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
Inference Compute
🖥️ Inference Compute
Specific
inference-time compute, test-time compute, scaling inference
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
126
posts in
9.7
ms
Apple's Foundation
Models
can now use third-party LLMs (Claude, Gemini) [video]
💡
AI Reasoning
developer.apple.com
·
3d
3 days ago
·
Hacker News
Actions for Apple's Foundation Models can now use third-party LLMs (Claude, Gemini) [video]
Does
Reasoning
Preserve Alignment? On the Trustworthiness of Large
Reasoning
Models
💡
AI Reasoning
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models
Token Spend Out of Control? The Case for Smarter Routing
🔧
Tool Use
Content type:
News
Content type:
Blog
blog.bytebytego.com
·
3d
3 days ago
Actions for Token Spend Out of Control? The Case for Smarter Routing
Nvidia and Microsoft partner to bring agentic AI systems to PCs and data centers
💡
AI Reasoning
4sysops.com
·
6d
6 days ago
Actions for Nvidia and Microsoft partner to bring agentic AI systems to PCs and data centers
Two Leaps to 1000 Tokens/s on a 1T-Parameter
Model
: On
Inference
Systems, Execution Boundaries, and
Co-Design
🕵️
AI Agents
Content type:
Blog
tilert.ai
·
2d
2 days ago
·
Hacker News
Actions for Two Leaps to 1000 Tokens/s on a 1T-Parameter Model: On Inference Systems, Execution Boundaries, and Co-Design
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
AVIS: Adaptive
Test-Time
Scaling
for Vision-Language Models
🎭
Multimodal AI
Content type:
Academic
arxiv.org
·
11h
11 hours ago
Actions for AVIS: Adaptive Test-Time Scaling for Vision-Language Models
NVIDIA Nemotron 3 Ultra now available on Amazon SageMaker JumpStart
🕵️
AI Agents
Content type:
Blog
aws.amazon.com
·
6d
6 days ago
Actions for NVIDIA Nemotron 3 Ultra now available on Amazon SageMaker JumpStart
The emerging AI x TechBio stack (120 companies mapped)
🕵️
AI Agents
mmc.vc
·
2d
2 days ago
·
Hacker News
Actions for The emerging AI x TechBio stack (120 companies mapped)
Revisiting GSM-Symbolic: Do 2026 Frontier
Models
Still Fail at Confounded Grade School Math?
💡
AI Reasoning
lesswrong.com
·
5d
5 days ago
Actions for Revisiting GSM-Symbolic: Do 2026 Frontier Models Still Fail at Confounded Grade School Math?
Tearing into ChatGPT's container environment
💡
AI Reasoning
Content type:
Blog
pncnmnp.github.io
·
2d
2 days ago
Actions for Tearing into ChatGPT's container environment
Anthropic’s AI fearmongering isn’t what it appears to be
🧠
LLMs
Content type:
Blog
techzine.eu
·
6d
6 days ago
Actions for Anthropic’s AI fearmongering isn’t what it appears to be
Posting for authoring
💡
AI Reasoning
turingpost.com
·
3d
3 days ago
Actions for Posting for authoring
No Token Left Behind: Demystifying Token-in-Token-Out in Miles
💡
AI Reasoning
Content type:
Blog
lmsys.org
·
1d
1 day ago
·
Hacker News
Actions for No Token Left Behind: Demystifying Token-in-Token-Out in Miles
🤖 AI Agents Weekly: Microsoft's Seven MAI
Models
, Gemma 4 12B, NVIDIA Nemotron 3 Ultra, Agents' Last Exam, Devin Desktop, and More
🕵️
AI Agents
Content type:
News
nlp.elvissaravia.com
·
5d
5 days ago
Actions for 🤖 AI Agents Weekly: Microsoft's Seven MAI Models, Gemma 4 12B, NVIDIA Nemotron 3 Ultra, Agents' Last Exam, Devin Desktop, and More
Dropout-GRPO: Variational Stochasticity for Continuous Latent
Reasoning
💡
AI Reasoning
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning
A one-parameter
model
that gets 100% on ARC-AGI-2
💡
AI Reasoning
eitanturok.github.io
·
6d
6 days ago
·
Hacker News
Actions for A one-parameter model that gets 100% on ARC-AGI-2
NIBRT selected by WHO as European Regional Training Centre for Biomanufacturing
💡
AI Reasoning
siliconrepublic.com
·
2d
2 days ago
Actions for NIBRT selected by WHO as European Regional Training Centre for Biomanufacturing
Google's new
open
model
DiffusionGemma generates text from noise instead of word by word
🔓
Open-source Models
the-decoder.com
·
20h
20 hours ago
Actions for Google's new open model DiffusionGemma generates text from noise instead of word by word
fix(config): allow thinkingLevelMap in persisted
model
schema · openclaw/openclaw@a1f1895
💡
AI Reasoning
Content type:
Code
github.com
·
4d
4 days ago
Actions for fix(config): allow thinkingLevelMap in persisted model schema · openclaw/openclaw@a1f1895
« 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