AI just killed consultants. You can now use LLM like Grok 4 to do everything Deloitte and McKinsey charge $25,000 for: → Ops audits
→ Market research
→ Strategic plans Here are the 3 exact mega-prompts I use to replicate Deloitte-style consulting for free:
LLMS
-
Using LLMs to Replicate Professional Consulting Workflows
By
–
-
LLMs Bridge Math and Coding Cultures in Education
By
–
The Math Olympiad is great, coding is important, accelerating science has tremendous value. But LLMs give a chance for both cultures to contribute in ways that have not been possible for a long time.
-
Transformers: The Standard AI Model’s Strengths and Gaps
By
–
Transformers are the standard model of AI. They’re both:
– The result of a long series of breakthroughs
– Surprisingly powerful
– A big mess
– Missing key pieces -
Liberal Arts Approach to AI Mastery Better Than STEM
By
–
Don't leave AI to the STEM folks. They are often far worse at getting AI to do stuff than those with a liberal arts or social science bent. LLMs are built from the vast corpus human expression, and knowing the history & obscure corners of human works lets you do far more with AI
-
Optimal Number of Examples for Effective AI Prompting
By
–
Depends on the prompt, but yes, I've found that for certain kinds of prompts, 3-10 examples (depending on the length of the example) is the sweet spot. Although there's also another sweet spot where you have like a Claude Project with 30 examples in the knowledge
-
o3 Pro Now Available in LLM Dropdown Menu
By
–
Start a new conversation and you will see o3 pro in the LLM pull down
-
Comparing Local LLM Sizes to Wikipedia Dumps
By
–
Evan Hahn made this handy table comparing the size of different LLMs to the size of Wikipedia dumps in various shapes and formats https://
evanhahn.com/local-llms-ver
sus-offline-wikipedia/
… -
Intelligence: Efficiency Ratio for Acquiring and Deploying Skills
By
–
Intelligence isn't a collection of skills. It's the efficiency with which you acquire and deploy new skills. It's an efficiency ratio. And that's why benchmark scores can be very misleading about the actual intelligence of AI systems.
