Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Close
You're currently offline. Some features may not work.
Close
Copied to clipboard
Close
Unable to share or copy to clipboard
Close
✖️ Cross-encoders
Reranking, BERT Scoring, Listwise Learning, Pointwise Ranking
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
2516
posts in
63.8
ms
lightonai/next-plaid:
NextPlaid
,
ColGREP
: Multi-vector search, from database to coding agents.
github.com
·
14h
🎨
ChromaDB
Tiny
Recursion
Models (
TRM
): How Tiny Networks With
Recursion
Beat Large Models on Hard Puzzles
pub.towardsai.net
·
15h
🧠
LLM Inference
GPU-Serving
Two-Tower
Models for Lightweight Ads Engagement Prediction
medium.com
·
19h
🔍
FAISS
Random Forest (
ooh.directory
)
ooh.directory
·
3h
🔍
Vector Search Algorithms
Table of
Contents
- Data Engineering for Large Models: Architecture,
Algorithms
& Projects
datascale-ai.github.io
·
15h
·
Discuss:
Lobsters
🔤
Tokenization
You are
probably
overpaying
for intelligence
residuals.bearblog.dev
·
22h
📊
Model Serving Economics
Computer Vision Agent
npmjs.com
·
7h
·
Discuss:
Hacker News
🔍
FAISS
Building a
Smarter
Image Search with Gemini and
Elasticsearch
pub.towardsai.net
·
1h
✨
Gemini
Use more text than one
token
to avoid
neuralese
lesswrong.com
·
21h
🎯
Semantic Tokens
A Survey on
Federated
Fine-Tuning
of Large Language Models
openreview.net
·
20h
·
Discuss:
Hacker News
🦙
Ollama
IndeLLM
: Leveraging protein language models and a scoring function for indel
characterization
and transfer learning: Patterns
cell.com
·
12h
🕯️
Candle
Running an
experiment
with Claude Code
overnight
blog.nolank.ca
·
2h
🚀
Astral
How low-bit
inference
enables
efficient AI
dropbox.tech
·
7h
·
Discuss:
Hacker News
🧠
LLM Inference
LLMs struggle to
verbalize
their
internal
reasoning
lesswrong.com
·
3h
🏆
LLM Benchmarking
Latte on X: "I tested
Seedance
2.0 vs
Kling
3.0. The winner was obvious. Same prompt, same reference image, ...."
x.com
·
26m
·
Discuss:
X
🪄
Prompt Engineering
Decodability
, sensitivity, and
criticality
measured through single-neuron perturbations
nature.com
·
20h
⚡
Hardware Acceleration
how to make your organisation
dumber
- adding the term “adversarial context” to the
lexicon
backofmind.substack.com
·
1h
·
Discuss:
Substack
🎯
Semantic Tokens
We Are the
Average
of Our Models
mercurialsolo.github.io
·
23h
💰
Tokenomics
Readable and
concise
concatenative
programming
cognate-lang.github.io
·
4h
·
Discuss:
Hacker News
🔤
Tokenization
moonshine-ai/moonshine
: Fast and accurate automatic speech recognition (
ASR
) for edge devices
github.com
·
15h
✨
Gemini
Loading...
Loading more...
Page 2 »
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
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