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
LLMs
馃挰 LLMs
Specific
large language models, GPT, Claude, foundation models
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
210
posts in
24.9
ms
馃
Agentic AI
llama-dash.dev
路
13h
13 hours ago
One go-to control plane for local
inference
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 One go-to control plane for local inference
馃摎
LMS
GitHub
路
5d
5 days ago
Native
Inference
Engine for macOS 14 or newer
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 Native Inference Engine for macOS 14 or newer
馃
AI
Claude
路
1d
1 day ago
The full
Claude
Desktop experience on AWS, Google Cloud, and Microsoft
Foundry
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 The full Claude Desktop experience on AWS, Google Cloud, and Microsoft Foundry
馃
AI
Baseten
路
1h
1 hour ago
We built the fastest API for GLM-5.2 (280 TPS)
Covers聽
GLM-5.2 (6 minute read)
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 We built the fastest API for GLM-5.2 (280 TPS)
馃
Agentic AI
akarouter.dev
路
1d
1 day ago
Flat per-call
LLM
API gateway (20x cheaper than
Claude
Max)
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 Flat per-call LLM API gateway (20x cheaper than Claude Max)
馃摎
LMS
lector.dev
路
3d
3 days ago
Show HN: Evaluating Local
LLMs
as
language
translators for my app
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 Show HN: Evaluating Local LLMs as language translators for my app
馃
AI
fareedkhan-dev.github.io
路
1d
1 day ago
Train
LLM
from Scratch
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 Train LLM from Scratch
馃敡
Hardware
ludion.ai
路
22h
22 hours ago
WebGPU feature detection was not enough to run small
LLMs
on phones
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 WebGPU feature detection was not enough to run small LLMs on phones
馃
AI
whyopensource.ai
路
9h
9 hours ago
A running list of reasons to move to open source
Covers聽
3聽stories
See all stories this covers
聽including聽
Statement on the US government directive to suspend access to Fable 5 and Mythos 5
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 A running list of reasons to move to open source
馃敡
Hardware
Hacker News
路
6d
6 days ago
Ask HN: What are some good/fast coding
models
for Apple Silicon?
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 Ask HN: What are some good/fast coding models for Apple Silicon?
馃
AI
portal.neuralwatt.com
路
1d
1 day ago
Neuralwatt: Energy-based pricing for AI
inference
. Efficient prompts cost less
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 Neuralwatt: Energy-based pricing for AI inference. Efficient prompts cost less
馃敡
Hardware
graphsignal.com
路
1d
1 day ago
CUDA Profiler for Production
Inference
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 CUDA Profiler for Production Inference
馃
AI
hello-fri-end.github.io
路
5d
5 days ago
Integer
Quantization
: Deep Dive
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 Integer Quantization: Deep Dive
馃敡
Hardware
groq.com
路
1d
1 day ago
Groq Raises Another $650M
Covered by聽
TechCrunch
,
SiliconANGLE
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 Groq Raises Another $650M
馃敡
Hardware
brightray.ai
路
5d
5 days ago
Built Uber aggregator that tracks top AI researchers and leaders
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 Built Uber aggregator that tracks top AI researchers and leaders
馃敡
Hardware
julianrdcosta.substack.com
路
2d
2 days ago
Any Sufficiently
Large
Lookup Table Must Be Conscious
Discussed on
Substack
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 Any Sufficiently Large Lookup Table Must Be Conscious
馃敡
Hardware
rocm.blogs.amd.com
路
6d
6 days ago
Unlocking Extreme AMD Instinct
Inference
with Software-Hardware Co-Optimization
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 Unlocking Extreme AMD Instinct Inference with Software-Hardware Co-Optimization
馃殌
Tech Trends
tokenprices.io
路
1d
1 day ago
I Tracked
LLM
Pricing for 8 Weeks. Here's What the Data Shows
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 I Tracked LLM Pricing for 8 Weeks. Here's What the Data Shows
馃敡
Hardware
xcancel.com
Content type:
Video
路
4d
4 days ago
Fable 5 pushed
Gemma
4 to 255 tok/s on WebGPU
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 Fable 5 pushed Gemma 4 to 255 tok/s on WebGPU
Less-relevant results
馃
Agentic AI
moorcheh.ai
路
11h
11 hours ago
Information-Theoretic Vector Search Is Having Its Moment
Covered by聽
GitHub
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 Information-Theoretic Vector Search Is Having Its Moment
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