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
🤖 AI
Broad
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
91
posts in
11.1
ms
Pythia 1.4B reproduces 3.6% of training samples verbatim given 950-token prompts
🔓
Open Source
Content type:
Blog
ret2libc.com
·
4d
4 days ago
·
Hacker News
Actions for Pythia 1.4B reproduces 3.6% of training samples verbatim given 950-token prompts
a desktop GUI to browse, search, & visualize your
vector
databases
🗃
Databases
vectorlens.dev
·
1d
1 day ago
·
Hacker News
Actions for a desktop GUI to browse, search, & visualize your vector databases
The Cosmological Hart-Tipler Conjecture
🔍
AI Interpretability
Content type:
Academic
arxiv.org
·
16h
16 hours ago
·
Hacker News
Actions for The Cosmological Hart-Tipler Conjecture
I open-sourced my UFC prediction
model
, code, and
database
after 5 years of work
⚡
LLM Optimization
mcinerney.ai
·
6d
6 days ago
·
Hacker News
Actions for I open-sourced my UFC prediction model, code, and database after 5 years of work
GPT-2: Too Dangerous To Release (2019)
⚡
LLM Optimization
Content type:
Blog
naokishibuya.github.io
·
1d
1 day ago
·
Hacker News
Actions for GPT-2: Too Dangerous To Release (2019)
Introducing Piper: A Programmable Distributed Training System
⚡
Model Efficiency
Content type:
Academic
Content type:
Blog
syfi.cs.washington.edu
·
13h
13 hours ago
·
Hacker News
Actions for Introducing Piper: A Programmable Distributed Training System
China's Xiaomi MiMo Is Now 15X Faster Than ChatGPT and Claude (4 minute read)
⚡
Model Efficiency
Content type:
News
decrypt.co
·
2d
2 days ago
·
Hacker News
Actions for China's Xiaomi MiMo Is Now 15X Faster Than ChatGPT and Claude (4 minute read)
Running Qwen 35B MoE at 450k Context on a Single 32GB GPU
⚡
LLM Optimization
local-llm.utop.workers.dev
·
4d
4 days ago
·
Hacker News
Actions for Running Qwen 35B MoE at 450k Context on a Single 32GB GPU
"Trust Us" Is Not a Control Surface: Anthropic and the Case for Open Weights
🗃
Databases
trust-us.vercel.app
·
16h
16 hours ago
·
Hacker News
Actions for "Trust Us" Is Not a Control Surface: Anthropic and the Case for Open Weights
Introducing North Mini Code: Cohere’s First
Model
For Developers
✍️
Prompt Engineering
Content type:
Blog
huggingface.co
·
2d
2 days ago
·
Hacker News
Actions for Introducing North Mini Code: Cohere’s First Model For Developers
GGUF vs GPTQ vs AWQ: The Plain-English Guide to
LLM
Quantization (and Which One to Pick)
⚡
LLM Optimization
vettedconsumer.com
·
5d
5 days ago
·
Hacker News
Actions for GGUF vs GPTQ vs AWQ: The Plain-English Guide to LLM Quantization (and Which One to Pick)
Researchers trained an open source
AI
search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information
🗃
Databases
venturebeat.com
·
2d
2 days ago
·
Hacker News
Actions for Researchers trained an open source AI search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information
If Claude Fable stops helping you, you'll never know
✍️
Prompt Engineering
Content type:
Blog
jonready.com
·
1d
1 day ago
·
Lobsters
,
Hacker News
Actions for If Claude Fable stops helping you, you'll never know
Tejas-TA/predikit: The missing bridge between your ML
models
and your
AI
agents.
🐍
Python
Content type:
Code
github.com
·
21h
21 hours ago
·
Hacker News
Actions for Tejas-TA/predikit: The missing bridge between your ML models and your AI agents.
Fine-tuning
vs RAG vs MeMo: Where should
LLM
Knowledge Live?
✍️
Prompt Engineering
pub.towardsai.net
·
4d
4 days ago
Actions for Fine-tuning vs RAG vs MeMo: Where should LLM Knowledge Live?
Claude Fable 5 and new
AI
safety fables
⚡
LLM Optimization
Content type:
News
interconnects.ai
·
1d
1 day ago
·
Hacker News
Actions for Claude Fable 5 and new AI safety fables
"North Mini Code"; open weights, 30B param, Canadian coding
model
⚡
Model Efficiency
Content type:
Blog
cohere.com
·
2d
2 days ago
·
Hacker News
,
Hacker News
Actions for "North Mini Code"; open weights, 30B param, Canadian coding model
Gemma 4 QAT
models
: Optimizing model compression for mobile and laptop efficiency
⚡
LLM Optimization
Content type:
News
Content type:
Blog
blog.google
·
6d
6 days ago
·
Hacker News
Actions for Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency
Claude Fable 5 silently degrades its own performance on frontier
AI
work
⚡
Model Efficiency
Content type:
News
Content type:
Blog
mkotlikov.substack.com
·
1d
1 day ago
·
Substack
Actions for Claude Fable 5 silently degrades its own performance on frontier AI work
Stack Overflow didn't just help
AI
learn
to code
✍️
Prompt Engineering
zozo123.github.io
·
4d
4 days ago
·
Hacker News
Actions for Stack Overflow didn't just help AI learn to code
« 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