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

In contrast I’m a fan of the overeager messages for actual updates like these presented.

It is just when after said delivery that I then end up on a mailing list where I get sent something seemingly daily from a single vendor that I’m less pleased.


I strongly suspect that "Do not send me marketing emails" at checkout time ACTUALLY means "Wait 6 months before sending me marketing emails, when I might plausibly forget that I checked this box", because I always do my best to opt out of mailing lists and I always seem to start getting stuff anyway 6-12 months after making a purchase. The Silicon Valley model of consent strikes again.

They classify it as "transactional" emails (like what is supposed to be order receipts, shipping updates, etc) and so "decide" they can send you an "order update" to an "existing customer with a business relationship" 6 months later, instead of adding you to the spam list immediately.

I just received a marketing email from Dell, and in the footer they claimed it was a transactional message. The last transaction I made with them was 3 years ago!

It's insane - I rarely want marketing emails (there are some I do, new products from Saddleback Leather are always interesting) but when I do actually find out about some new product that's desirable, I find that I never get marketing emails for it, even if I'm signed up to things you would think would cover it!

Apple knows who I am, what I've bought, and I'm not unsubscribed from all, and yet they've never told me about the Neo, though they did send me an email talking about the event that might have been the one that revealed it.


Same here. Back in 1999 buying something of a yahoo market website was a crapshoot and you didn’t know what was going on till you got it. I have no issue with overzealous updates. But after that; go away! I know you exist.

It's honestly one of his worst videos, but Jon Bois has quite thoroughly documented how many mattresses they tried to sell him as a result of him buying a mattress. https://www.youtube.com/watch?v=n36R8xlhe1U

Jon Bois worst video is still better than 99.9% of all videos.

Yeah I feel like we’re getting pranked here

It’s also possible this is the first iteration of the loop described in the “A practical loop for training taste” section. Which would be less of a “prank” and more of “using the HN audience to feed the machine”.

The loop (some points snipped for brevity):

> 1. Pick one high-leverage artifact from your week. A paragraph…

> 2. Generate 10 to 20 versions with an AI model.

> 3. For each version, write one sentence that starts with "fails because..."

> 4. Rewrite the strongest version with a hard constraint…

> 5. Ship the final version somewhere real and observe what happens.


Indeed, no taste.

It’s a fun book. Definitely worth a read.

And very creepy too. I loved it.

I’ve found that just not answering any calls from unknown numbers (and having my phone just silence those calls so I don’t even see them) prevents all of this. If the caller is legitimate (e.g., new dentist office regarding an appointment) they can leave a voicemail. And if it isn’t spam and they aren’t willing to leave a voicemail and have me call the back, it probably wasn’t important in the first place.

Sure, I may be missing out on some opportunities. But the peace of mind is far greater.


Seconded. Even if one unknown number call isn't a scam, they will almost certainly pass on your number to ones that are. I made the mistake of answering one last week and since then I've been absolutely drowned in spam calls. Some of them even call a second time immediately after the first attempt, presumably to try to break through DND.

This, my pixel marks almost all calls not in my address book as suspected spam or phishing.

The difference is that the recruiters come to you on LinkedIn. This is quite handy when you're currently employed since opportunities come to you that you wouldn't have otherwise looked for.

Cool, even more reason to dislike it. I want my people doing their work, not wondering if the grass is greener somewhere else.

Your personal opinion does not (and should not) dictate how others behave.

The same could be said of almost all luxury goods.

Disagree - Buying because you like the style or the exclusivity is not the same as buying because you have the false belief that the more expensive thing works better when it doesn't

Someone who spends $10k on a watch doesn't believe it tells better time than their iPhone

Someone who spends $10k on their digital CD player believes the digits it's sending to their digital amp are some how magically different than the digits from a $20 digital CD player. They're the same digits, delivered at exactly the same speed. Bit for bit identical.


Obviously the knowledge gap required to go from zero to doing something useful has shrunk substantially. That is improved accessibility.


I can’t say I understand why one would want this lol. Watching cc session replays doesn’t seem particularly useful. But the execution seems well done, so nice job!


I'm discovering new possibilities all the time with how Claude can work on a new type of task in our codebase and business more broadly. While a lot of this can be brought to the team by saying "encapsulate what you just did into a skill," sometimes it's as much about knowing what kinds of prompts to use to guide it as well.

Showing a colleague that flow, and the sequence of not just prompts but the types of Claude outputs to expect, all leading to Claude doing something that would have taken us a half day of work? As a linear video, rather than just a dump or screenshot of a final page? That could help to diffuse best practices rapidly.

OP - you might want to look at the kind of data model Loom used for this problem for videos in general, in terms of workspaces and permissions. Could make a startup out of this!

(Also as a smaller note - you might want to skip over long runs and generations by default, rather than forcing someone into 5x mode! A user of this would want to see messages, to and from Claude, at a standardized rate - not necessarily a sped up version of clock time.)


That’s a really interesting way to frame it — showing the flow of prompts and responses rather than just the final result.

I’ve mostly been using it for demos and sharing sessions with teammates, but the training / best-practices angle is a great point.

On navigation: you can already step through turns with the arrow keys or jump around the timeline, so you don’t have to sit through long generations. But I agree that smarter defaults (skipping or collapsing long runs) could make it smoother.

And the Loom comparison is interesting — I hadn’t thought about the workspace/permission side yet since this started as a small CLI tool for sharing sessions, but that’s a good direction to think about.


> Showing a colleague that flow, and the sequence of not just prompts but the types of Claude outputs to expect, all leading to Claude doing something that would have taken us a half day of work? As a linear video, rather than just a dump or screenshot of a final page? That could help to diffuse best practices rapidly.

Would this not be visible in a text dump without taking half a day to watch? What's/who's the benefit/benificiary of the realtime experience here?

Granted, I have friends who don't read but prefer visual stimulation. I don't think the overlap with people comfortable with code is very large at all.


They can go hand in hand! But if you give a dump of a session to someone, with literal reams of command inputs and outputs etc. interleaved in the session... they'll most likely read the beginning and the end. And possibly absorb the importance of the discovery, but not the types of "prodding" I was doing to the agent to make that possible.

Slowing it down to show the back-and-forth, and to let the viewer absorb and internalize the techniques behind each "prod," is vital!


I thought the same about watching people play video games but that's clearly a thing! This might be useful for educating people on how to use these new tools, perhaps those not in engineering but product, UX, less familiar with CLIs.


Thank you, and fair question :) I’ve been experimenting with using Claude Code with hardware, where the interesting part is the tool usage and workflow, not just the final output. Screenshots and recordings made it hard to show, so the replay lets you step through the session and inspect what actually happened.


I think the main use case is training. I feel more and more confident with my prompts ( and what tasks I can safely pass to what models ), but it is sometimes hard to explain to anyone else what made me go a particular route. This may help, because a person can follow your intuition.


Similarly, the comments complaining about comments complaining about AI are growing quite tiresome.


I do find it kind of wild how intimidating most people I know find baking. Get a food scale and follow the directions and you're good to go and will have something respectable and delicious. As with anything, you can dive deep and go extreme with it. But baking delicious food is not rocket science.


It is fun but it's also not universal. While every house and apartment I've lived in in the USA had an oven, the default in Japan is no oven. 1 to 3 burners, and possibly a broiler is the norm.

If you want an oven you get microwave/oven combo.

Might be similar in Korea? China? Taiwan? India?


Funny you'd say that. Other people say cooking is art, while baking is a science. No room for errors.


Those people are dead wrong on both counts. Cooking meals benefits more from precision than they claim (if you want reproducible results you best be measuring!), and baking does not require as much precision as they claim (I estimate ingredients all the time when baking and my bakes come out great).

There's a lot of mysticism around baking online, but in truth it's very easy. Just follow the recipe and you'll be ok. You don't need to carefully weigh ingredients and stuff like people say.


It depends, I guess. When I make pizza dough, I use around .1% yeast. Using .4g instead of .8g would make a huge difference, and getting that right without carefully weighing it is neigh impossible.


Cooking is art, baking is a very easy science (weight things and check the temperature), pastry is another thing. That requires talent, experience and a lucky star.


Baking bread is fun because its not science. It had guidelines but thats it


Science can be fun!


if there was no room for "errors", how is it possible that there are tens of thousands of different bread and cookie recipes and stuff like that?


Because while the recipes are easy to follow, you can't fix a baked dough. If you messed up the salt, the yeast, etc. that's it. Cooking is more forgiving in that sense.


Baking bread is not like that unless you have strict control of the environment; it is sensitive to temperature, and nature of the water and flour. It's an art; you have to read the signs. And mastering that is rewarding.


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

Search: