💬 Prompt Engineering - shaoyi

Less-relevant results

If LLMs are all persona, whose persona are they?

🧠LLM Reasoning

persona.earthpilot.ai··Hacker News

MLPerf and the rise of latency-aware LLM benchmarking

🧠LLM Reasoning

edn.com·

Humans and LLMs share a mental disorder: Fugue Lock

🧠LLM Reasoning

vwwwv.org··Hacker News

Running LLM Inference on Kubernetes: What It Actually Takes

🧠Knowledge Representation Blog

fairwinds.com·

FOD#155: Continual Learning in LLMs: Why AI Models Need Sleep

🤝Agent Systems

turingpost.com·

Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 (@elder_plinius)

🤖AI-native development

xcancel.com··Hacker News

Turn specs into evals for any agent with ASSERT

🧠LLM Reasoning

malware.news·

A wild idea: Abstract reality using ontology

🕸Ontology Discussion

news.ycombinator.com··Hacker News

Context Engineering Is Eating Prompt Engineering

🧠LLM Reasoning Blog

medium.com

Kimi Code: Next-Gen AI Code Agent for Terminal & IDE

🤖AI-native development

kimi.com

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.

🤝Agent Systems Code

github.com··Hacker News

Tiberius: A Security Testing Framework for LLM Applications in Java

🤖AI-native development

foojay.io·

AI worm prototype shows attackers don’t need Mythos to take over your network

🤖AI-native development

csoonline.com·

Running Qwen 35B MoE at 450k Context on a Single 32GB GPU

🤖AI-native development

local-llm.utop.workers.dev··Hacker News

Melanie Mitchell: What We Get Wrong About AI

🧠LLM Reasoning

yalereview.org··Substack, Hacker News, Hacker News

For Robotaxis, Safety Must Be Built In, Not Bolted On

🧠LLM Reasoning Blog

blogs.nvidia.com·

Adrarsh Divakaran: Building AI Agents in Python

🧠LLM Reasoning Blog

blog.adarshd.dev·

The Bill Arrives: How to Manage Agentic AI Costs at Scale

🤖Agentic Systems Blog

cockroachlabs.com·

What's in the Box? A Field Guide to AI Models

Deep Learning Weekly: Issue 458

If LLMs are all persona, whose persona are they?

MLPerf and the rise of latency-aware LLM benchmarking

Humans and LLMs share a mental disorder: Fugue Lock

Running LLM Inference on Kubernetes: What It Actually Takes

FOD#155: Continual Learning in LLMs: Why AI Models Need Sleep

Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 (@elder_plinius)

Turn specs into evals for any agent with ASSERT

A wild idea: Abstract reality using ontology

Context Engineering Is Eating Prompt Engineering

Kimi Code: Next-Gen AI Code Agent for Terminal & IDE

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.

Tiberius: A Security Testing Framework for LLM Applications in Java

AI worm prototype shows attackers don’t need Mythos to take over your network

Running Qwen 35B MoE at 450k Context on a Single 32GB GPU

Melanie Mitchell: What We Get Wrong About AI

For Robotaxis, Safety Must Be Built In, Not Bolted On

Adrarsh Divakaran: Building AI Agents in Python

The Bill Arrives: How to Manage Agentic AI Costs at Scale