Live data from Hacker News

Ask HN: What are you working on? (July 2025)

news.ycombinator.com

771–780 of 900 posts

Re: Ask HN: What are you working on? (July 2025)

#771
post #760

I’m building Popgot ( https://popgot.com ): compare unit prices (per oz/sheet/lb) across Costco, Walmart, Target, and Amazon. We normalize fuzzy sizes (“family,” “mega,” multipacks) so you see the actually cheapest option for staples. New: a deep research mode that, on demand, crawls thousands of product pages and uses visual LLMs to read label photos (ingredients, counts, square footage) when the text is messy. Firs…

haha this is fun. shared with my partner.. he spends hours doing it manually

thanks! let me know if y'all have any feedback :)

Re: Ask HN: What are you working on? (July 2025)

#772
post #310

Two things: I am building a Pinterest clone that filters out AI generated imagery[1]. It is built on top of Bluesky so gets the benefit of its large library of well alt-text'd images, which aids with search. Also working on a new kind of social media, where every user is a verified human[2]. The idea is to avoid the problems that sock puppet accounts controlled by the rich and powerful can have on our society. Again,…

But what about the furries :(

Re: Ask HN: What are you working on? (July 2025)

#773

Earlier quoted context omitted.

There's an awful lot of complex navigation, signal processing and trigonometry required here, good luck. What's the fidelity of the sonar in detection of flying mosquitoes?

What do you mean by fidelity? We’re still unsure about the tails in terms of detection probability/false detection rate

I mean the smallest possible detectable object within reasonable distance to make an intercept maneuver.

Say got example that you can only detect an average sized mosquito from a range of 1cm, then you're in random collision only territory.

Re: Ask HN: What are you working on? (July 2025)

#774

I’m building Popgot ( https://popgot.com ): compare unit prices (per oz/sheet/lb) across Costco, Walmart, Target, and Amazon. We normalize fuzzy sizes (“family,” “mega,” multipacks) so you see the actually cheapest option for staples. New: a deep research mode that, on demand, crawls thousands of product pages and uses visual LLMs to read label photos (ingredients, counts, square footage) when the text is messy. Firs…

Interesting idea. Running the LLMs would be expensive. How are you monetising this product? Additionally, since the product is targeted towards frugal customers, do you think you will be able to generate a decent revenue from it?

The LLMs are in fact quite expensive! We run dozen of LLM calls across thousands of products. That's thousands to tens of thousands of calls per search query. The idea is we've got to find the best & the cheapest, and I have spared no expense in doing so. (Plus we have GCP credits.)

Eventually products will overlap between search queries, so we can serve fast and low latency results that have been pre-processed by LLMs. That will be near zero cost. And of course LLM prices will continue to drop quickly.

We monetize via affiliate fees -- you buy something off that list, and we get 1-4% back at no cost to you.

Re: Ask HN: What are you working on? (July 2025)

#775
post #701

Earlier quoted context omitted.

why spend the scarce energy of the battery in addition what's already being spent spinning the propellers

I mean getting rid of drone, and having just laser turret.

Oh my bad, yeah that's a cool idea, think I've seen something along those lines once actually, think it was someone on youtube that built one

Re: Ask HN: What are you working on? (July 2025)

#776

Have you ever wanted to write your life story but found it too overwhelming? I’m developing an app that acts as your personal interviewer, guiding you through your memories and helping you share them with your loved ones. The app is designed for older adults who enjoy reminiscing but struggle to organize their thoughts into a coherent narrative. The goal is to preserve their hard-won insights and pass them down—to fa…

I love this.

My great grandmother, who lived into my 20s, wrote a 10 page memoir about growing up - life stories, people, places etc... And I found it super interesting - I built a vacation around the places last summer.

I asked her daughter/my grandmother to do the same, but she wasn't interested. And then I've thought about the exercise myself - it's hard to think of things in my life that a future great-grandchild might find interesting. And it's not clear if my great-grandmother's story I find interesting, in contrast with financial hardships I did not face? How do you pick out the interesting from the mundane? What is most interesting about today 100 years from now?

And I can see the potential for core interview questions to help draw it out.

Re: Ask HN: What are you working on? (July 2025)

#777

I'm continuing the work on Cellm, an Excel extension that let's you call LLMs in cell formulas like =PROMPT(A1, "Rate the sentiment of the customer feedback as positive, neutral, or negative"), and then drag the formula down to apply the same prompt to thousands of rows. I built it after my girlfriend had to manually classify 7,500 research papers. Cellm automates that kind of repetitive work. Since we added MCP and…

Will keep an eye out for this when it launches.

Re: Ask HN: What are you working on? (July 2025)

#778

After 10 years in defense tech, watching missile attacks in Ukraine and the Middle East made it clear how little most people really get about air defense. So I'm building this simulator which drops you into the operator’s seat. You can test out different scenarios and build an air defense network against various types of threats (stats from real world). Also have Ukraine, Israel-Iran scenarios. The new version is a l…

That seems neat. Modern missile command, haha. After 10 years in defense tech I’m sure you are very aware of this sort of thing, but how worried are you about accidentally leaking some non-public info? I guess one nice thing about public info is, well, it is public, so you can just use whatever’s public.

That's a very valid question! I've based everything on strictly datasheets or datapoints from open sources to be clear on those counts.

Re: Ask HN: What are you working on? (July 2025)

#779

I'm continuing the work on Cellm, an Excel extension that let's you call LLMs in cell formulas like =PROMPT(A1, "Rate the sentiment of the customer feedback as positive, neutral, or negative"), and then drag the formula down to apply the same prompt to thousands of rows. I built it after my girlfriend had to manually classify 7,500 research papers. Cellm automates that kind of repetitive work. Since we added MCP and…

Somewhat similar is https://paradigmai.com .

Kind of looks a bit like what Clay is built to do...?

Re: Ask HN: What are you working on? (July 2025)

#780
post #682
post #506

Earlier quoted context omitted.

Super interesting project! What stage are you at currently? What are the main open challenges that you are facing?

Good question. How does your drone know the difference between a fly and a mosquito (and a human)?

I've watched OP's talk: https://www.youtube.com/watch?v=6ScCG3qTOuc

At 17th minute he explains that they look at microdoppler signatures and can detect mosquitos through the wing flapping frequency. Pretty cool.

Post reply on HN