Stwerner

I know it's easier said than done, but don't let the anti-AI crowd get to you. Would love to exchange ideas (and be emotional support if the mean comments are taking their toll)! Definitely reach out (I'm scott@ (the domain in my profile))

This is really cool! I've started building a similar tool with some different ideas based around the way I like to ideate with LLMs and write. Debating whether to open source it because it's so tied to my process.

Will be interesting to see where you take this. I'd love to see more experimentation around AI tooling and UX to support creativity.

Curious if anyone else has seen this role start to pop up? As I’ve been talking to people and sharing this idea I’m seeing hints of it, but mostly just figuring it out as hoc.

Building software is getting faster and cheaper than ever before and when that happens to a medium, all sorts of new things become possible.

Some friends and I have been having a ton of fun making standalone, interactive artifacts lately and I started thinking: what would a social media site around that look like?

That's a great point about the choreographer. Hopefully I'll be able to afford one some day...

Ahh cool, I'll dig through your comment history tonight :) I will say, I suspect we're only in the early stages of the LLM's writing equivalent of "autotune" while we all collectively figure out what's tasteful use, what isn't, what it might be like to use autotune as an instrument itself, and then what gets overused. So it'll probably get a lot worse before it gets better.

And thanks for the note about the images, I'll take that into account! I only really just started this project and am going to keep iterating as I learn to use the tools better and I find the right visual language for it.

Since you seem in the mood to give feedback ;) If you take a quick glance at the previous story, do you feel the same way about the images in that one or was it just this one's that you found particularly unpolished?

Yeah, there's a lot more work and personal touch that went into this (and the previous piece) than just "write prompt -> copy/paste into substack".

It's really interesting to hear about others that have been exploring generating fiction with Claude. I clearly need some more work based on some of the comments, but it has been really interesting discovering and coming up with different techniques both LLM-assisted and manual to end up with something I felt confident enough about to put out.

I'd be curious to hear more about your experience!

Thanks! Yeah there were a couple I decided to leave in rather than try to rework as I wasn't trying to hide that it was written with AI, more trying to add more variety to the storytelling. I'm sure as I do more of these I'll be able to recognize them a lot easier. I have been toying with the idea of working them more into character's dialogue in the future, as I've already noticed some people I know speaking in LLMisms.

Yeah responsibility and accountability are also some areas I'd like to explore. I'm mostly digging through this artifact I created with Claude to look at first order and second order effects and then "traffic jams" in the "good science fiction doesn't predict the car, it predicts the traffic jam" and what kind of roles might pop up to solve those issues: https://claude.ai/public/artifacts/39e718fa-bc4b-4f45-a3d5-5...

I've mostly been digging through my own version of that and trying to find things I find interesting and seeing what kinds of stories we can build about what a day in that job might look like.

I appreciate the question and I think the answer is much longer and more nuanced than can really effectively fit into this form factor. I think this question is getting asked right now about all art forms because of AI and from a lot of different people.

My short answer to “why should I care about the mathematical model output from the human artistic input” is “I think we’re all figuring that out right now!” And I’m pretty sure the answer isn’t “you shouldn’t care at all”. Especially if the mathematical model output from the human artistic input expresses what the human wants to express at a quality level that passes that human’s “Taste Gap” (https://www.youtube.com/watch?v=91FQKciKfHI)

I’m sure we could go back and forth about this a lot (and happy to keep this conversation going, I truly do feel like exploring and discussing, this is very interesting to me!) so happy to dig into any aspect with you :)

I will say that I think what’s happening is that we’re seeing more people explore art forms that couldn’t before because of mechanical skill gaps, and that’s interesting in the same way that synthesizers and sampling and software instruments did to music or I imagine digital art tools did to physical art, and I imagine digital photography did to photography which did the same to painting. It’s an interesting time to be alive!

Funny, I was talking to a friend the other day about some thoughts on branding and he commented "as someone with a background in marketing & advertising communications, it's wild to watch a software engineer learn the value of branding and marketing from first principles".

I guess I'm also learning the value of working with an editor from first principles... over the last couple weeks before publishing I read through and made edits to this piece at least twice a day and still didn't catch this.

Ugh yeah, I had an aside about the right-to-repair fights still going on indefinitely into the future that I ended up cutting. I kept the title because it seemed like a warning the characters would see on everything they bought, even if they ignored it. I'm sure I'll explore the idea more in the future though, I plan to explore insurance and liability and law at some point too.

Thank you for this comment, I'm so glad it made you feel a little bit better about the future, if even for a little while!

This is really the whole idea behind this project with Near Zero. I think there's a lot of anxiety out there around AI and the future, I was there for a while too. Ultimately I've ended up pretty optimistic about it all, and inspired by what the group at Protocolized is doing, found science fiction a great way to help express that.

Yeah I was wondering the same thing. I didn’t realize there was any kind of rule against this kind of stuff

Haha well it was me and Claude ;)

Funny I actually saw this tweet this morning about an Openclaw instance getting too advanced for the users to know how to control and fix: https://x.com/jspeiser/status/2033880731202547784?s=46&t=sAq...

Thanks! Yeah this was AI assisted. As an experiment I started asking Claude to explain things to me with a fiction story and it ended up being really good, so I started seeing how far I could take it.

Haha thank you for that quote, this is exactly how it feels.

Has it bugged any of you that everyone you talk to has their own unique prompting technique that they swear by and none of them are exactly the same but still seem to kind of work?

Yep, and the primary transport method is json rpc over stdio

Yeah that’s definitely been my experience too. It’s just as exhausting, compressed into a much shorter amount to time. I’ve gotten more endurance as I keep pushing, kind of reminds me how pair programming felt the first few months of doing it all day.

I can't speak for everyone, I've definitely seen people make the transition or at least bring in-person tournaments into the games they play. I suspect a lot do just prefer online because of how convenient it is and don't really explore in-person events.

For me, there was definitely a high level of anxiety and nerves when I sat down at a table for the first time again after playing online for a while. But it gets easier and easier to shake that off and just get into the flow of watching betting patterns (which is the main thing you have to work with online) which to me was always the primary source of tells rather than anything physical. So maybe in my case the answer to your question is yes haha :) though it didn't seem to impact me negatively much.

I look at it kind of similarly to what the rise of online poker did for texas hold'em. You had people who spent decades playing in person to learn enough to get to the highest tier, but when online poker came about people were able to play 4+ tables at once basically 24/7 at a higher hourly hand rate per table than was possible in person (let alone having access to analysis tools like Poker Tracker). People were able to get very good in a much shorter amount of time.

I suspect we're going to see something similar with Junior talent across the board. A lot of the barriers to actually getting to the core of software engineering for example are going away, and you're going to be able to get orders of magnitude more trial and error attempts in than you previously could in the same amount of time.

Gave it a shot real quick, looks like I need to fix something up about automatically running the migrations either in the CI script or locally...

But if you're curious, task was this:

----

Title: Bug: Users should be able to add tags to a task to categorize them

Description: Users should be able to add multiple tags to a task but aren't currently able to.

Given I am a user with multiple tasks When I select one Then I should be able to add one or many tags to it

Given I am a user with multiple tasks each with multiple tags When I view the list of tasks Then I should be able to see the tags associated with each task

----

And then we ended up with:

GPT-4o ($0.05): https://github.com/sublayerapp/buggy_todo_app/pull/51

Claude 3.5 Sonnet ($0.09): https://github.com/sublayerapp/buggy_todo_app/pull/52

Gemini 2.0 Flash ($0.0018): https://github.com/sublayerapp/buggy_todo_app/pull/53

One thing to note that I've found - I know you had the "...and you should be able to filter/group tasks by tag" on the request - usually when you have a request that is "feature A AND feature B" you get better results when you break it down into smaller pieces and apply them one by one. I'm pretty confident that if I spent time to get the migrations running, we'd be able to build that request out story-by-story as long as we break it out into bite-sized pieces.

Thanks, and having another step for reviewing each other's code is a really cool extension to this, I'll give it a shot :) Whether it works or it doesn't it could be really interesting for a future post!

Ahh I absolutely love this idea of trying to infuse more emotional and fuzzy attributes to see what the LLM comes up with!

When I broke out the layout and style components I was thinking of being able to change the whole site aesthetic from something like "standard b2b" to "geocities fan page", but I'm excited to try getting fuzzier with the descriptions!

Yeah, totally agree that something related to this will likely be the next paradigm. I've been putting together experiments in different directions trying to find that thing that's missing but haven't really found a killer use case yet to pull it all together.

That's a really cool idea that once you can get something somewhat reliably consistent generated, you can kind of let your A/B tests start to run themselves with just rough guidelines on what you're trying to optimize for...

Wow, cool to see this make it on to HN!

Author here, happy to answer any questions about this or chat about the ideas behind it :)

Ahh yeah - so I've found prototypal inheritance (or what Hofstadter calls The Prototype Principle) is a useful way to think about what's going on with in-context learning and few shot prompting and ways to take it further.

If you provide a "prototype" to a model, you can operate on that prototype and create new instances or variations of it. This is useful for working with code by defining an abstraction or a class, and then having the LLM work with and modify it, generating new code that fits or inherits conceptually from that original prototype.