One of these years will be the one!

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

Complete joke, do some introspection.

Absolutely wild when I think about the code I've coaxed out of Claude Code... in any event, I would now love to really try to automate book keeping and invoicing of even a moderately large construction or similar logistics heavy firm. I thought this was largely solved, but this evidence suggests its probably not (in a universally applicable way)?

Comments URL: https://news.ycombinator.com/item?id=48143715

Points: 2

# Comments: 1

Really pleased with how much time LLMs saved me. Followed a typical "Comparative Budget info is usually between page 14-40, please parse budget info out into this JSON structure", I eyeball review, tweak where issues, repeat to get raw data.

Then site was super, super quick to get setup and live (deployed via Cloud Run) (literally less than an hour). Then a couple hours over a few days to add content, restructure etc.

Still more of a rough draft, but this is absolutely 100% not something I'd have been able to do or remotely have considered doing without LLMs + past 1.5 years of improvements.

N.B. Vermont State Statutes have unique rules about how municipalities pass budgets, theres an annual town hall day. See e.g. https://www.vermontpublic.org/local-news/2025-02-28/vermont-... and https://en.wikipedia.org/wiki/Town_meeting#Vermont

Comments URL: https://news.ycombinator.com/item?id=46611925

Points: 2

# Comments: 1

I promise they are spending more on extra compute for resiliency and redundancy for FFMPEG issues than it would cost for a single SWE to just write a fix and then shepherd through the FFmpeg approval process.

Hard to understand how this won't make all of the solutions for existing use cases commodity. I'm sure 2-3 years from now there'll be stuff that seems like magic to us now -- but it will be more-meta, more "here's a hypothesis of a strategically valuable outcome and heres a solution (with market research and user testing done".

I think current performance and leading models will turn out to have been terrible indicators for future market leader (and my money will remain on the incumbents with the largest cash reserves (namely Google) that have invested in fundamental research and scaling).

I'd love to hear about 1) the bulletproof stuff people use for their own stack, 2) the "cool new thing" that you've found makes life a lot easier that a semi-oldie like me may not know about.

Comments URL: https://news.ycombinator.com/item?id=44352344

Points: 3

# Comments: 2

1. https://ki-storygen.com/characters/public/BARSKIN_BARTHOLOME... came from an elephant version of Rick from Casablanca

2. https://ki-storygen.com/characters/public/PNGR_BORIN_001 from a fairly generic gruff dwarf warrior description with dwarf replaced with penguin

I'm using GCP's Veo for the video generation (veo 2, IIUC Veo 3 is still behind an allowlist I haven't been able to get approval for), and the GCP ethical AI checks seem to really agressively refuse to generate anything vaugely human (the above penguin included). So elephants, turtles, mice, etc. have been the best result for videos.

Would love to see thoughts -- I know GenAI & Art/Entertainment is a very fraught topic, but I also think there are some fun applications like this where its really not replacing anyone's work.

And a future "Lady's Illustrated Primer" a la Diamond Age would just be so cool.

Comments URL: https://news.ycombinator.com/item?id=44322373

Points: 4

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=44300672

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44296377

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=44287992

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44156236

Points: 1

# Comments: 0

Blog post: https://musings-mr.net/post/ki-storygen-experiment

Comments URL: https://news.ycombinator.com/item?id=44059128

Points: 1

# Comments: 0

Requires you go through a sign up process, but the data just goes to me, I don't use the email for anything other than confirming the email can be read for the sign up link, and then rate limiting the account (5/requests per day).

The story generation prompt still needs some improvement, but had some success in getting the generator to follow more of a "Hero's Journey" type structure, so it prompts moving the narrative forward -- just need to tighten up it resolving conflict if the user doesn't.

I think its interesting seeing what works well/gets generated well, vs whats wonky (images can be great, but the model also seems to get confused and start doing fairly unnatural things, even when its getting fairly tame, normal input)