Subscribe
Sign in
Home
Podcast
Archive
About
Latest
Top
Discussions
Trump's "Big Beautiful Bill" likely created with AI - what does this imply?
Emdashes per legislative page in this bill are 30% more than a bill of a similar size sent to Congress before AI use
Jul 1
•
Jonathan Bennion
June 2025
Apple's Illusion of Thinking Paper & Concept of AI Tool Half-Life
No matter how an "AI agent" is defined (and improved upon), the paper argues that complex reasoning will "collapse" - more research suggests AI tool…
Jun 30
•
Jonathan Bennion
1
January 2025
Querying pypi to fact-check AI hype
Pypi downloads allow us to see who is publicly lying; AI hype is over.
Jan 13
•
Jonathan Bennion
September 2024
Confounds and Complex Bias Interplay from Human Bias Mitigation in Language Model Datasets Used for Finetuning LLMs
A 2023 dataset that balanced occupational bias distribution in one dataset may have decreased racial bias (unintentionally), but increased gender and…
Sep 30, 2024
•
Jonathan Bennion
Zapier's Deviation from AI Tool Adoption Trends in AI Hype Cycle and Potential Comeback
Diverging trends suggest automation tools faced challenges during AI hype cycle - will trend reverse as hype subsides?
Sep 4, 2024
•
Jonathan Bennion
August 2024
How AI Was (Briefly) Hijacked by Hype - Why We Can't Have Good Things
Hypothesis on how an intelligent new technology was overtaken by hype from covid-era business school graduates, uneducated marketers, and influencers…
Aug 28, 2024
•
Jonathan Bennion
2
Chicken or Egg: Relationship between LinkedIn posts by HuggingFace employees and Nvidia Stock Price
Oddly correlated - are they symbiotic?
Aug 26, 2024
•
Jonathan Bennion
4
Querying AI and Cloud Trends: Azure and OpenAI Dominate but Growth Slows, Amazon May Have Peaked
Cutting through the AI hype to query actual developer usage (with presumptions), for prioritization of safety tools and guidance for partnerships.
Aug 22, 2024
•
Jonathan Bennion
GraphRAG Analysis, Part 2: Graph Creation and Retrieval vs Vector Database Retrieval
Since Microsoft's GraphRAG paper showed only vaguely defined lift, I found GraphRAG increased faithfulness but not other RAGAS metrics - the ROI of…
Aug 20, 2024
•
Jonathan Bennion
3
July 2024
Preventing Prompt Injection: A Case Study with Priceline's AI Tool Penny
Strategies to Mitigate Persistent Prompt Injection Threats in AI Systems
Jul 11, 2024
•
Jonathan Bennion
GraphRAG Analysis, Part 1: How Indexing Elevates Vector Database Performance in RAG When Using Neo4j
A deep dive on Microsoft's GraphRAG paper found questionable metrics with vaguely defined lift, so I analyzed knowledge graphs in RAG overall using…
Jul 9, 2024
•
Jonathan Bennion
17
8
May 2024
Langchain’s built-in eval metrics for AI output: how are they different?
Mostly creating my own custom metrics, but have come across these built-in metrics for AI tools in LangChain repeatedly and ran a quick analysis.
May 22, 2024
•
Jonathan Bennion
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts