Prompt Engineering

Feeds to Scour
SubscribedAll
Scoured 105 posts in 15.4 ms

jianzhichun/permafrost: Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.

 🧠Claude  Content type: Code
github.com··Hacker News
Less-relevant results

Designing Memory for a Minimal Rust Coding Agent, Without a Vector Store

 🧠Claude

Tracing Eval-Awareness Emergence Through Training of OLMo 3

 🎮Reinforcement Learning
lesswrong.com·

manavgup/context-analyzer: Context window usage analyzer for Claude Code — MCP server + interactive dashboard

 🔌API Design  Content type: Code
github.com··Hacker News

local AI agents for Cursor with pre-tuned marketplace/commu

 🧠Claude
locaible.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.

 🧠Claude  Content type: Code
github.com··Hacker News

Why AI code optimization needs production-grounded benchmarks

 👁️Observability  Content type: Blog
datadoghq.com··Hacker News

Can activation verbalizers surface an internal chain of thought?

 🤖AI
lesswrong.com·

Inferoa AI harness claimed 90% cache savings. We ran it and measured 97.8%

 ⚙️AI Infrastructure
zozo123.github.io··Hacker News

desplega-ai/claude-bridge: A simple `claude -p` bridge, drop-in replacement

 🧠Claude  Content type: Code
github.com··Hacker News

Agentic search - retrieval, harness, or model?

 🧮Embedding Models  Content type: Blog

Bad MCP design cost your Agent 5× more tokens

 🕸️WASM  Content type: Discussion

vishal-dehurdle/state-harness: Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness

 🧠Claude  Content type: Code
github.com··Hacker News

Build a Zero-Cost Web Automation Pipeline With OpenRouter, OpenClaw, and MediaUse

 🔌API Design

TjWheeler/deep-memory: A GraphRAG implementation with a Vocabulary system to optimise AI integration

 🧠Claude  Content type: Code
github.com··Hacker News

Revisiting GSM-Symbolic: Do 2026 Frontier Models Still Fail at Confounded Grade School Math?

 🧠Claude
lesswrong.com·

You are here on the AI change curve

 🎮Reinforcement Learning

Airlines Are Using AI To Manufacture Empathy Instead Of Solving Problems — One Passenger Was Sent The Prompt By Mistake

 🧠AI Research

Building Pakistan Notice Helper: A Small AI Tool for a Very Local Safety Problem

 🧠Machine Learning  Content type: Blog
huggingface.co·

No more posts from pwadstrom's subscribed feeds.

Sign up or log in to see more results

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