5/ Research Plan Prompt: "Act as an AI Research Assistant and craft a clear and actionable plan for gathering, analyzing, and presenting data on {topic}. Include efficient use of time and tools."
PROMPT ENGINEERING
-
Using Grok as an AI Productivity Consultant for Research and Writing
By
–
4/ Productivity Hacks
— God of Prompt (@godofprompt) 26 février 2025
Prompt:
"Role-play as an AI Productivity Consultant. Explain how to save time in research and writing by using Grok for summarizing papers, brainstorming ideas, and applying writing frameworks." pic.twitter.com/v3a1zeOIrK4/ Productivity Hacks Prompt: "Role-play as an AI Productivity Consultant. Explain how to save time in research and writing by using Grok for summarizing papers, brainstorming ideas, and applying writing frameworks."
-
Using AI as a Writing Coach for Research Notes
By
–
2/ Writing Workflow
— God of Prompt (@godofprompt) 26 février 2025
Prompt:
"You are an AI Writing Coach. Suggest a workflow using bullet points for transforming scattered research notes on {topic} into a cohesive article. Include templates for structuring arguments." pic.twitter.com/JQjIbAUarJ2/ Writing Workflow Prompt: "You are an AI Writing Coach. Suggest a workflow using bullet points for transforming scattered research notes on {topic} into a cohesive article. Include templates for structuring arguments."
-
10 Powerful Prompts for Grok 3 Research
By
–
Grok 3 is the most powerful AI research chatbot. But most people don’t know how to use it. Here are 10 powerful prompts to revolutionize your research:
-
Anthropic Claude Sonnet 3.7: Drop-in Replacement with Extended Thinking
By
–
One thing I really like about @AnthropicAI models – on release of Sonnet 3.7, everything is well-supported, and it's a drop in replacement for other models we used to use. Enabling thinking was also easy, and we're already testing it + modifying our prompts as necessary.
-
New Deep Research Toggle for ChatGPT macOS App
By
–
1/2 ChatGPT app for macOS will be getting a new toggle for Deep Research on top of the prompt bar
-
LLM thinking toggle routing and model selection strategies
By
–
Interesting. Maybe it's one with thinking always-on and one always-off. Similar to the IBM Granite model with the toggle. And on the Claude website, maybe they have another "small" LLM routing the user prompt / controlling that toggle.
-
Inference-Time Scaling: Prompt Modification vs Sampling and Verification
By
–
*One might argue that modifying prompts (eg classic "think step by step") counts as inference-time scaling due to the extra output tokens. So in that sense they use inference-time scaling.
I should have been more clear: I meant specifically sampling techniques + using a verifier. -
System Card Analysis: Reasoning Implementation via RL Toggle
By
–
What a week! Just read the system card, and it looks like they implemented reasoning via RL. My guess is the thinking on/off toggle is likely a system prompt. I wonder if they added inference-time scaling like o1 or if it’s just RL like R1. Anyone found details on that?
-
LangSmith Adds Metadata Grouping for Experiment Analysis
By
–
📊 You can now group LangSmith experiments by metadata to get valuable insights!
— LangChain (@LangChain) 25 février 2025
We’ve added a new view that allows you to group experiment results by metadata. Compare the performance of your evaluations across different segments (eg. user segments or subject areas) to pinpoint… pic.twitter.com/2nGo2bm7JYYou can now group LangSmith experiments by metadata to get valuable insights! We’ve added a new view that allows you to group experiment results by metadata. Compare the performance of your evaluations across different segments (eg. user segments or subject areas) to pinpoint