Article
From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output
•
17
Wassim Trabelsi PRO
wath5
AI & ML interests
AI Engineer NLP & Computer Vision
Recent Activity
upvoted
an
article
about 1 hour ago
From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output
liked
a model
10 days ago
moonshotai/Kimi-K2.5
Organizations
upvoted
an
article
about 1 hour ago
upvoted
an
article
5 days ago
Article
Community Evals: Because we're done trusting black-box leaderboards over the community
- +5
•
58
upvoted
an
article
17 days ago
Article
RexRerankers: SOTA Rankers for Product Discovery and AI Assistants
•
44
upvoted
4
articles
21 days ago
Article
One Year Since the “DeepSeek Moment”
•
55
Article
How We Built a Semantic Highlight Model To Save Token Cost for RAG
•
64
Article
Differential Transformer V2
•
41
Article
Open Responses: What you need to know
-
- +2
•
105
upvoted
an
article
29 days ago
Article
The Optimal Architecture for Small Language Models
•
116
upvoted
an
article
2 months ago
Article
Curating datasets directly on the Hub
•
22
upvoted
2
articles
3 months ago
Article
Continuous batching from first principles
- +1
•
324
Article
Diffusers welcomes FLUX-2
- +6
•
178
upvoted
an
article
4 months ago
Article
Introducing RTEB: A New Standard for Retrieval Evaluation
- +4
•
135
upvoted
2
papers
4 months ago
upvoted
3
articles
5 months ago
Article
Gaia2 and ARE: Empowering the community to study agents
- +9
•
127
Article
RexBERT: Encoders for a brave new world of E-Commerce
•
50
Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
•
755
upvoted
an
article
8 months ago
Article
Training and Finetuning Embedding Models with Sentence Transformers v3
•
264
upvoted
an
article
9 months ago
Article
AI Personas: The Impact of Design Choices
•
15
upvoted
an
article
10 months ago
Article
Introducing smolagents: simple agents that write actions in code.
- +1
•
1.17k