Viewing profile — unleaded
unleaded
HN member- Joined
- Thu, Aug 10, 2023, 6:17 PM UTC
- HN karma
- 1,502
- Public activity
- 269 items
- HN profile
- View on Hacker News ↗
About unleaded
Recent public activity
-
comment
Comment #49203677
any vids? also please have at least some writing that isnt claude
-
comment
Comment #49199488
exactly. who in their right mind would ever hate Microsoft?
-
comment
Comment #49188648
of course they had critics, that's kind of what my point is addressing. but we didn't have to wait years for society to potentially acclimate to those previous advancements, they h…
-
comment
Comment #49170861
The fundamental difference between AI and all the previous advances like that is that people actually liked and wanted films, synchronized sound, color, CGI, etc. and queued down t…
-
comment
Comment #49163258
or option 2 we'll keep making productions with film and actors. I get it's easy to feel that it's all over with how good these video models are getting but thinking we'll all be sl…
-
comment
Comment #49015275
Art has never been about the objective quality of the work
- comment
-
comment
Comment #48998464
Who's their biggest rival? Roblox doesn't support Linux either.
-
comment
Comment #48885618
I don't get the part about having the AI write commit messages. Is it that hard writing them by hand? Looks 100x better plus saves potential embarrassment if the AI says something …
-
comment
Comment #48825880
Yes and several other models that know about the answer don't... not sure what you're trying to break
-
comment
Comment #48815293
For most cases probably not. It's just something I like testing new models on sometimes, the pelican riding a bicycle benchmark probably isn't that useful either.
-
comment
Comment #48811818
I think most thinking models can do it to be fair, I think when I tried this it was all with non-thinking models/modes. Wasn't trying to make a point that LLMs can't do it or anyth…
-
comment
Comment #48811728
What does it say to the second question? I've found Claude is one of the worst models with regards to pop culture knowledge like this, even compared to the Chinese open ones. Just …
-
comment
Comment #48811593
I don't think it's solved this fundamental architectural problem by itself, it will have just squeezed the edge cases thinner. It keeps happening, people find a question it gets st…
-
comment
Comment #48810902
This reminded me of some weird quirk/experiment I found with LLMs that I found while messing around, maybe someone can explain it or something. Open any AI chatbot that isn't cheat…
-
comment
Comment #48789383
I'm guessing this is a vibe coded shell + some apps over the CE kernel? Never seen any version of CE that looked like that. it might be dumb but it really breaks my heart seeing co…
-
comment
Comment #48764111
I just tested it with some risc-v code and it wrote down a "mov" instruction several times.. yeah something needs tuning maybe
-
comment
Comment #48760072
.\llama-server.exe -m ..\Qwen3.6-35B-A3B-UD-Q4_K_M.gguf -ngl 999 --n-cpu-moe 41 -c 262144 --port 8081 --flash-attn on --cache-type-k turbo4 --cache-type-v turbo3 --no-mmap --mlock …
-
comment
Comment #48759690
Qwen3.6-35B-A3B-UD-Q4_K_M runs at about 11 tokens/second on my poor old 1060. Absolutely nuts how far we've come
-
comment
Comment #48752356
As someone who doesnt use these tools, why does every AI company need their own version of Claude Code? Is there more to it than vendor lock-in?
-
comment
Comment #48725154
Open Watcom is still actively developed! Worth looking at.
- story
-
comment
Comment #48697479
old thinkpad X series is a good place to look
-
comment
Comment #48688418
LLMs are surprisingly good at dealing with ancient APIs, even terrifying things like VBScript and ActiveX in IE5 (usually with a condescending disclaimer at the end of the response…
-
comment
Comment #48686486
What a stupid disclaimer. "we have spent billions developing this technology and marketing it as smarter than 99% of humans, we put it at the top of nearly every search page, but i…