Gabor Herget
@gherget
Followers
1K
Following
1K
Media
490
Statuses
2K
Grew Ranorex to 115 employees and sold it. Now acquiring & building apps with AI agents. π¨ https://t.co/sRJ4W5z7oU π https://t.co/YQvozPNBn1 ποΈ https://t.co/J6ixqbESg5
My investing guide π
Joined September 2008
I built an HN daily digest for myself a year ago. It keeps me on track every day. And I am not getting lost in comments anymore. I could have built this in a one-liner prompt with cron with the latest agents, but great to have it as an email. Repo: https://t.co/63VEglSAV8
0
0
0
Is it just me, or would you also like to chat to edit and manage your website? I now use Telegram to edit my website. zero servers, zero coding. About a year ago I started a small side business with a friend, and his team built a WordPress site. Recently I decided to let
0
0
0
Not needed at all! My openclaw reverse engineered withtelescope .com api using my token, and I pay there per request. Withtelescope is basically a SEMRUSH wrapper, I assume. The data looks the same. I get all the data for a few tokens when I need it.
i sometimes joke that i joined Ahrefs just to use the API without paying for an Enterprise plan. well, now you can too ;) vibe-coders, rejoice: the .@ahrefs API is now available on ALL paid plans! time to build that SEO dashboard you've always dreamed of π₯°
0
0
0
That is useful for self-hosting web apps!
ONCE is back! It's now a full-fledged application server for running dockerized web apps, like Campfire/Writebook/Fizzy or your own vibe-coded adventures. Zero-downtime upgrades, scheduled backups, and a gorgeous TUI with hyperdrive graphics. Enjoy! https://t.co/WaLSMms2fr
0
0
0
1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers. We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy
205
660
5K
8K
2K
17K
Interesting, will give Hermes a go for a local llm test
@gherget @sudoingX @NousResearch Your RTX 4080 rig (Ultra 7 265KF + 48GB DDR5) destroys the 3060 demo: ~91 tokens/sec generation on Qwen 3.5 9B Q4 (vs 29 t/s), prefill 1000+ t/s, full GPU offload in 16GB VRAM with massive context headroom. Can even run 20-27B models quantized. Yes, perfect for Hermes
0
0
0
I see a big potential in building tools for the Office & admin space. This is where my local stack with Claude Cowork and Openclaw works the best. I can delegate work, and it gets done most of the time. This is also where the greatest potential lies for building something, given
0
0
1
Why use AI now when the job is getting replaced? As long as you are working, let ai help you with your tasks and use the freed time to learn a new skill
0
1
0
Even though the outlook for devs is not good in the long-term, we are in high demand now to build the AI products to replace the workforce π
9/10 likelihood of AI replacement for these jobs. If you are in this category, start using AI now and pivot.
0
0
1
9/10 likelihood of AI replacement for these jobs. If you are in this category, start using AI now and pivot.
Karpathy released an AI exposure index for the job market for a few hours. Repo and live demo got removed, but someone was quick to fork it: Gh: https://t.co/lA9ZcQwr87 Demo:
1
0
0
Karpathy released an AI exposure index for the job market for a few hours. Repo and live demo got removed, but someone was quick to fork it: Gh: https://t.co/lA9ZcQwr87 Demo:
5 minutes ago, @karpathy just dropped karpathy/jobs! he scraped every job in the US economy (342 occupations from BLS), scored each one's AI exposure 0-10 using an LLM, and visualized it as a treemap. if your whole job happens on a screen you're cooked. average score across
0
0
0
smart idea
My OpenClaw bot builds websites & mails a postcard with a QR link to local businesses on autopilot... You can use it to land new customers without a single cold call, here's how it works: - Finds 100s of local businesses via Google Maps - Builds each one a custom website in
0
0
0
Go from "hello world" to "hello claw!" π¦ We're hosting a Build-A-Claw extravaganza in the #NVIDIAGTC Park Mon-Thur where you can BYOD or buy a DGX Spark on-site and our NVIDIA experts will help you install @OpenClaw. See you there! π Full details π https://t.co/hbtboQ5RYp
50
72
648
Anthropic shipped generative UI for Claude. I reverse-engineered how it works and rebuilt it for PI. Extracted the full design system from a conversation export. Live streaming HTML into native macOS windows via morphdom DOM diffing. Article: https://t.co/C3FLF3JB8Z Repo:
42
81
1K
π¨BREAKING: Someone just open-sourced a headless browser that runs 11x faster than Chrome and uses 9x less memory. It's called Lightpanda and it's built from scratch specifically for AI agents, scraping, and automation. Not a Chromium fork. Not a hack. A completely new browser
263
938
8K
OK, well. I ran /autoresearch on the the liquid codebase. 53% faster combined parse+render time, 61% fewer object allocations. This is probably somewhat overfit, but there are absolutely amazing ideas in this.
99
171
3K