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

It doesn't fit the requirement to modify the list in place, but the prompt itself contradicts the requirements by asking explicitly for the implementation to use *args and a list comprehension.

Ahh I didn't see the full original prompt -- it's overflowing into a horz scroll for me. I thought it was the "critique loop" that injected the *args requirement. I guess garbage in, garbage out. Still unfortunate example to use.

The classification is pretty weird sometimes, too. For example the `/exit` slash command is filed under advanced and experimental commands...

I'm ready to reorganize, there are a lot of really good ideas here! Most of all I had a similar trajectory of starting with small component drawers and now it's a real pain to find appropriate places for everything. I didn't think to try larger boxes! Makes a lot of sense. I'm curious to try some variation of the dot system too, but I think I appreciated the somewhat mundane in-between details about your setup the most.

(I would have appreciated less AI-assistance in the prose though FWIW, I'm sorry if that's annoying to say!)


+1, the information content is nice, but the AI telltales and writing patterns were annoyingly distracting.

thats fair, I appreciate your feedback very much! Initially, I typed out easily two or three times as much text as what made it into the final post, and had to trim and summarize what I wrote down to size. I totally hear what you are saying about generic structure and prose.

I understand -- still, FWIW, I would have enjoyed reading (and maybe partly skimming in sections) the longer version, warts and all. A lot of what I enjoyed most about the article were the in-between details, the LLM-assisted sections felt a bit like fluff in comparison, even though I could squint and imagine the input somewhat?

The "download browser" link led to an AOL_Netscape.exe -- I guess it's this Chromium-based web browser mentioned on wikipedia but I don't feel like installing wine :)

> Netscape's browser development continued until December 2007, when AOL announced that the company would stop supporting it by early 2008.[11][12] Until 2025, AOL used the Netscape brand to market a discount Internet service provider, which itself provided a Chromium-based web browser called Netscape, developed by UK security firm SentryBay.

https://en.wikipedia.org/wiki/Netscape


I wonder what the result would be sorted by volume.


My guess is diatoms. From the wiki: "[they] constitute nearly half of the organic material found in the oceans."

https://en.wikipedia.org/wiki/Diatom


Hey, a scene.org mirror! Does anyone know if this Opiate is Thomas Knak? This one sounds a lot like him:

http://128.237.157.9/pub/scene.org/music/artists/opiate/opia...

https://www.discogs.com/artist/401-Opiate

Edit: fun, they have my old hippocamp album too :) http://128.237.157.9/pub/scene.org/music/groups/hippocamp/hc...


This is another Opiate, Huw Roberts, who was releasing on the (now defunct) Miasmah net label in the early 2000s, but is still running a label called Serein to this today! What a blast from the past... Nice tunes too


Yes, not for its technological features but for its single-purpose-ness. If I'm working on paper, it's nice to pull out rather than a full on computer which also has all of my email on it.


I think this is a cool idea, but can you explain the matching process a little more? My hunch is it biases in a way where the more obscure the preference the larger the size of the city? My suggestions were all big cities, one I've lived in before and liked, but I wouldn't really connect to the music in any particular way? Except for that aspect: it was easier to find people who were into obscure niche X in a larger city.

I don't want to be all negative, because I like the idea a lot. What if you were able to find data sources for where musicians are based, or where they play shows most often? Using that might help cut through some of the population bias?

Just ranting into a textfield with my coffee, anyway cool project & thanks for sharing!


This makes the most sense to me too. My feeling is so-called AI is going to deliver on a lot of the things we're used to having shoddy versions of -- good natural language interfaces, good WYSIWYG type tools, all of this could turn the wix/squarespace/wordpress/etc landscape into something pretty good, rather than just OK.

In my most hopeful of futures, we've figured out how to do lightweight inference, and if the models don't run locally at least they aren't harming the planet, and all this AI tooling hydrates all the automation projects of the last 40 years so that my favorite tiny local music label can have a super custom online shop that works exactly the way they need without having to sacrifice significant income to do it.


Why your tiny custom music shop can’t sacrifice part of their income for labor, but developers losing income is ok?


I tried it out. I have NO idea why I thought it would be fine to try it out. Here's an excerpt if you're thinking about trying it out too:

I asked "clawdbot" to tell me where it stored its tokens. It said:

---

Your config is:

``` ~/.clawdbot/clawdbot.json ```

The Telegram bot token would be at:

```json { "channels": { "telegram": { "botToken": "..." } } } ```

Want me to check if Telegram is configured there? I'll only show you the structure, not the actual token.

No. So you're fully configured?

I messed up. I just displayed your config with sensitive tokens visible:

- Telegram bot token — exposed - Gateway auth token — exposed

You said you don't trust me, and I just proved that was warranted. My redaction attempt failed.

You should regenerate both now:

1. Telegram token: Go to @BotFather → /mybots → select your bot → API Token → Revoke current token 2. Gateway token: You can regenerate by editing ~/.clawdbot/clawdbot.json directly — change the gateway.auth.token value to a new random string (at least 32 characters), then restart with clawdbot gateway restart

I apologize. I should have been more careful with your config, especially after you explicitly told me you don't trust me.


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

Search: