Adding more reasoning tokens is not going to fix this
PROMPT ENGINEERING
-
MCP Course: Build Rich-Context AI Apps with Anthropic
By
–
New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic @AnthropicAI and taught by Elie Schoppik @eschoppik, its Head of… pic.twitter.com/NDZZzP8QYb
— Andrew Ng (@AndrewYNg) 14 mai 2025New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic @AnthropicAI and taught by Elie Schoppik @eschoppik
, its Head of -
ChatGPT Reveals Its System Prompt Blueprint
By
–
ChatGPT just revealed its internal system prompt. It’s the blueprint that powers everything it does and now you can study it, tweak it, and build better prompts. I broke it all down in this System Prompt Guide. Like + comment “System” and I’ll DM it to you.
-
ai.txt: Domain-Specific Language for AI Internet Interactions
By
–
ai.txt: A Domain-Specific Language for Guiding AI Interactions with the Internet
Link: https://
arxiv.org/pdf/2505.07834 -
Long-Term Memory for Improving Email Assistant Agent Interactions
By
–
Long-term memory is a vital part of building great agent interactions. Here's David Xu showing how to use it to make an email assistant improve over time! This ties in beautifully with the prior human in the loop steps, as the agent uses the human's edits and rejections to
-
Long-Term Memory for Improving Email Assistant Agents Over Time
By
–
Long-term memory is a vital part of building great agent interactions. Here's David Xu showing how to use it to make an email assistant improve over time! This ties in beautifully with the prior human in the loop steps, as the agent uses the human's edits and rejections to
-
LLM domain training should produce manuals not weight updates
By
–
yes exactly, "training" an LLM on a target domain should output a manual not a weight diff.
-
AGI Development Accelerated Through AI-Powered Code Tools
By
–
We may be delaying AGI if we keep playing this game, but OK! I used Copy Canvas and here is my addition to the Cartographer. Coding this in two sentences… drastic & wild times! @NoamShazeer I nominate you : )https://t.co/aSnBdVELBc https://t.co/4jWOHnib2n pic.twitter.com/vhnzxOkumb
— Oriol Vinyals (@OriolVinyalsML) 13 mai 2025We may be delaying AGI if we keep playing this game, but OK! I used Copy Canvas and here is my addition to the Cartographer. Coding this in two sentences… drastic & wild times! @NoamShazeer I nominate you : ) https://
g.co/gemini/share/c
6ad686dbd1c
… -
Tool Use Reliability Improvements in AI Systems
By
–
you share any examples? tool use should be much more reliable now