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
LLM prompts, Claude, GPT, instructions
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
253
posts in
5.8
ms
Claude
vs
GPT-4
: Which AI API Is Better for Developers? (2026)
🔬
Anthropic
kalyna.pro
·
5d
5 days ago
·
DEV
Actions for Claude vs GPT-4: Which AI API Is Better for Developers? (2026)
Comparing
Claude
Fable 5's
system
prompt
to Opus 4.8
🔬
Anthropic
Content type:
Blog
twelvetables.blog
·
1d
1 day ago
·
Hacker News
Actions for Comparing Claude Fable 5's system prompt to Opus 4.8
Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 (@elder_plinius)
🔬
Anthropic
xcancel.com
·
6h
6 hours ago
·
Hacker News
Actions for Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 (@elder_plinius)
Local Agentic Programming on the Cheap:
Claude
Code + Ollama + Gemma4
💬
LLMs
kdnuggets.com
·
5h
5 hours ago
Actions for Local Agentic Programming on the Cheap: Claude Code + Ollama + Gemma4
A free diagnostic for the
Claude
Certified Architect exam
🔬
Anthropic
Content type:
Discussion
Content type:
Tutorial
claudecertifiedarchitects.com
·
1d
1 day ago
·
Hacker News
Actions for A free diagnostic for the Claude Certified Architect exam
Measuring Embedding Drift: Why Hybrid Search Saves Stale Models.
🎯
Fine-Tuning
pub.towardsai.net
·
13h
13 hours ago
Actions for Measuring Embedding Drift: Why Hybrid Search Saves Stale Models.
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
Assessing Automated
Prompt
Injection
Attacks in Agentic Environments
🔐
Cryptography
Content type:
Academic
arxiv.org
·
15h
15 hours ago
Actions for Assessing Automated Prompt Injection Attacks in Agentic Environments
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.
💬
LLMs
Content type:
Code
github.com
·
1d
1 day 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.
Initial impressions of
Claude
Fable 5
💬
LLMs
simonwillison.net
·
19h
19 hours ago
·
Hacker News
Actions for Initial impressions of Claude Fable 5
Prompt
Injection
in RAG Agentic
Systems
💬
LLMs
ulad.net
·
2d
2 days ago
·
Hacker News
Actions for Prompt Injection in RAG Agentic Systems
Prompt
Caching Doesn't Just Save Money. It Lets You Run 20K-Token
System
Prompts.
🔬
Anthropic
hackernoon.com
·
6d
6 days ago
Actions for Prompt Caching Doesn't Just Save Money. It Lets You Run 20K-Token System Prompts.
Presentation: Beyond
Prompting
:
Context
Engineering
and Memory Management for AI Systems at Scale
💬
LLMs
Content type:
News
infoq.com
·
7h
7 hours ago
Actions for Presentation: Beyond Prompting: Context Engineering and Memory Management for AI Systems at Scale
Claude
Fable 5 and Mythos 5 pricing: Anthropic's new $10/$50 top tier
🔬
Anthropic
aipricing.guru
·
1d
1 day ago
·
Hacker News
Actions for Claude Fable 5 and Mythos 5 pricing: Anthropic's new $10/$50 top tier
Context
Engineering
Is the Skill That Actually Ships Reliable AI Agents
💬
LLMs
haloproject.gumroad.com
·
3d
3 days ago
·
DEV
Actions for Context Engineering Is the Skill That Actually Ships Reliable AI Agents
Anthropic
Claude
Fable 5 | AINews
🔬
Anthropic
news.smol.ai
·
1d
1 day ago
Actions for Anthropic Claude Fable 5 | AINews
Automate Writing Your
LLM
Prompts
💬
LLMs
towardsdatascience.com
·
5d
5 days ago
Actions for Automate Writing Your LLM Prompts
Contextual
Identity Laundering: How
Claude
’s Image Refusal Can Be Routed Through Web Search
🔬
Anthropic
lesswrong.com
·
2d
2 days ago
Actions for Contextual Identity Laundering: How Claude’s Image Refusal Can Be Routed Through Web Search
How You Fool AI Mirrors How Your Boss Fools You - 36 Kr
🔬
Anthropic
eu.36kr.com
·
6d
6 days ago
Actions for How You Fool AI Mirrors How Your Boss Fools You - 36 Kr
OpenAI unveils Lockdown Mode to protect sensitive data from
prompt
injection
attacks
🔐
Hardware Security
techcrunch.com
·
3d
3 days ago
·
Hacker News
Actions for OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
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