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
馃 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
145
posts in
5.4
ms
How LLMs work | Practical Leaders
聽
馃
LLM
practical-leaders.com
路
6d
6 days ago
路
Hacker News
Actions for How LLMs work | Practical Leaders
Why LLMs (still) lack taste
聽
馃
AI
beyondtheprior.com
路
1d
1 day ago
路
Hacker News
Actions for Why LLMs (still) lack taste
Timing Trick Cuts Energy Used in
LLM
Training by Up to 14 Percent
聽
馃
LLM
聽
Content type:
News
spectrum.ieee.org
路
12h
12 hours ago
路
Hacker News
Actions for Timing Trick Cuts Energy Used in LLM Training by Up to 14 Percent
defai-digital/ax-engine
: Apple Silicon
LLM
runtime supporting Gemma 4 and
Qwen
3.6 MTP modes
聽
馃
AI
聽
Content type:
Code
github.com
路
22h
22 hours ago
路
Hacker News
Actions for defai-digital/ax-engine: Apple Silicon LLM runtime supporting Gemma 4 and Qwen 3.6 MTP modes
Humans and LLMs share a mental disorder: Fugue Lock
聽
馃
computer science
vwwwv.org
路
1d
1 day ago
路
Hacker News
Actions for Humans and LLMs share a mental disorder: Fugue Lock
Best explanations of how LLMs work
聽
鈿涳笍
Quantum Computing
聽
Content type:
Blog
vorushin.github.io
路
3d
3 days ago
路
Hacker News
Actions for Best explanations of how LLMs work
A Plea to the Labs: Let the
Models
Diagnose.
聽
馃
LLMs
聽
Content type:
Blog
tangent.bearblog.dev
路
7h
7 hours ago
路
Hacker News
Actions for A Plea to the Labs: Let the Models Diagnose.
Integrate on-device
AI
models
into your app using Core
AI
- WWDC26 - Videos
聽
馃
AI
developer.apple.com
路
2d
2 days ago
路
Hacker News
Actions for Integrate on-device AI models into your app using Core AI - WWDC26 - Videos
Apple WWDC On-Device
AI
Deep Dive -
Google
Docs
聽
馃
AI
gist.is
路
1h
1 hour ago
路
Hacker News
Actions for Apple WWDC On-Device AI Deep Dive - Google Docs
Initial impressions of
Claude
Fable 5
聽
馃
Claude Code
simonwillison.net
路
23h
23 hours ago
路
Hacker News
Actions for Initial impressions of Claude Fable 5
What Are Tokens in LLMs?
聽
馃
LLM
聽
Content type:
Blog
bearisland.dev
路
3d
3 days ago
路
Hacker News
Actions for What Are Tokens in LLMs?
A system programmer鈥檚 guide to
LLM
inference
聽
馃
LLM
聽
Content type:
Blog
blog.xiangpeng.systems
路
2d
2 days ago
路
Hacker News
Actions for A system programmer鈥檚 guide to LLM inference
know the mother tongue of your LLMs
聽
馃
LLM
mothertoken.inigoimaz.com
路
1d
1 day ago
路
Hacker News
Actions for know the mother tongue of your LLMs
Show HN: Audit any
AI/data
pairing with Veritrooper
聽
鈿欙笍
AI Applications
veritrooper.com
路
5d
5 days ago
路
Hacker News
Actions for Show HN: Audit any AI/data pairing with Veritrooper
Pythagora-io/gpt-pilot
Compromised on GitHub - Shai-Hulud Credential Stealer Blocked by Python Linter
聽
馃攼
Cybersecurity
聽
Content type:
Blog
stepsecurity.io
路
8h
8 hours ago
路
Hacker News
Actions for Pythagora-io/gpt-pilot Compromised on GitHub - Shai-Hulud Credential Stealer Blocked by Python Linter
Dario Amodei says
frontier
models
should face mandatory third-party testing for cyber, bio, and autonomy risks, in addition to overall transparency requirements...
聽
鈿欙笍
platform engineering
techmeme.com
路
3h
3 hours ago
Actions for Dario Amodei says frontier models should face mandatory third-party testing for cyber, bio, and autonomy risks, in addition to overall transparency requirements...
Researchers trained an open source
AI
search agent, Harness-1, that outperforms
GPT-5.4
on recalling relevant information
聽
馃
AI
venturebeat.com
路
2d
2 days ago
路
Hacker News
Actions for Researchers trained an open source AI search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information
Research Proposal: Decoupled
RISC-LLM
Architectures
via Circadian Synaptic Consolidation
聽
鈿欙笍
AI Applications
aermia.com
路
4d
4 days ago
路
Hacker News
Actions for Research Proposal: Decoupled RISC-LLM Architectures via Circadian Synaptic Consolidation
Claude
Fable 5 silently degrades its own performance on
frontier
AI
work
聽
馃彈
System Design Patterns
聽
Content type:
News
聽
Content type:
Blog
mkotlikov.substack.com
路
15h
15 hours ago
路
Substack
Actions for Claude Fable 5 silently degrades its own performance on frontier AI work
Purpose-built local
AI
agents
聽
馃
Claude Code
聽
Content type:
Blog
samihonkonen.com
路
2d
2 days ago
路
Hacker News
Actions for Purpose-built local AI agents
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