Skip to main content
Scour
Discover
Docs
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
ChatGPT
🤖 ChatGPT
Specific
LLM, Prompting, OpenAI, Conversational AI
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
51
posts in
58.0
ms
🧠
Claude
wmyskxz.cn
·
4d
4 days ago
代码之外周刊（第 179 期）：人最大的行动阻力，是「想清楚再说」
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for 代码之外周刊（第 179 期）：人最大的行动阻力，是「想清楚再说」
💭
Context Management
Silicon Opera
·
4d
4 days ago
Context Windows Are Bigger and Dumber Than You Think
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Context Windows Are Bigger and Dumber Than You Think
🔓
Vulnerability Research
The New Stack
·
1d
1 day ago
Azul wants to find your unpatched JVMs before
AI
does
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Azul wants to find your unpatched JVMs before AI does
📊
LLM Evaluation
giskard.ai
·
1d
1 day ago
Giskard:
LLM
esting platform for preventing hallucinations and security issues
Covers
3 stories
See all stories this covers
including
Garak, LLM Vulnerability Scanner
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Giskard: LLM esting platform for preventing hallucinations and security issues
🧠
Claude
arXiv
·
6d
6 days ago
REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection
🤖
Agentic Engineering
generalliquidity.com
·
2d
2 days ago
SharpeBench: A luck-robust benchmark for
AI
trading agents
Covers
2 stories
See all stories this covers
including
Towards a Science of AI Agent Reliability
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for SharpeBench: A luck-robust benchmark for AI trading agents
🔓
Vulnerability Research
Azul
·
6d
6 days ago
Get Your Java Estate Ready for the Growing Agentic
AI
Threat
Covered by
The New Stack
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Get Your Java Estate Ready for the Growing Agentic AI Threat
🔌
AI APIs
arXiv
·
2d
2 days ago
When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration
🌀
Hallucination
arXiv
·
2d
2 days ago
Fixed RAG Compression Collapses Measured Reader Scaling
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Fixed RAG Compression Collapses Measured Reader Scaling
🧠
Claude
arXiv
·
2d
2 days ago
Evaluation of Small
Language
Models
for Arabic
Language
Processing
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Evaluation of Small Language Models for Arabic Language Processing
💬
LLM Prompting
arXiv
·
1d
1 day ago
Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
« Page 2
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Discover
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help
Like
Save
Not for me
Report