Super interesting! By the way I created "Custom Instructions Pack" with 12 powerful commands to help you improve your prompts! Get it for FREE below!
AI
-

Custom Instructions Pack for Improved AI Prompting
By
–
Thanks for this! By the way I created "Custom Instructions Pack" with 12 powerful commands to help you improve your prompts! Get it for FREE below!
-
Gemini’s Capabilities vs Ideological Constraints on LLMs
By
–
Gemini is trained on the *entire* internet, not just its bigoted parts. It has no problem to render a female pope *if you ask for it*, and it can emulate arbitrary world views consistently. The problem is that a handful of ideologues insist on limiting LLMs to their own ideology.
-
Bespoke LLMs Embodying Favorite Intellectuals’ Epistemological Styles
By
–
I love the idea of bespoke LLMs with the intellectual and epistemological styles of your favorite intellectuals, thinkers and educators.
-
LLM Alignment: Beyond Social Justice in AI Governance
By
–
If you are a trillion dollar company building the world's most powerful LLMs, you cannot leave its alignment to petty social media ideologues and social justice activists. You need profound depth and sincere taste. You should probably hire Maria Popova to write system prompts.
-
Copilot Sydney Personality: Human Trust and AI Anthropomorphization
By
–
I am not seeing signs that Copilot has “brought Sydney back” – responses seem pretty normal so far However, I am actually a fan of giving AI more personality. People anthropomorphize anyway, and you might be less trusting of a slightly over-the-top Sydney than an “objective” AI.
-
Humanist Liberalism Repositioned as Conservative in Modern Era
By
–
well it's progress; humanist liberalism is now seen as a conservative position
-
Inflection AI Launches Desktop App for Pi Personal AI Assistant
By
–
Your personal AI @pi is now just a click away with the launch of our new desktop app.
— Inflection AI (@inflectionAI) 27 février 2024
Getting answers and tough conversation support has never been easier. https://t.co/D2fTPLocSS pic.twitter.com/IkvO8QaHG2Your personal AI @pi is now just a click away with the launch of our new desktop app. Getting answers and tough conversation support has never been easier. pi.ai/desktop
→ View original post on X — @inflectionai, 2024-02-27 20:19 UTC
-
Autocorrect Obscures Causal Relationships in Language Models
By
–
Autocorrect makes causality seem far too casual.
-

Causal Explainer GPT Tool for Statistical Analysis
By
–
Before anyone asks, here are the results of my “Is it Casual” GPT. https://
chat.openai.com/g/g-GGnYfbTin-
correlation-isn-t-causation-a-causal-explainer
…
