abstract257
Re:Ask HN: What would you name your own LLM?
on Saturday June 06, 2026 @02:34AM (#48422027)
That's exactly the analogy I use:
The overeager PhD, knowing everything and having no business sense or expierence.
Re:Show HN: Local-first fast CPU image to text for screenshots, PDFs, ...
on Saturday June 06, 2026 @02:32AM (#48422010)
Thanks
Re:Show HN: Local-first fast CPU image to text for screenshots, PDFs, ...
on Friday June 05, 2026 @09:20AM (#48412158)
Curious how it does on multi-page scanned PDFs vs. single screenshots? The ORT vision/decoder split is the part that usually makes or breaks CPU VLM OCR...
Re:AI Makes Adding Features Faster – So Why Not Add Just One More?
on Monday May 25, 2026 @02:25AM (#48264005)
I know this so well. When is good, good enough?
Re:Ask HN: How do small teams securely share env files?
on Saturday May 23, 2026 @06:42AM (#48246537)
I started to use the croc tool to sent the .env files.
Re:Show HN: Files.md – Open-source alternative to Obsidian
on Tuesday May 19, 2026 @03:45AM (#48190450)
Seams we had a similar urge recently. I like the simplicity of your approach. Will post a show a little later about my approach to notetaking and LLM integration.
Re:Ask HN: How do you choose a model for a task?
on Tuesday May 12, 2026 @08:57AM (#48107612)
Similar for me, just no perplexity and I try to utilize more of Qwen for my coding, instead of cursor/claude, but i see my lazyness. This brings the advantage of having to go back to the basics aswell e.g. Search and Replace instead of just a brainless prompt...
Re:Show HN: Doomscroll the Goverment's UFO Files as One Gigantic Micro...
on Tuesday May 12, 2026 @08:51AM (#48107536)
these 55K pictures is soemthing i can get lost in. thanks for building.