Viewing profile — samagra14
samagra14
HN member- Joined
- Wed, Sep 25, 2019, 6:21 PM UTC
- HN karma
- 15
- Public activity
- 40 items
- HN profile
- View on Hacker News ↗
About samagra14
No profile information was provided.
Recent public activity
-
story
Show HN: Small OSS experiment to re-create the 2.5B valued Instinct assistant
Was just trying to understand how much time it would take to recreate this end to end. THis was somewhat useful esp with adding the vault and oauths. Will release them too. But it …
-
comment
Comment #48930396
i am talking about evolution of trust being the best thing on the internet btw
-
comment
Comment #48930249
best thing i have seen on the internet till date ... It was just wow.
-
comment
Comment #48930222
I am hoping vibe coding would bring back the fun era of the internet!
- story
-
comment
Comment #47700054
I spent the morning reading all 244 pages. About 180 of them are getting zero coverage. Here are the findings that deserve more attention from anyone building with AI esp the psych…
- story
-
story
Ask HN: What Inference Server do you use to host TTS Models?
All the examples I have are highly unoptimized - For eg, Modal Labs uses FastAPI - https://modal.com/docs/examples/chatterbox_tts\ BentoML also uses FastAPI like service - https://…
-
comment
Comment #43973909
I am unsure as to why this is still not a native EKS feature. I understand that there can be a cascading node failure but that can be easily detected and fixed. Karpenter version t…
-
comment
Comment #43779371
In this post, we’ll break down what NCCL does, why it’s critical for multi-GPU training, and how to tackle one of its common challenges – the dreaded “watchdog timeout” error.
- story
- story
- story
- story
- story
- story
-
comment
Comment #42630958
Sounds interesting! I love all these edge experiments. But as long as there is architecture dependent code for models, I feel these edge experiments can't fully express their stron…
-
comment
Comment #42519837
The approach is purely cryptographic and requires three base axioms 1. A guess of what type of script it is - Logopgraphic (Chinese)or Syllabic (Linear Greek) or Segmental (English…
- story
- story
- comment
- story
-
comment
Comment #42406032
GPU workloads cannot be tested on local machines and need access to specialised hardware and specific types of GPU machines and production deployments need Docker containerised fil…
- story
-
comment
Comment #42400616
At Tensorfuse we have been rewriting and restructuring our docs as they have become a huge dump of how to guides rather than being something that is navigable and understandable. A…