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
LLMs
🧠 LLMs
Specific
Large Language Models, GPT, Transformers
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
346
posts in
6.2
ms
Research Proposal: Decoupled
RISC-LLM
Architectures via Circadian Synaptic Consolidation
🤖
AI Agents
aermia.com
·
4d
4 days ago
·
Hacker News
Actions for Research Proposal: Decoupled RISC-LLM Architectures via Circadian Synaptic Consolidation
What's in the Box? A Field Guide to AI
Models
🤖
AI Agents
Content type:
Blog
iankduncan.com
·
2d
2 days ago
Actions for What's in the Box? A Field Guide to AI Models
Claude Fable 5 is Mythos for the masses
✨
vibe coding
Content type:
Blog
techzine.eu
·
1d
1 day ago
Actions for Claude Fable 5 is Mythos for the masses
Quantum circuits help AI overcome memory limitations with minimal new parameters
🤖
AI Agents
phys.org
·
4d
4 days ago
Actions for Quantum circuits help AI overcome memory limitations with minimal new parameters
Less-relevant results
Context windows in AI: why every
token
is a budget decision
🤖
AI Agents
Content type:
Blog
redis.io
·
8h
8 hours ago
Actions for Context windows in AI: why every token is a budget decision
Start Up No.2680: Apple to relaunch Siri *again*, jet fuel shortage hits Brazil, astrophysicists see
LLM
future, and more
✨
vibe coding
Content type:
Blog
theoverspill.blog
·
2d
2 days ago
Actions for Start Up No.2680: Apple to relaunch Siri *again*, jet fuel shortage hits Brazil, astrophysicists see LLM future, and more
Why Shrinking an AI
Model
Often Makes It More Useful
🤖
AI Agents
siliconopera.com
·
3d
3 days ago
Actions for Why Shrinking an AI Model Often Makes It More Useful
Show HN: Run
Llama.cpp
In-Process from Java with Project Panama FFM
✨
vibe coding
deemwar-products.github.io
·
5d
5 days ago
·
Hacker News
Actions for Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM
Pro
Wrestlers Are Fighting in Libraries Now, and It’s Actually for a Good Cause
✨
vibe coding
Content type:
News
vice.com
·
1d
1 day ago
Actions for Pro Wrestlers Are Fighting in Libraries Now, and It’s Actually for a Good Cause
The Order Matters: Sequential
Fine-Tuning
of
LLaMA
for Coherent Automated Essay Scoring
✨
vibe coding
Content type:
Academic
arxiv.org
·
23h
23 hours ago
Actions for The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring
The Edge
LLM
Offload Story
✨
vibe coding
semiengineering.com
·
6d
6 days ago
Actions for The Edge LLM Offload Story
Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn’t Be This Good
✨
vibe coding
Content type:
Blog
towardsai.net
·
2d
2 days ago
Actions for Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn’t Be This Good
PagedAttention vs Traditional KV Cache: How
vLLM
Reinvented GPU Memory for
LLM
Inference
🤖
AI Agents
Content type:
Blog
medium.com
·
2d
2 days ago
Actions for PagedAttention vs Traditional KV Cache: How vLLM Reinvented GPU Memory for LLM Inference
MLPerf and the rise of latency-aware
LLM
benchmarking
🤖
AI Agents
edn.com
·
5d
5 days ago
Actions for MLPerf and the rise of latency-aware LLM benchmarking
Revisiting GSM-Symbolic: Do 2026 Frontier
Models
Still Fail at Confounded Grade School Math?
🤖
AI Agents
lesswrong.com
·
5d
5 days ago
Actions for Revisiting GSM-Symbolic: Do 2026 Frontier Models Still Fail at Confounded Grade School Math?
KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe
Flash-Attention
for
llama.cpp
, fully measured on real hardware.
🐛
Bug Bounty
Content type:
Code
github.com
·
11h
11 hours ago
·
Hacker News
Actions for KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
DiffusionGemma: The Developer Guide
✨
vibe coding
Content type:
Blog
developers.googleblog.com
·
1d
1 day ago
Actions for DiffusionGemma: The Developer Guide
Running
LLM
Inference on Kubernetes: What It Actually Takes
🤖
AI Agents
Content type:
Blog
fairwinds.com
·
5d
5 days ago
Actions for Running LLM Inference on Kubernetes: What It Actually Takes
Token4Token —
pay-per-token
inference on Gnosis + Swarm
🐛
Bug Bounty
t4t.eth.link
·
1d
1 day ago
·
Hacker News
Actions for Token4Token — pay-per-token inference on Gnosis + Swarm
Alignment Defends
LLMs
from Property Inference Attacks
🐛
Bug Bounty
Content type:
Academic
arxiv.org
·
23h
23 hours ago
Actions for Alignment Defends LLMs from Property Inference Attacks
Sign up or log in to see more results
Sign Up
Login
« 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