Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
sinhal
sinhal
4
2
5
P(doom)
10%
Follow
hehjfb's profile picture
webbrain-z6m9q4t2's profile picture
Dmil1411's profile picture
6 followers
·
9 following
Zephyr4772
sinhal-joshi-244603275
AI & ML interests
Humans lack the apathy to live forever
Recent Activity
new
activity
33 minutes ago
SupersonicLabs/Julia-1:
Independent test: Julia-1 as an agent step guard (vs Laya) — fast, but never escalates to a human
new
activity
about 1 hour ago
mistralai/Mistral-7B-Instruct-v0.3:
Mistral-7B-Instruct-v0.3 declines to answer about post-cutoff court cases based on the date alone
updated
a dataset
about 1 hour ago
sinhal/Indian_Supreme_Court_Judgments
View all activity
Organizations
None yet
sinhal
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
SupersonicLabs/Julia-1
33 minutes ago
Independent test: Julia-1 as an agent step guard (vs Laya) — fast, but never escalates to a human
#4 opened 33 minutes ago by
sinhal
New activity in
mistralai/Mistral-7B-Instruct-v0.3
about 1 hour ago
Mistral-7B-Instruct-v0.3 declines to answer about post-cutoff court cases based on the date alone
#216 opened about 1 hour ago by
sinhal
New activity in
convaiinnovations/laya
about 5 hours ago
Zero-shot Laya as an agent step guard: agrees when agents say "done", never escalates destructive commands, blind past 320–768 tokens
👀
2
5
#15 opened 19 days ago by
sinhal
New activity in
Ultralytics/YOLO26
about 7 hours ago
YOLO26 laptop benchmark: 8 runtimes, full COCO val, and a Windows power-mode trap
#6 opened about 7 hours ago by
sinhal
New activity in
convaiinnovations/laya
19 days ago
Zero-shot Laya as an agent step guard: agrees when agents say "done", never escalates destructive commands, blind past 320–768 tokens
👀
2
5
#15 opened 19 days ago by
sinhal