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
Prompt Engineering
✍️ Prompt Engineering
prompt design, system prompt, few-shot, chain of thought
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
422
posts in
13.1
ms
How to cut the cost of long AI agent threads (without making the agent dumber)
🤖
AI Agents
Content type:
Blog
viktor.com
·
1d
1 day ago
·
Hacker News
Actions for How to cut the cost of long AI agent threads (without making the agent dumber)
Anthropic Told Claude Not to Blackmail People. It Didn't Work. Here's What Did..
🔷
Anthropic
Content type:
Blog
medium.com
·
5d
5 days ago
Actions for Anthropic Told Claude Not to Blackmail People. It Didn't Work. Here's What Did..
the dumbest shit I could find in leaked grokipedia
prompts
🟠
Hacker News
Content type:
Blog
aionwikipedia.bearblog.dev
·
1d
1 day ago
Actions for the dumbest shit I could find in leaked grokipedia prompts
Evaluate your Amazon Nova Sonic voice agent at scale, no microphone required
🔷
Anthropic
Content type:
Blog
aws.amazon.com
·
1d
1 day ago
Actions for Evaluate your Amazon Nova Sonic voice agent at scale, no microphone required
AI Literacy Is Not
Prompt
Literacy. Ann Handley Says It’s Judgment Literacy via @sejournal, @gregjarboe
🧠
AI
searchenginejournal.com
·
4d
4 days ago
Actions for AI Literacy Is Not Prompt Literacy. Ann Handley Says It’s Judgment Literacy via @sejournal, @gregjarboe
AI and EU Harmonization: A Practical Public Sector Use Case from Montenegro
🛡️
AI Safety
Content type:
Blog
medium.com
·
1d
1 day ago
Actions for AI and EU Harmonization: A Practical Public Sector Use Case from Montenegro
The Safest-Looking
Prompt
Is Often the One That Breaks Things
🛡️
AI Safety
siliconopera.com
·
6d
6 days ago
Actions for The Safest-Looking Prompt Is Often the One That Breaks Things
Build a Basic AI Agent from Scratch: Long Task Planning
🤖
AI Agents
Content type:
Blog
ruxu.dev
·
2d
2 days ago
·
Hacker News
Actions for Build a Basic AI Agent from Scratch: Long Task Planning
Model Evaluations: Prove Your Routing Policy Actually Works
🔷
Anthropic
Content type:
Blog
digitalocean.com
·
5d
5 days ago
Actions for Model Evaluations: Prove Your Routing Policy Actually Works
Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
💬
LLMs
Content type:
Academic
arxiv.org
·
7h
7 hours ago
Actions for Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
Pi Coding Agent
👨💻
AI Coding
pi.dev
·
2d
2 days ago
Actions for Pi Coding Agent
Logits as a new monitor for evaluation awareness
⚙️
MLOps
lesswrong.com
·
5d
5 days ago
·
Hacker News
Actions for Logits as a new monitor for evaluation awareness
ashp15205/guardian-runtime: A
zero-latency
, local-first runtime firewall for LLMs. Intercept every
prompt
and response locally to stop data leaks and runaway token costs.
🤖
AI Agents
Content type:
Code
github.com
·
18h
18 hours ago
·
Hacker News
Actions for ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.
Claude Opus 4.8 Review: Better At What’s It Good At, Worse At What It’s Not
🔷
Anthropic
Content type:
News
decrypt.co
·
2d
2 days ago
Actions for Claude Opus 4.8 Review: Better At What’s It Good At, Worse At What It’s Not
The smartest ChatGPT users are putting local AI in front of it — here's why
🔷
Anthropic
tomsguide.com
·
4d
4 days ago
Actions for The smartest ChatGPT users are putting local AI in front of it — here's why
Production AI Playbook: Complex Agent Patterns
🤖
AI Agents
Content type:
Blog
blog.n8n.io
·
1d
1 day ago
Actions for Production AI Playbook: Complex Agent Patterns
Microsoft Research's Lens proves detailed captions matter more than raw scale for training efficient image generators
🟢
OpenAI
Content type:
News
the-decoder.com
·
1d
1 day ago
Actions for Microsoft Research's Lens proves detailed captions matter more than raw scale for training efficient image generators
Why Claude Code’s Agent Loop Is Over 1,400 Lines
🔷
Anthropic
internals.laxmena.com
·
6d
6 days ago
·
Hacker News
Actions for Why Claude Code’s Agent Loop Is Over 1,400 Lines
Show
HN:
Zerostack
, an open coding agent optimized for memory footprint
🟠
Hacker News
gi-dellav.github.io
·
5d
5 days ago
·
Hacker News
Actions for Show HN: Zerostack, an open coding agent optimized for memory footprint
Claude Opus 4.8
system
prompt
leaked
🔷
Anthropic
gist.github.com
·
5d
5 days ago
·
Hacker News
Actions for Claude Opus 4.8 system prompt leaked
« 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