopera from Kagi Small Web. Because it breaks multiple of their guidelines: multi-author, all fake authors, and all LLM content at non-human scale.

Does anyone use a decent "ai detection" algo/service/on device model that they are happy with?

ha. speaking of the devil. for the "curse of knowledge" mention i made above i had a link that google served me up to a post that was totally rotten now. so i went back in to include the wikipedia version.

A couple other versions of this that have always stood out to me:

1) There's always a new cohort of people that don't know the things you know. You assume since you know it, everyone does. But kids coming up, or whoever, aren't you. They don't know this stuff yet. You can easily be the first time they've heard "make something people want" and where that comes from. The Curse of Knowledge https://en.wikipedia.org/wiki/Curse_of_knowledge

2) There's always another tone/anecdote/verse that makes whatever idea more palatable to someone out there. They might not like the PG version, or the Wired version or the Daring Fireball version, whatever. There's probably some version of you in this lesson that someone out there vibes better with.

yeah. exactly. they have these "self-hosted sandboxes" which seems to be the unlock we'd need. https://platform.claude.com/docs/en/managed-agents/self-host... but those only seem available to their "managed agents" so like "scheduled prompts" i think. one day i assume they'll merge Claude Web sessions with these self-sandboxes maybe

Is this still using Claude Web sessions? Also, has anyone used Claude Web environments to do anything besides stuff with repo access? Like running real environments? SSHing into anything more super powered? Anyone putting real creds into those environments?

ah. techcrunch must have alluded to you not having milkbones

https://techcrunch.com/2026/06/16/apple-plans-to-change-its-...

I guess I'll go back to mailinator. That thing has 100s of aliases by the way for some that don't use that yet. Great service. Not guaranteed private really so don't depend on it for that. (Though if you use a strong has for a hash@mailinator.com address, is it pretty secure for "email purposes"?)

Not sure I follow. I wasn't talking about local LLMs. I'm trying to identify how folks are managing their employees using essentially Claude Code local vs Claude Code web. The web seems to be the version you'd ask non-engineer type folks to use to "vibe code" but Clode Code web is so neutered from an environment perspective.

I'm assuming there's some OpenCode/OpenRouter kind of VM framework some folks here are using to power up Claude Code in VMs for their employees to get the best of both worlds while just being in the cloud.

Ugh. It really is. I have allihat.com which is the only safari extension (i think still) that talks to claude. And it's well sought for. But you as a user have to enter a friggin claude api key. :( And I still don't grok their TOS around this. Like you can still type: ```setup-token Set up a long-lived authentication token (requires Claude subscription)``` but this seems like a trap? :) Whose using this? Doesn't this like insta break their TOS if you use that anywhere?

Right now for allihat.com I just let people use the Apple model locally if you don't feel like using the claude key. And my conversions to paying user shot up like 3x! But it really isn't a replacement obviously to claude. I was hoping Apple would make proxying to Claude some kind of thing they do for me so I also don't have to proxy to my own server just to try and manage API to Claude usage.

Coincidentally and somewhat relatedly... I just saw this: https://www.youtube.com/watch?v=xe4nUZqX9Ec Roald Dahl predicted AI slop. and even coined "slop" in 1954!?

Stuart Smalley (snl) must have written it. https://www.youtube.com/watch?v=HMRX-Wj2WOk

I feel like this is just the start. There's going to be more and more legislation on the major LLMs to do this in their surface areas.

That's why I reached for Apples own local LLM to fool with similar ideas like this: https://pageforth.com. Apple is better than I expected at this. Right now it filters through things like hacker news articles and whatever else you point it at to summarize and find things that match your interests. Apple's LLM reminds me of Claude like 3 years ago. It's weak for sure. But useful for small dose kind of problems.

It's funny the convos I now have with Sonnet that I wasn't having with Opus. I feel like most of us here are starting to be told to draw down some of our 1M Opus xtrahigh thinking tokens :)

Is anyone using a local router to deal with that? Something thats like "don't even bother with sonnet for this task, just go with Opus". I wonder if Haiku could even do that math and recommend the model you should be in?

The small stuff has their place. I have this safari extension and needed a way to quickly title people's chat histories. Haiku is the fast cheap thing to come up with decent titles of blocks of text. I feel like there's a bunch of those little things lying around you need a model for. I'm even finding Apple's Foundation Model is super useful for stuff like that. Even summarizing an article. It's like equally awful at doing it, but gets enough done to still be useful as a way to be like "oh yeah, this article is actually worth reading"

This makes me wonder if the LLM labs/Perplexities can figure out with CNN a proper revenue share model. I keep writing about this but it feels like we need something like AMP back (i hated AMP). but some kind of thing the publisher can declare: "if you use my content, you better show this ad because this is why that content was written. use my ad so we can still get paid."

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.