DEV Community

#research

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Trained a Vulnerability Detection Model. It Was Reading Comments, Not Code.

I Trained a Vulnerability Detection Model. It Was Reading Comments, Not Code.

Comments
3 min read
I Said My Model Was Cheating. The Follow-up Says It Was Mostly Real.

I Said My Model Was Cheating. The Follow-up Says It Was Mostly Real.

Comments 1
2 min read
Instagram Content Moderation: User-level observational study

Instagram Content Moderation: User-level observational study

Comments
3 min read
Notion Zotero Integration: An Honest Setup Guide

Notion Zotero Integration: An Honest Setup Guide

Comments
8 min read
We measured the LLM signature in 398,296 Korean journal abstracts

We measured the LLM signature in 398,296 Korean journal abstracts

Comments
4 min read
Caltech's Physics AI Ditches Transformers for Neural Operators

Caltech's Physics AI Ditches Transformers for Neural Operators

Comments
3 min read
Frontier Models Fail at Research-Level Reasoning

Frontier Models Fail at Research-Level Reasoning

Comments
2 min read
Anthropic's Claude Is Designing Proteins That Work

Anthropic's Claude Is Designing Proteins That Work

Comments
2 min read
When RAG Failure Labels Depend on Retrieval Depth

When RAG Failure Labels Depend on Retrieval Depth

Comments 1
4 min read
Can EnvHarness Turn Static Worlds Into Real Agent Training Grounds?

Can EnvHarness Turn Static Worlds Into Real Agent Training Grounds?

Comments
2 min read
Frontier Models Hit a Wall on Research Thinking

Frontier Models Hit a Wall on Research Thinking

Comments
2 min read
Labs are ditching factual knowledge for reasoning speed

Labs are ditching factual knowledge for reasoning speed

Comments
2 min read
Deciding the criteria for excluding an AI-collected research topic candidate

Deciding the criteria for excluding an AI-collected research topic candidate

Comments
9 min read
We Counted AI Hallucination Disclosures in Every 10-K. Pharma Outnumbered Software 29 to 10.

We Counted AI Hallucination Disclosures in Every 10-K. Pharma Outnumbered Software 29 to 10.

1
Comments
8 min read
Compression Is Understanding: Two July Papers That Prove AI Gets Smarter by Compressing Physics

Compression Is Understanding: Two July Papers That Prove AI Gets Smarter by Compressing Physics

Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.