Prompt Engineering

Feeds to Scour
SubscribedAll
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··Hacker News

Anthropic Told Claude Not to Blackmail People. It Didn't Work. Here's What Did..

 🔷Anthropic  Content type: Blog
medium.com
·

the dumbest shit I could find in leaked grokipedia prompts

 🟠Hacker News  Content type: Blog

Evaluate your Amazon Nova Sonic voice agent at scale, no microphone required

 🔷Anthropic  Content type: Blog
aws.amazon.com·

AI Literacy Is Not Prompt Literacy. Ann Handley Says It’s Judgment Literacy via @sejournal, @gregjarboe

 🧠AI

AI and EU Harmonization: A Practical Public Sector Use Case from Montenegro

 🛡️AI Safety  Content type: Blog
medium.com·

The Safest-Looking Prompt Is Often the One That Breaks Things

 🛡️AI Safety
siliconopera.com·

Build a Basic AI Agent from Scratch: Long Task Planning

 🤖AI Agents  Content type: Blog
ruxu.dev··Hacker News

Model Evaluations: Prove Your Routing Policy Actually Works

 🔷Anthropic  Content type: Blog
digitalocean.com·

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

 💬LLMs  Content type: Academic
arxiv.org·

Pi Coding Agent

 👨‍💻AI Coding
pi.dev·

Logits as a new monitor for evaluation awareness

 ⚙️MLOps
lesswrong.com··Hacker News

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··Hacker News

Claude Opus 4.8 Review: Better At What’s It Good At, Worse At What It’s Not

 🔷Anthropic  Content type: News
decrypt.co·

The smartest ChatGPT users are putting local AI in front of it — here's why

 🔷Anthropic
tomsguide.com
·

Production AI Playbook: Complex Agent Patterns

 🤖AI Agents  Content type: Blog
blog.n8n.io·

Microsoft Research's Lens proves detailed captions matter more than raw scale for training efficient image generators

 🟢OpenAI  Content type: News
the-decoder.com
·

Why Claude Code’s Agent Loop Is Over 1,400 Lines

 🔷Anthropic

Show HN: Zerostack, an open coding agent optimized for memory footprint

 🟠Hacker News

Claude Opus 4.8 system prompt leaked

 🔷Anthropic

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help