Viewing profile — alasr
alasr
HN member- Joined
- Fri, Feb 11, 2022, 2:42 AM UTC
- HN karma
- 289
- Public activity
- 74 items
- HN profile
- View on Hacker News ↗
About alasr
Recent public activity
-
comment
Comment #49205524
- See "Llama.cpp vs Ollama"[0] and "Llama.cpp vs LM Studio"[1] for a high-level features comparison and find out which one suite you best (check out the "Target Users" category[0][…
- comment
-
comment
Comment #49124097
Why do you think that just sharing a link to an earlier HN post means 'promoting' someone? I referenced the HN post because I found that it's less about Martin Shkreli himself and …
-
comment
Comment #49123207
Earlier on HN: Martin Shkreli breaks down the collapse of Situational Awareness - https://news.ycombinator.com/item?id=49119380 Edit: added context
-
comment
Comment #49122028
From Valhalla's design notes[0]: > For the primitive types longer than 32 bits (long and double), it is not guaranteed that reads and writes from different threads (without suitabl…
- story
-
comment
Comment #48495583
> Why does it need to be beautiful? "Beauty", IMO, signifies the idea that you're doing `something` for its own the sake where "its own sake" approximate the idea of getting/being …
-
comment
Comment #48469845
Regarding the the current HN post's title, I like the TFA original title ("The New 20% Time, Minus the Time") better, along its sub-title; IMHO, the current HN post's title ("Googl…
- comment
- story
- comment
- comment
- story
-
comment
Comment #47378463
GitHub repo.: https://github.com/kfoynt/neural_doom
- story
-
comment
Comment #47378246
Just a small nitpik with the following part of your post. > As the paper suggests: ... This is not a paper; it's just a blog post which is mentioned in this post's URL (i.e. .../bl…
- story
- story
-
comment
Comment #46806330
I think you're reading the docs correct: one still uses "lms server [command]" command to manage an LM Studio (LMS) server.
-
comment
Comment #46802252
> What exactly is the difference between lms and llmsterm? With lms, LM Studio's frontend GUI/desktop application and its backend LLM API server (for OpenAI compatibility API endpo…
-
comment
Comment #46726531
> I think I kind of have an idea what the author was doing, but not really. Me neither; However, just like the rest I can only speculate (given the available information): I guess …
-
comment
Comment #45794902
I haven't used any LLM deep research tools in the past; today, after reading this HN post, I gave Tongyi DeepResearch a try to see how it performs on a simple "research" task (in a…
-
comment
Comment #45705552
https://archive.is/lgDXT
- story
-
comment
Comment #45511468
Regarding C# and Java part of your comment, I think you might want to take a look at the following Wikipedia entries: - Microsoft Java Virtual Machine: https://en.wikipedia.org/wik…