welanes
Joined 11 years ago
Karma
1,147
Submissions
265
Member since
May 2
Recent submissions
Comment · 2 months ago
Comment · 3 months ago
I released Humm[1] last week. Realtime speech-to-text with a focus on privacy. No backend, no telemetry - just a fast, nicely designed app wrapping local stt models.
[1] https://humm.so/
Comment · 7 months ago
Data extraction: https://simplescraper.io
A project that I launched on HN that became a business. Simplescraper rode the no-code wave of a few years back ('instant structured data without parsing html').
Now working on increasing the surface area for AI agents: MCP support, screenshots API, and (experimentally) x402[1]
Comment · 8 months ago
Whoops, developer mode needs to be toggled on. Just updated the instructions
Comment · 8 months ago
Made a quick tool so you can check if your extensions are on the list: https://extensioncheck.val.run
1. Go to chrome://extensions and toggle Developer mode on (so IDs are visible)
2. Select all text on the page with your mouse and copy
3. Paste it into the tool
It parses the IDs and warns you if any are among the 287 spyware extensions.
Comment · 1 year ago
This guide may be useful for anyone interested in building their own spec-compliant MCP server: https://simplescraper.io/blog/how-to-mcp.
Albeit, it's a few weeks old so already in need of an update!
Comment · 1 year ago
> I'm always a bit wary of approaching these ideas though because I feel like nobody would ever pay for small web stuff?
Build them and find out! There's almost always room for something better, and if what you build is that, then some people will pay.
Unless the tools have large running costs, consider offering them for free (at least at first).
A few things are likely to happen:
Nobody cares enough to sign up – fine, zero users, zero costs.
People use it but don’t stick around – ask them what would make the tool more valuable.
People use it a lot – great, now you can charge for the value.
Two examples come to mind: spaced repetition app Mochi and markdown editor Typora. Mochi is $5 a month, I think. Typora was free and is now a $15 one-time purchase.
Both compete with free alternatives and still have many paying users.
Comment · 1 year ago
1. Clicking the box programmatically – possible but inconsistent
2. Outsourcing the task to one of the many CAPTCHA-solving services (2Captcha etc) – better
3. Using a pool of reliable IP addresses so you don't encounter checkboxes or turnstiles – best
I run a web scraping startup (https://simplescraper.io) and this is usually the approach[0]. It has become more difficult, and I think a lot of the AI crawlers are peeing in the pool with aggressive scraping, which is making the web a little bit worse for everyone.
[0] Worth mentioning that once you're "in" past the captcha, a smart scraper will try to use fetch to access more pages on the same domain so you only need to solve a fraction of possible captchas.
Comment · 2 years ago
Making my data extraction Saas (https://simplescraper.io) more LLM friendly.
Markdown extraction, improved Google search, workflows - search for this terms, visit the first N links, summarize etc. Big demand for (or rather, expectation of) this lately.
Comment · 2 years ago
Things are much easier for one-person startups these days—it's a gift.
I remember building a todo app as my first SaaS project, and choosing something called Stormpath for authentication. It subsequently shut down, forcing me to do a last-minute migration from a hostel in Japan using Nitrous Cloud IDE (which also shut down). Just pain upon pain.[1]
Now, you can just pick a full-stack cloud service and run with it. My latest SaaS[2] is built on Google Cloud, so Authentication, Cloud Functions, Docker containers, logging, etc straight out of the box.
Not to mention, modern JavaScript and CSS are finally good. With so many fewer headaches, it’s a great time to build.
[1] Admittedly, I was new to software dev and made some rather poor tech choices
If time allowed, I'd focus on the AI photo and video generation. Have seen friends hit $500 relatively quickly by targeting niches.
Sounds like a played out category, but if you look closer it's a bit of a potemkin village - many incumbents are not that good or haven't kept up with the latest models.
Each year it gets more crowded out there, but almost always room for better.