Viewing profile — dandinu
dandinu
HN member- Joined
- Wed, Nov 10, 2010, 2:22 PM UTC
- HN karma
- 22
- Public activity
- 30 items
- HN profile
- View on Hacker News ↗
About dandinu
Recent public activity
-
comment
Comment #48608197
Correction - "Obviously, this is probably a bad idea."
-
comment
Comment #48607471
That's a good question. It started off as pure technical curiosity (in the realm of: will this even work?). but as a side note, I always think of my screen time and the amount we s…
-
comment
Comment #48607420
The method I used in the article is real and is pretty standard. Also, I do a decent amount of distillation and tinkering with weights for work, so I can assure you I did try that …
-
comment
Comment #48602964
Author here. This is a personal weekend project that grew into a working WhatsApp bot. It replies as me to two allowlisted contacts (myself + one friend who knew about the experime…
- story
-
story
Show HN: AlphaGenome Dashboard – Analyze Your Genome with DeepMind AlphaGenome
I built an open-source dashboard for analyzing whole genome sequencing data using Google DeepMind's AlphaGenome API. After getting my WGS data from Dante Labs a few years ago, I wa…
-
comment
Comment #46095922
So the deal with AWE (Address Windowing Extensions) is that it lets 32-bit apps access memory above 4GB by essentially doing manual page mapping. You allocate physical pages, then …
-
comment
Comment #46095909
Oh darn, you're absolutely right (pun intended) about the 32-bit situation. SSE2 is really the "floor" there if you want any kind of reasonable compatibility. I was being a bit opt…
-
comment
Comment #46095294
That's pretty accurate. I'm always amazed how much we move forward with technology, just to later realize we already had it 15 years ago. regarding your question: I have a 32bit XP…
-
comment
Comment #46095174
there is a full technical write-up in the Github repo in "WINDOWS_XP.md": https://github.com/dandinu/llama.cpp/blob/master/WINDOWS_XP.... Sorry for failing to mention that. Link to…
-
story
Show HN: I cross-compiled llama.cpp to run on Windows XP
Had a dumb thought: what if someone in 2003 could run a local LLM on their machine? XP desktop, rolling hills wallpaper, maybe Winamp in the corner—and you just chat with an AI loc…
-
comment
Comment #45927427
I just finished testing the Tinker API launched by Mira Murati's Thinking Machines and I can honestly say, even though it feels unfinished, it's pretty great. The setup is really s…
- story
-
comment
Comment #37186634
Hey everyone, stumbled upon this cool info about AI 'Mega-Personas' I thought I'd write a post on. Everyone knows in AI, 'Personas' are like simulated fictional characters. But 'Me…
- story
-
comment
Comment #37175256
They removed the Azure templates used to deploy as well, so I created an up to date tutorial on how to deploy the whole thing manually: https://tensorthinker.hashnode.dev/privategp…
-
comment
Comment #37175250
Apparently, they removed the Azure templates used to deploy as well, so in frustration, I created an up to date tutorial on how to deploy it manually: https://tensorthinker.hashnod…
-
comment
Comment #37150650
or this: https://github.com/dandinu/azurechatgpt
-
comment
Comment #37150610
I managed to fork it here: https://github.com/dandinu/azurechatgpt
-
comment
Comment #31063050
Well, I guess the myth that Facebook is listening in on your conversations and showing you relevant ads are coming true after all. It feels like a self-fulfilling prophecy.
-
comment
Comment #14058092
Not at all, I like to believe I wanted to convey the exact opposite. I agree that is not something altruistic, exactly my reason for saying this: > I knew I made the right decision…
- story
- story
- story
-
comment
Comment #4726874
Looks interesting and from the video tour I was rather convinced to use it. I saw that it does not have a grid system to snap the columns and text at proportional sizes/positions. …