"With the shift towards this multi-agent collaboration and orchestration world, you need a neutral substrate that has money, identity, cryptography, and web-of-trust  baked in, to make everything work."
Pablo & Gigi are getting high on glue nostr.
 
Books and articles mentioned:

Saving beauty by Byung-Chul Han
LLMs as a tool for thought by Amelia Wattenberger

In this dialogue:

vibeline & vibeline-ui
LLMs as tools, and how to use them
Vervaeke: AI thresholds & the path we must take
Hallucinations and grounding in reality
GPL, LLMs, and open-source licensing
Pablo's multi-agent Roo setup
Are we going to make programmers obsolete?
"When it works it's amazing"
Hiring & training agents
Agents creating RAG databases of NIPs
Different models and their context windows
Generalists vs specialists
"Write drunk, edit sober"
DVMCP.fun
Recklessness and destruction of vibe-coding 
Sharing secrets with agents & LLMs 
The "no API key" advantage of nostr
What data to trust? And how does nostr help? 
Identity, web of trust, and signing data 
How to fight AI slop
Marketplaces of code snippets 
Restricting agents with expert knowledge 
Trusted sources without a central repository 
Zapstore as the prime example 
"How do you fight off re-inventing GitHub?" 
Using large context windows to help with refactoring 
Code snippets for Olas, NDK, NIP-60, and more
Using MCP as the base 
Using nostr as the underlying substrate 
Nostr as the glue & the discovery layer 
Why is this important? 
Why is this exciting? 
"With the shift towards this multi-agent collaboration and orchestration world, you need a neutral substrate that has money/identity/cryptography and web-of-trust  baked in, to make everything work."
How to single-shot nostr applications 
"Go and create this app" 
The agent has money, because of NIP-60/61
PayPerQ 
Anthropic and the genius of mcp-tools 
Agents zapping & giving SkyNet more money 
Are we going to run the mints? 
Are agents going to run the mints? 
How can we best explain this to our bubble? 
Let alone to people outside of our bubble? 
Building pipelines of multiple agents 
LLM chains & piped Unix tools 
OpenAI vs Anthropic 
Genius models without tools vs midwit models with tools 
Re-thinking software development 
LLMs allow you to tackle bigger problems 
Increased speed is a paradigm shift 
Generalists vs specialists, left brain vs right brain 
Nostr as the home for specialists 
fiatjaf publishing snippets (reluctantly) 
fiatjaf's blossom implementation 
Thinking with LLMs
The tension of specialization VS generalization 
How the publishing world changed
Stupid faces on YouTube thumbnails 
Gaming the algorithm 
Will AI slop destroy the attention economy? 
Recency bias & hiding publication dates 
Undoing platform conditioning as a success metric 
Craving realness in a fake attention world 
The theater of the attention economy 
What TikTok got "right" 
Porn, FoodPorn, EarthPorn, etc. 
Porn vs Beauty 
Smoothness and awe 
"Beauty is an angel that could kill you in an instant (but decides not to)."
The success of Joe Rogan & long-form conversations 
Smoothness fatigue & how our feeds numb us 
Nostr & touching grass 
How movement changes conversations 
LangChain & DVMs 
Central models vs marketplaces 
Going from assembly to high-level to conceptual 
Natural language VS programming languages 
Pablo's code snippets 
Writing documentation for LLMs
Shared concepts, shared language, and forks 
Vibe-forking open-source software 
Spotting vibe-coded interfaces 
Visualizing nostr data in a 3D world 
Tweets, blog posts, and podcasts 
Vibe-producing blog posts from conversations 
Tweets are excellent for discovery 
Adding context to tweets (long-form posts, podcasts, etc) 
Removing the character limit was a mistake 
"Everyone's attention span is rekt"
"There is no meaning without friction" 
"Nothing worth having ever comes easy" 
Being okay with doing the hard thing
Growth hacks & engagement bait
TikTok, theater, and showing faces and emotions
The 1% rule: 99% of internet users are Lurkers
"We are socially malnourished"
Web-of-trust and zaps bring realness
The semantic web does NOT fix this LLMs might
"You can not model the world perfectly"
Hallucination as a requirement for creativity

Ver todos los episodios