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 Reasoning
💡 AI Reasoning
Specific
chain of thought, reasoning models, o1, DeepSeek
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
271
posts in
25.1
ms
ReasoningFlow
: Discourse Structures for Understanding LLM Reasoning
Traces
🖥️
Inference Compute
Content type:
Academic
arxiv.org
·
6d
6 days ago
Actions for ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces
Estimating No-CoT Task-Completion
Time
Horizons of Frontier
AI
Models
🧠
LLMs
lesswrong.com
·
22h
22 hours ago
Actions for Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Less-relevant results
No Token Left Behind: Demystifying Token-in-Token-Out in Miles
🖥️
Inference Compute
Content type:
Blog
lmsys.org
·
1d
1 day ago
·
Hacker News
Actions for No Token Left Behind: Demystifying Token-in-Token-Out in Miles
Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise
AI
🔓
Open-source Models
Content type:
Blog
huggingface.co
·
6d
6 days ago
Actions for Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI
Claude Fable 5 🚀, Gemini 3.5 Live Translate 📱,
scaling
test
time
compute 📈
🕵️
AI Agents
tldr.tech
·
1d
1 day ago
Actions for Claude Fable 5 🚀, Gemini 3.5 Live Translate 📱, scaling test time compute 📈
Transitioning from Azure Language Features to Foundry
Models
🎭
Multimodal AI
techcommunity.microsoft.com
·
23h
23 hours ago
Actions for Transitioning from Azure Language Features to Foundry Models
Fully
open
reproduction of
DeepSeek-R1
🔓
Open-source Models
lemmy.ml
·
2h
2 hours ago
Actions for Fully open reproduction of DeepSeek-R1
Reasoning
RL
in 2026: GRPO, DPO, RLVR, Agentic PO & Beyond
🎮
RL
turingpost.com
·
4d
4 days ago
Actions for Reasoning RL in 2026: GRPO, DPO, RLVR, Agentic PO & Beyond
Tokenminning: Because Tokenmaxxing Is a Bad Idea
🧠
LLMs
tokenminning.com
·
2d
2 days ago
·
Hacker News
Actions for Tokenminning: Because Tokenmaxxing Is a Bad Idea
😸 WATCH: Sleeping on Microsoft
AI
? Whoops.
🕵️
AI Agents
theneurondaily.com
·
21h
21 hours ago
Actions for 😸 WATCH: Sleeping on Microsoft AI? Whoops.
If LLMs are all persona, whose persona are they?
🖥️
Inference Compute
persona.earthpilot.ai
·
12h
12 hours ago
·
Hacker News
Actions for If LLMs are all persona, whose persona are they?
BacteReason: A
Reasoning
Model
for Antimicrobial Resistance Prediction
🖥️
Inference Compute
Content type:
Academic
biorxiv.org
·
4d
4 days ago
Actions for BacteReason: A Reasoning Model for Antimicrobial Resistance Prediction
high-performance classification API (beats GPT-5.4-mini)
🧠
LLMs
Content type:
Discussion
classer.ai
·
3h
3 hours ago
·
Hacker News
Actions for high-performance classification API (beats GPT-5.4-mini)
Researchers say they trained a foundation
model
from scratch for about $1,500
🖥️
Inference Compute
venturebeat.com
·
18h
18 hours ago
·
Hacker News
Actions for Researchers say they trained a foundation model from scratch for about $1,500
The Next
AI
Supply
Chain
Risk: Malicious Skills in Agentic
AI
🕵️
AI Agents
hiddenlayer.com
·
1h
1 hour ago
Actions for The Next AI Supply Chain Risk: Malicious Skills in Agentic AI
OpenAI
launches GPT-Rosalind and biodefense action plan for biological security
🖥️
Inference Compute
4sysops.com
·
6d
6 days ago
Actions for OpenAI launches GPT-Rosalind and biodefense action plan for biological security
Microsoft
open
sources
AI
evaluation framework for enterprise agents
🕵️
AI Agents
Content type:
News
infoworld.com
·
3h
3 hours ago
Actions for Microsoft open sources AI evaluation framework for enterprise agents
Making a
Model
“Think Harder”: The Mechanics of
Test-Time
Compute
🖥️
Inference Compute
Content type:
Blog
medium.com
·
1h
1 hour ago
Actions for Making a Model “Think Harder”: The Mechanics of Test-Time Compute
Does
Reasoning
Preserve Alignment? On the Trustworthiness of Large
Reasoning
Models
🖥️
Inference Compute
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models
Why Claude Produces High-Quality Output: A Developer’s Guide to Token Efficiency and Hallucination…
🧠
LLMs
Content type:
Blog
medium.com
·
6d
6 days ago
Actions for Why Claude Produces High-Quality Output: A Developer’s Guide to Token Efficiency and Hallucination…
Page 2 »
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