AI is eating academic research jobs. You can now use any LLM like ChatGPT, Gemini, DeepSeek, or Qwen to find sources, summarize PDFs, generate citations all in one prompt. Here’s the exact mega prompt I use to make any LLM a world-class academic researcher for free:
PROMPT ENGINEERING
-
Adding Configuration to Claude Code and IDE Tools
By
–
To use it, add it to your http://
claude.md if using claude code, or to your claude project if using the web ui, or to your cursorrules etc as appropriate if you're using an IDE. -
Teaching Claude FastHTML Through Code Review Cycles
By
–
The way I wrote this guide was to give Claude a few little apps to write in FastHTML, then I code reviewed them, then I had Claude write an explanation for each code review suggestion so it won't make that mistake again. I only needed fairly minor edits to what it wrote.
-
Reason from Future: Bidirectional Reasoning for LLM Enhancement
By
–
Reason from Future: Reverse Thought Chain Enhances LLM Reasoning This paper introduces a novel reasoning paradigm called Reason from Future (RFF), which generates reasoning paths by bidirectional reasoning that combines top-down planning with bottom-up reasoning accumulation.
-
Cursor’s Code Interface and Natural Language Interoperability Capabilities
By
–
Possibly I agree – in Cursor you're still pretty much looking at code just as before, too. My point is that "add mountains in the background and make the punch look faster and more intense" would just work. It's less about the input to the human and more about interoperability.
-
LLMs and Documentation Should Avoid Excessive Step-by-Step Lists
By
–
Yeah exactly, I weep every time an LLM gives me a bullet point list of the 10 things to click in the UI to do this or that. Or when any docs do the same. "How to upload a file to an S3 bucket in 10 easy steps!"
-
Cursor 1.0: New Features & Improvements
By
–
Cursor released Cursor 1.0 with loads of new improvements:
— 🚨 AI News | TestingCatalog (@testingcatalog) 4 juin 2025
– Bug bot – can automatically review your PRs and catch potential bugs and issues.
– Broader release for Background Agents
– Memories
– MCP one-click install
– New Settings and Dashboard https://t.co/w2Dm1od7mK pic.twitter.com/g3kq06sWp7Cursor released Cursor 1.0 with loads of new improvements:
– Bug bot – can automatically review your PRs and catch potential bugs and issues.
– Broader release for Background Agents
– Memories – MCP one-click install
– New Settings and Dashboard -
Gemini Outperforms Grok on Advanced Mathematical Problem Solving
By
–
Just tried some advanced math manipulations with the AI tools., Still relatively "standard" stuff, although on the graduate school level. Gemini was the most accurate, especially for some tricker calculations. Grok handled easier stuff really well, but stumbled on the more
-
AI-Assisted Coding Workflow: Structuring for Reduced Verification
By
–
Related tweet from earlier where I was describing my own (developing) workflow of "AI Assisted coding" where among other things I try really hard to structure it to decrease verification.
-
SketchAgent: LLM-Powered Stroke-by-Stroke Drawing Without Training
By
–
SketchAgent leverages an off-the-shelf LLM to draw stroke-by-stroke w/o training on any data — instead, the researchers developed a "sketching language" in which a sketch is translated into a numbered sequence of strokes on a grid. SketchAgent also provides textual annotations