Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
AI Models
🧠 AI Models
frontier models, LLM, GPT, Claude, Gemini
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
144
posts in
10.7
ms
Claude
Fable 5 silently degrades its own performance on
frontier
AI
work
🏗
System Design Patterns
Content type:
News
Content type:
Blog
mkotlikov.substack.com
·
13h
13 hours ago
·
Substack
Actions for Claude Fable 5 silently degrades its own performance on frontier AI work
LLMs and almost
good
code
🏗️
software engineering
entropicthoughts.com
·
1d
1 day ago
·
Hacker News
Actions for LLMs and almost good code
StereoTales: Multilingual Open-Ended Stereotype Discovery in LLMs
🤖
LLM
Content type:
Blog
research.giskard.ai
·
6d
6 days ago
·
Hacker News
Actions for StereoTales: Multilingual Open-Ended Stereotype Discovery in LLMs
Show HN: One API Key for 45
AI
Models
– Pay per Token, OpenAI Compatible
🤖
Claude Code
modelhub-api.com
·
2d
2 days ago
·
Hacker News
Actions for Show HN: One API Key for 45 AI Models – Pay per Token, OpenAI Compatible
Florian Brand, Prime Intellect research
engineer
, adopts Gemma 4 E4B 6-bit quantized as his primary local Mac
LLM
🤖
AI
Content type:
News
digg.com
·
3d
3 days ago
·
Hacker News
Actions for Florian Brand, Prime Intellect research engineer, adopts Gemma 4 E4B 6-bit quantized as his primary local Mac LLM
If
Claude
Fable stops helping you, you'
ll
never know
🤖
LLMs
Content type:
Blog
jonready.com
·
1d
1 day ago
·
Lobsters
,
Hacker News
Actions for If Claude Fable stops helping you, you'll never know
Running
Qwen
35B MoE at 450k
Context
on a Single 32GB GPU
🤖
AI
local-llm.utop.workers.dev
·
3d
3 days ago
·
Hacker News
Actions for Running Qwen 35B MoE at 450k Context on a Single 32GB GPU
Tokenminning: Because Tokenmaxxing Is a Bad Idea
🤖
AI
tokenminning.com
·
1d
1 day ago
·
Hacker News
Actions for Tokenminning: Because Tokenmaxxing Is a Bad Idea
Guardian Angels:
LLM
Personalization for Productivity and Security
🔐
Cybersecurity
gwern.net
·
3d
3 days ago
·
Hacker News
Actions for Guardian Angels: LLM Personalization for Productivity and Security
Show HN: JazzBench, an
LLM
reasoning benchmark using jazz improvisation
🤖
Claude Code
Content type:
Blog
flatnine.co
·
1d
1 day ago
·
Hacker News
Actions for Show HN: JazzBench, an LLM reasoning benchmark using jazz improvisation
Don't dethrone consciousness
🤖
LLMs
Content type:
News
theintrinsicperspective.com
·
5d
5 days ago
·
Hacker News
Actions for Don't dethrone consciousness
Appraising Artworks with Joins and LLMs (Ultorg Database UI)
🤖
LLM
ultorg.com
·
6d
6 days ago
·
Hacker News
Actions for Appraising Artworks with Joins and LLMs (Ultorg Database UI)
The Data Systems Group (DSG) at MIT
🤖
LLMs
Content type:
Academic
dsg.csail.mit.edu
·
17h
17 hours ago
·
Hacker News
Actions for The Data Systems Group (DSG) at MIT
Agentic search - retrieval, harness, or
model
?
⚙️
AI Applications
Content type:
Blog
softwaredoug.com
·
2d
2 days ago
·
Hacker News
Actions for Agentic search - retrieval, harness, or model?
Anthropic/OpenAI may be spending more than $1000 for every $100 you pay them
🤖
Claude Code
ea.rna.nl
·
3d
3 days ago
·
Hacker News
Actions for Anthropic/OpenAI may be spending more than $1000 for every $100 you pay them
Show HN: AuthAI, an open-source relay for user-authorized
AI
sessions
🤖
LLM
Content type:
Code
github.com
·
7h
7 hours ago
·
Hacker News
Actions for Show HN: AuthAI, an open-source relay for user-authorized AI sessions
Microsoft
AI
boss no longer believes that
AI
will replace human workers
🤖
AI
neowin.net
·
18h
18 hours ago
·
Hacker News
Actions for Microsoft AI boss no longer believes that AI will replace human workers
Speed over Caution: What NSPM-11 Means
🤖
AI Coding
smallwarsjournal.com
·
2d
2 days ago
·
Hacker News
Actions for Speed over Caution: What NSPM-11 Means
Ask HN: Is it feasible to run a
model
on device for complete privacy?
🧠
computer science
Content type:
Discussion
news.ycombinator.com
·
3d
3 days ago
·
Hacker News
Actions for Ask HN: Is it feasible to run a model on device for complete privacy?
DeepSeek enters the fight for token volume, Anthropic continues to dominate spend
🤖
Claude Code
Content type:
Blog
vercel.com
·
2d
2 days ago
·
Hacker News
Actions for DeepSeek enters the fight for token volume, Anthropic continues to dominate spend
« Page 1
·
Page 3 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
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
Browse
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