Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Building on HF
3
1
8
River Rider
PRO
RiverRider
Follow
LiteMind's profile picture
keblezhu's profile picture
webxos's profile picture
12 followers
ยท
12 following
Space-Bacon
AI & ML interests
Computational semiotics is empirically proven. It takes three to tango ๐๐ชฉ๐บ
Recent Activity
reacted
to
their
post
with ๐
about 12 hours ago
A single forward pass of the frozen Qwen-2.5-7B model plus a lightweight classifier reaches 0.866 plus or minus 0.011 AUC on the full TruthfulQA-MC2 benchmark. No adapters. No fine-tuning. No extra parameters on the backbone. This is the strongest hidden-state truthfulness detector reported on the benchmark to date. The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead. You can watch the underlying latent geometry in action right here: https://huggingface.co/spaces/RiverRider/srt-nla-av-v1-demo Full code, artifacts, and reproduction steps are in the repository: https://github.com/space-bacon/SRT Try the Glass Box https://huggingface.co/spaces/RiverRider/srt-nla-demo
posted
an
update
4 days ago
A single forward pass of the frozen Qwen-2.5-7B model plus a lightweight classifier reaches 0.866 plus or minus 0.011 AUC on the full TruthfulQA-MC2 benchmark. No adapters. No fine-tuning. No extra parameters on the backbone. This is the strongest hidden-state truthfulness detector reported on the benchmark to date. The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead. You can watch the underlying latent geometry in action right here: https://huggingface.co/spaces/RiverRider/srt-nla-av-v1-demo Full code, artifacts, and reproduction steps are in the repository: https://github.com/space-bacon/SRT Try the Glass Box https://huggingface.co/spaces/RiverRider/srt-nla-demo
updated
a Space
5 days ago
RiverRider/srt-nla-demo
View all activity
Organizations
RiverRider
's models
9
Sort:ย Recently updated
RiverRider/srt-nla-av-gemma2-2b-v1
Feature Extraction
โข
Updated
6 days ago
โข
51
RiverRider/srt-nla-av-llama32-3b
Feature Extraction
โข
Updated
6 days ago
โข
58
RiverRider/srt-nla-av-v1
Feature Extraction
โข
Updated
9 days ago
โข
91
โข
3
RiverRider/srt-adapter-v22c_a050
Updated
13 days ago
RiverRider/srt-adapter-v21a
Updated
13 days ago
RiverRider/srt-adapter-v18
Updated
13 days ago
RiverRider/srt-adapter-v8a
Feature Extraction
โข
Updated
13 days ago
โข
253
โข
2
RiverRider/zooL4nD3r-v0.1
Feature Extraction
โข
Updated
21 days ago
โข
19
RiverRider/srt-adapter-v1.0
Feature Extraction
โข
Updated
26 days ago
โข
47