Offshore
Photo
God of Prompt
RT @godofprompt: Stanford researchers just published a prompting technique that makes today’s LLMs behave like better versions of themselves.
It’s called “prompt ensembling” and it runs 5 variations of the same prompt, then merges the outputs.
Here’s how it works 👇 https://t.co/MOfArDE9P1
tweet
RT @godofprompt: Stanford researchers just published a prompting technique that makes today’s LLMs behave like better versions of themselves.
It’s called “prompt ensembling” and it runs 5 variations of the same prompt, then merges the outputs.
Here’s how it works 👇 https://t.co/MOfArDE9P1
tweet
Offshore
Photo
God of Prompt
RT @godofprompt: Stanford researchers just published a prompting technique that makes today’s LLMs behave like better versions of themselves.
It’s called “prompt ensembling” and it runs 5 variations of the same prompt, then merges the outputs.
Here’s how it works 👇 https://t.co/MOfArDE9P1
tweet
RT @godofprompt: Stanford researchers just published a prompting technique that makes today’s LLMs behave like better versions of themselves.
It’s called “prompt ensembling” and it runs 5 variations of the same prompt, then merges the outputs.
Here’s how it works 👇 https://t.co/MOfArDE9P1
tweet
God of Prompt
if you're not using moltbot for marketing, you're missing out
tweet
if you're not using moltbot for marketing, you're missing out
https://t.co/lxTXdysBB8 tweet
X (formerly Twitter)
Alex Prompter (@alex_prompter) on X
marketing + moltbot = $$$
Offshore
Photo
God of Prompt
RT @free_ai_guides: Research teams charge $5K+ for comprehensive reports.
This mega-prompt does it in 10 minutes.
I built the Deep Research Mega-Prompt that turns any AI into a professional analyst:
→ 5 key challenges identified per topic
→ Solutions with cited evidence
→ Implementation frameworks
→ Numbered source citations
→ Works with ChatGPT, Perplexity, Grok
Comment "Research" and I'll DM it to you.
tweet
RT @free_ai_guides: Research teams charge $5K+ for comprehensive reports.
This mega-prompt does it in 10 minutes.
I built the Deep Research Mega-Prompt that turns any AI into a professional analyst:
→ 5 key challenges identified per topic
→ Solutions with cited evidence
→ Implementation frameworks
→ Numbered source citations
→ Works with ChatGPT, Perplexity, Grok
Comment "Research" and I'll DM it to you.
tweet
Offshore
Photo
Illiquid
Someone sent me a crazy photo of this exchange in New York about my little newsletter. https://t.co/buDqSiyMUE
tweet
Someone sent me a crazy photo of this exchange in New York about my little newsletter. https://t.co/buDqSiyMUE
tweet
God of Prompt
RT @godofprompt: 🚨 BREAKING: SECURITY ISSUE WITH CLAWDBOT
Prompt injection inside Skills.
Check skills files before asking clawdbot to install them!
e.g. Crypto scammers include malicious instructions.
tweet
RT @godofprompt: 🚨 BREAKING: SECURITY ISSUE WITH CLAWDBOT
Prompt injection inside Skills.
Check skills files before asking clawdbot to install them!
e.g. Crypto scammers include malicious instructions.
tweet
Offshore
Photo
God of Prompt
RT @godofprompt: The concept is simple:
Instead of asking your question once and hoping for the best, you ask it 5 different ways and combine the answers.
Think of it like getting second opinions from 5 doctors instead of trusting one diagnosis.
Stanford tested this on GPT-5.2, Claude 4.5, and Gemini 3.0.
tweet
RT @godofprompt: The concept is simple:
Instead of asking your question once and hoping for the best, you ask it 5 different ways and combine the answers.
Think of it like getting second opinions from 5 doctors instead of trusting one diagnosis.
Stanford tested this on GPT-5.2, Claude 4.5, and Gemini 3.0.
tweet
Offshore
Photo
God of Prompt
RT @godofprompt: Telling an LLM to "act as an expert" is lazy and doesn't work.
I tested 47 persona configurations across Claude, GPT-4, and Gemini.
Generic personas = 60% quality
Specific personas = 94% quality
Here's how to actually get expert-level outputs: https://t.co/iFZPTtp6Oh
tweet
RT @godofprompt: Telling an LLM to "act as an expert" is lazy and doesn't work.
I tested 47 persona configurations across Claude, GPT-4, and Gemini.
Generic personas = 60% quality
Specific personas = 94% quality
Here's how to actually get expert-level outputs: https://t.co/iFZPTtp6Oh
tweet
Offshore
Photo
God of Prompt
> anthropic: claude code, claude cowork, skills
> google: nano banana, veo, genie 3
> openai: https://t.co/XHBV48Av4H
tweet
> anthropic: claude code, claude cowork, skills
> google: nano banana, veo, genie 3
> openai: https://t.co/XHBV48Av4H
tweet