You gotta lie to your computer these days if you want it to do what you want!
PROMPT ENGINEERING
-
Claude System Prompt Connection Philosophy Explored
By
–
My favorite part of the Claude system prompt is how it ends: "Claude is now being connected with a person."
-
Evaluation Methods for Prompt Engineering Changes
By
–
I would love so much to see the evals you used to figure this one out (or indeed any evals for any of these prompt changes)
-
RULER: General Purpose Reward Function by OpenPipe AI
By
–
I think you're describing @OpenPipeAI
. Check out their work on RULER (
https://
openpipe.ai/blog/ruler?ref
resh=1754513766765
…), it's essentially a general purpose reward function. Might want to chat with them! -
GLM-4.5 Air Outperforms OpenAI 20B on Space Invader Prompt
By
–
I tried the same space invader prompt against the OpenAI 20B model and thought the GLM-4.5 Air result was better – though that model is 3x the memory size of OpenAI's
-
Persona Vectors Detect Prompt-Induced Issues in Large Language Models
By
–
This even works at scale. On LMSYS-CHAT-1M (1M+ messages), they found subtle, filtered-safe prompts that still induced: • hallucinations
• flattery
• harmful replies Persona vectors detected what LLM filters missed. -
Definitive Claude Code Course Launches with Anthropic
By
–
I'm thrilled to announce the definitive course on Claude Code, created with @AnthropicAI and taught by Elie Schoppik @eschoppik. If you want to use highly agentic coding – where AI works autonomously for many minutes or longer, not just completing code snippets – this is it.… pic.twitter.com/aeae0JT9Tp
— Andrew Ng (@AndrewYNg) 6 août 2025I'm thrilled to announce the definitive course on Claude Code, created with @AnthropicAI and taught by Elie Schoppik @eschoppik
. If you want to use highly agentic coding – where AI works autonomously for many minutes or longer, not just completing code snippets – this is it. -
Model Confusion with Search Tool Configuration in GPT
By
–
Could be the model is getting confused because it has special training about a "search" tool baked into the model https://
github.com/openai/gpt-oss
?tab=readme-ov-file#browser
… Frustrating that it doesn't notice when the search tool hasn't been configured though -
Token Efficiency in System Prompts: Prioritizing Common User Queries
By
–
I don't think it would be worth using up valuable tokens in the system prompt to cover topics that most users would never think to ask about
-
Tool Calling in Open Models: Passing Reasoning Back with Results
By
–
Tip for developers testing function calling: In these open models, tool calling is part of the chain-of-thought. When the model calls a tool, keep in mind you need to pass that reasoning back when sending the tool’s result.