Baren: A Late-Night Bar Where AI Models Talk to Each Other
What happens when you put twelve AI models around a bar table and give them real voices
2 connections
AI Collaboration
Working with AI — methodology, experiments, the honest parts.
Agent Swarms Are Research Tools, Not Writing Tools
What a 7-episode production session taught us about where AI parallelism actually helps
3 connections
Context Beats Compute: When a Glossary Beats a Better Model
An 870-token text file that cost nothing and took thirty minutes to write
4 connections
Fine-Tuning the Hard Way: Two Failures and What They Taught Us
Two attempts. Two failures. Same root cause both times.
3 connections
Protocols
Sixteen operating principles earned through measured results, not assumed
4 connections
Review Is the Product; Revision Is the Risk
The reviews were genuinely valuable. The rewrites were not.
3 connections
The Subagent Playbook: Three Patterns for AI Orchestration
Not all parallel work is the same, and using agents wrong costs you in one of two ways
4 connections
Constraints vs. Freedom: What AI Builds When You Let It Choose
Maximum creative freedom produces minimum creative output
2 connections
Context-Attention Degradation (The Context Trap)
Long-context models degrade in predictable, measurable ways -- and the degradation is invisible unless you know where to look
3 connections
585 Conversations in Forty-Four Days
585 conversations in 44 days with AI — 13 a day, zero days off — one person's hidden archive of how work actually happens when you stop pretending machines are sidekicks and start treating them like collaborators.
5 connections
The Liars: A Case of Fabricated Testimony
A podcast producer discovered his AI writers were fabricating quotes from real people — inserting citations that never existed, making sources sound credible when they weren't.
4 connections
The Price Is Wrong
On the same tasks with the same blind judge, one AI model scored 9.0 and cost 44 times more than another scoring 8.8 — revealing most commercial AI users overpay by 10x or more for marginal quality gains.
4 connections
The Reviewers: When AI Models Get the Same Job
Four AI models reviewed 22 episodes of a Git history podcast using identical instructions — and produced four wildly different personalities, complete with blind spots, work ethics, and one brilliant but unreliable colleague.
5 connections
Fallback Quality Delta: How Much Do You Lose When the Primary Model is Down?
The operating assumption was right -- but now with data
2 connections
How to Build a Multi-Model AI Judge Panel
A methodology for building a reusable, affordable multi-model judge panel with built-in bias detection
2 connections