Descriptions:
Get Your Model Fit (Free). Tell it how you work, it hands you a model mix plus some “think bigger” prompts to give your work a boost: https://modelfit.natebjones.com/
GPT-5.6 Sol is the dumber model on my benchmarks, and it is still the AI model I open every morning. Here is how to pick the model that fits how you actually work.
Full post w/ Model Benchmarks:
https://natesnewsletter.substack.com/p/pick-ai-model-how-you-work?r=1z4sm5&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true
My Links 🔗
👉🏻 Newsletter: https://natesnewsletter.substack.com/
👉🏻 X: https://x.com/natebjones
👉🏻 TikTok: https://www.tiktok.com/@nate.b.jones
👉🏻 Instagram: https://www.instagram.com/nate.b.jones
What’s really happening inside the model race now that GPT-5.6 Sol, Fable 5, Grok 4.5, and GLM 5.2 are all on the table?
The common story is that you pick whatever tops the latest benchmark — but the real question is which model gets you to your own best work.
In this video, I share the inside scoop on choosing a model by work pattern instead of leaderboard position:
– Why Sol set a new high on Agent’s Last Exam and still lacks big model smell
– How OpenAI’s RL bet and Anthropic’s pre-train bet produced different model families
– What to look at before you look at the model itself
– Why I still run Fable as the architect inside Ringer
Models are becoming families you get to know rather than scores you rank, and the sooner you understand your own work, the less the leaderboard matters.
Chapters:
00:00 Which model works for you, not which model works for me
00:35 Sol scores 93 on Dingo, my knowledge work benchmark
02:26 Your best work may come from a different approach entirely
11:20 A tool to make choosing your own model mix easier over time
Listen to this video as a podcast.
Spotify: https://open.spotify.com/show/0gkFdjd1wptEKJKLu9LbZ4
Apple Podcasts: https://podcasts.apple.com/us/podcast/ai-news-strategy-daily-with-nate-b-jones/id1877109372
