💬 LLM Prompting - inarcissuss

Discussed on Hacker News

🧠LLM Reasoning freeCodeCamp·

What to Do When Reflection Won't Fix Your AI Agent's Output

🔧Tool Use XDA·

I connected my Docker server to local LLMs, and now my self-hosting workstation manages itself

🗣️Large Language Models arXiv·

Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning

🤖AI Assistants Hardware Secrets·

5 ChatGPT and Prompt Engineering Courses That Help You Learn AI the Practical Way

🤖AI Assistants GitHub·

Show HN: Route LLM prompts to cheapest capable model – pydantic-AI and litellm

Covered by DEV Community

Discussed on Hacker News

🧠Claude mathspp.com feed·

Rodrigo Girão Serrão: Write a coding agent from first principles

🧠Context Engineering Hacker News·

Changes that cut our LLM pipeline costs more than model-switching did

Discussed on Hacker News

✍️Prompt Engineering The New Stack·

'"An LLM and a harness": Nvidia''s simple thesis on what agents actually are'

Covered by GitHub

Discussed on DEV

✍️Prompt Engineering Forbes·

Digging Further Into AI System Prompts That Guide How AI Is To Conduct Mental Health Chats

🔌AI APIs Help Net Security·

Hundreds of AI-powered iOS apps found exposing credentials

Covered by 4sysops

✍️Prompt Engineering medium.com

Loop Engineering? Lets clear the things with this

🧠LLM Research MIT Technology Review·

A startup claims it broke through a bottleneck that's holding back LLMs

Covers 2 stories including Attention is all you need (2017)

Covered by 4 sources including Techrights, contextmaestro.com

Discussed on Hacker News and Hacker News

🤖LLM, Agent arXiv·

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

💭Context Management Silicon Opera·

Context Windows Are Bigger and Dumber Than You Think

🧠LLM Tooling GitHub·

chatstore – persistent chat history service for LLM apps, zero infrastructure

Discussed on DEV

🤖Anthropic Claude API arXiv·

Black-Box Forensics for Conversational LLM Agents

🗣️Large Language Models arXiv·

Temperature in LLMs Changes Much More Than Randomness

Steering Claude Code: skills, hooks, subagents and more

Show HN: LoopTroop – local orchestrator for long-running autonomous AI coding

What to Do When Reflection Won't Fix Your AI Agent's Output

I connected my Docker server to local LLMs, and now my self-hosting workstation manages itself

Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning

5 ChatGPT and Prompt Engineering Courses That Help You Learn AI the Practical Way

Show HN: Route LLM prompts to cheapest capable model – pydantic-AI and litellm

Rodrigo Girão Serrão: Write a coding agent from first principles

Changes that cut our LLM pipeline costs more than model-switching did

'"An LLM and a harness": Nvidia''s simple thesis on what agents actually are'

Digging Further Into AI System Prompts That Guide How AI Is To Conduct Mental Health Chats

Hundreds of AI-powered iOS apps found exposing credentials

Loop Engineering? Lets clear the things with this

A startup claims it broke through a bottleneck that's holding back LLMs

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

Context Windows Are Bigger and Dumber Than You Think

chatstore – persistent chat history service for LLM apps, zero infrastructure

Black-Box Forensics for Conversational LLM Agents

CrypFormBench: Benchmarking Formal Analysis Capability of Large Language Models for Cryptographic Schemes