@GergelyOrosz: With every new model, I put it to the test in writing - to see if I could do what I do - I give it a bunch of interview…
Summary
Gergely Orosz tests new AI models like Fable and GPT-6 by asking them to write articles in his style from his interviews, but finds they fail spectacularly, producing lots of words without understanding.
View Cached Full Text
Cached at: 07/13/26, 10:00 PM
With every new model, I put it to the test in writing - to see if I could do what I do - I give it a bunch of interviews I did on a topic, and ask to write an article in my style.
The models fail spectacularly, Fable and GPT-6 no different. Lots of words, but no understanding
Similar Articles
@GergelyOrosz: Many of the most “AI-pillled” people working at AI labs do their own writing and not let AI do it at all. They do it so…
Gergely Orosz highlights a paradox: many deeply 'AI-pilled' employees at AI labs still write everything themselves to preserve their thinking, while less AI-enthusiastic users hand writing over to AI—and it shows in their reasoning.
A new era of AI testing (2 minute read)
A compilation of Andrej Karpathy's recent tweets covering a minimal GPT implementation, vibe coding an iOS app, and a detailed comparison of GPT-4.5 with earlier models, offering insights into AI testing and scaling.
@rohanpaul_ai: Very interesting experiments by @thehypedotnews gpt-6 sol vs grok 4.7 vs gpt-6 astra vs muse spark 1.3 Amazing how litt…
Experiments comparing AI models like GPT-6 Sol, Grok 4.7, GPT-6 Astra, and Muse Spark 1.3 in generating browser artifacts from prompts highlight GPT-6 Sol's efficiency with minimal inference to produce working HTML files.
@GergelyOrosz: Interesting take on Fable vs GPT-5.6 Sol. From a dev at a large, and "AI-bullish" company, spending $$$ on AI: "Anthrop…
A developer from a large, AI-bullish company explains that Anthropic's data retention policy on Fable prevents its use, leading the company to heavily adopt GPT-5.6 Sol instead.
@levie: The reason I have an unhealthy obsession with AI right now is because I've spent my entire professional life on essenti…
Aaron Levie explains that recent AI models like GPT-5.6 Sol, Fable 5, Grok 4.5, and Muse Spark 1.1 enable processing of unstructured enterprise data at scale, transforming knowledge work by allowing complex queries and automated analysis.