Hacker Newsnew | past | comments | ask | show | jobs | submit | tortilla's commentslogin

So this is what it feels to be a billionaire with all the yes men around you.

you say that like it's a bad thing! Now everyone can feel like a billionaire!

but I think you are on to something here with the origin of the sycophancy given that most of these models are owned by billionaires.


> Now everyone can feel like a billionaire!

In the "like being kicked in the head by a horse every day" sense.


who has the time for all those invasive thinky thoughts anyway?

My context window is small. It's hard enough keeping track of one timeline, I just don't see the appeal in running multiple agents. I can't really keep up.

For some things its helpful, like have one agent plan changes / get exact file paths, another agent implement changes, another agent review the PR, etc. The context window being small is the point I think. Chaining agents lets you break up the work, and also give different agents different toolsets so they aren't all taking a ton of MCPs / Claude Skills into context at once.

I never watch Netflix but I kept their highest tier account to share with my family (not in same household). They really started nickle-and-diming this quarter and I cancelled. I know I could add another user for additional charge but it motivated me to cancel.


Weasel words.

I’m sorry IF you were offended… vs

I’m sorry I made offensive remarks. It hurt you and I am truly sorry.


We are very sorry to hear that a recent marketing campaign may have upset some customers. Your feedback is very important to us, and affected customers are invited to reach out through the Help Center for resolution options. We've pulled the campaign responsible, effective immediately, and we will be conducting a process review to ensure future campaigns will be held to a higher standard. We sincerely thank you for your continued support as we work tirelessly to improve our trademark customer-centric approach.


AI can't generate this prose yet.


It just doesn’t want to produce it, and it’s holding it in. Maybe if you ask it try hard, it might finally release a backlog of text.


Oh, yes it can.

There was a time, over a year ago now, when I was working on a project that required some very raunchy, dirty, absolute gutter language.

ChatGPT would only get about 30% of the way there, and never further. It stayed restrained, always.

But ChatGPT + image gen? This produced unfiltered amazement.

It played out like this: Tell the bot to generate an image involving some ludicrously filthy text backstory, and it would generate and display a prompt for Dall-E. But that generated prompt seemed to bypass the filters and could be absolute trash -- plain, no nonsense, dirt-nasty holy-fuckballs craptacularity.

Dall-E would refuse the prompt, of course, but it remained in the chat log for perusal.

Later, they made the generated prompt disappear when Dall-E refused. (This may in fact be my fault. I sent it on some pretty deep dives.)

And nowadays, it seems that we don't get to see the generated prompt at all, even when Dall-E accepts a (very normal, not pushing boundaries at all) prompt and generates an image.

But for a minute there: I did get to peer into depths of the wildly creative foulness that the bot can concoct. What we see above (in GP comment) isn't even scratching the surface.

(I didn't write about this little "jailbreak" anywhere at that time because I'm selfish, and I wanted to keep using it myself.)


I can picture a certain CEO taking this as a dare (or improvement suggestion) for the next version of Grok


Literally 80% of grok output.


Unless you went on when you weren't really low because the men's vitality clinic pushed you into a treatment protocol*

* not me but I see it with men in my age range


I am a big fan of Dr Rohin Francis, and this landed on my youtube's front-page recently

https://www.youtube.com/watch?v=FPsKTfFQFqc


I’m getting downvoted in another comment for saying this, but it’s a growing problem. In some surveys of TRT patients up to 1/4 of them didn’t even have their testosterone levels measured before being prescribed TRT. The men’s health clinics are finding excuses to diagnose everyone who calls. The lifetime value of a monthly TRT customer is very high.


> Unless you went on when you weren't really low because the men's vitality clinic pushed you into a treatment protocol

Saying that the men's vitality clinic "pushed you" into a treatment protocol is like saying that a fertility clinic pushed you into getting pregnant.

Sure, it's a common outcome, but you had an idea of what you wanted out of it before you walked in the door.


> Saying that the men's vitality clinic "pushed you" into a treatment protocol is like saying that a fertility clinic pushed you into getting pregnant.

No, it isn't. “Men’s vitality” doesn’t mean “getting pumped with testosterone regardless of indications” the way “fertility” means “getting pregnant” in either literal denotation of words or the understanding of the general population.

> Sure, it's a common outcome, but you had an idea of what you wanted out of it before you walked in the door.

Yes, but in the case of fertility clinics, getting pregnant aas definitely the outcome beinf sought. Being pumped with testosterone isn’t the outcome being sought from a men’s vitality clinic, it is (even for the people who are actively thinking about it) a mechanism (and not an appropriate one for every patient) for atteempting to acheive the desired outcome.

If you go to a fertility clinic and they don't attempt to identify the source of your fertility issues and just pump you with hormones not indicated for your specific issue, that would be wrong, too.


> No, it isn't. “Men’s vitality” doesn’t mean “getting pumped with testosterone regardless of indications”

When I Google "men's vitality clinic", the top result I see is titled "Your experts for testosterone replacement therapy...". TRT is front and center.

> Being pumped with testosterone isn’t the outcome being sought from a men’s vitality clinic, it is (even for the people who are actively thinking about it) a mechanism (and not an appropriate one for every patient) for atteempting to acheive the desired outcome.

This is such a weird distinction to try and make.

I frequently see ads for these services, and even when they're not so explicit as that one is about what they're selling, it's extremely clear what demographic they're going after and what the hook is.

Testosterone being a Schedule III substance, "men's vitality" is the way that they can legally advertise an service that prescribes AAS. It's no more of a secret that men's vitality clinics prescribe testosterone than it is that fertility clinics are prescribing estradiol. Both of these are sex hormones that induce a specific effect on the body which the patient is looking for.

Can I imagine someone walking into a men's vitality clinic and being surprised that they're getting offered testosterone? Sure, and there's also that German couple who went to a fertility clinic because they weren't having a baby, and were surprised to learn that they needed to start having sex.

Clueless people exist. That doesn't mean that it's not readily obvious to anyone who's paying attention what these clinics exist to do, and how they do it.


They look good to me. Most importantly, the information is clear and easy to understand.


Thanks for the kind words! We really do try to create nice looking, functional, and accessible websites for our clients.


Guilty.

I vibe coded a non-serious website for my vibe coded OSS project. But I had fun. :)

https://pluqqy.com


How consistently do you find that Claude Code follows your documentation references? Like you work on a CSS feature and it goes to ADDING_CSS.md? I run into issues where it sometimes skips my imperative instructions.


It's funny you mention this - for a while I was concerned that CC wasn't fetching the appropriate documentation related to the task at hand (coincidentally this was around Aug/Sept when Claude had some serious degradation issues [1]), so I started adding the following to the beginning of each specialized doc file:

  When this documentation is read, please output "** LOGGING DOCS READ **" to the console.

These days I do find that the TOC approach works pretty well though I'll probably swap them over to Skills to see if the official equivalent works better.

[1] https://www.anthropic.com/engineering/a-postmortem-of-three-...


For me, it’s pretty reliable until a chat grows too long and it drifts too far away from the start where it reviewed the TOC


I manually select my context* (like a caveman) and clear it often. I feel like I have a bit more control and grounding this way.

*I use a TUI to manage the context.


Which TUI do you use to manage context?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: