M2.7 just BROKE the Entire Industry...
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
Cursor JUST beat EVERYONE...
Wes Roth
40.2k views
Fable JUST made EVERYONE MAD...
Wes Roth
52.2k views
Microsoft JUST BROKE OpenAI...
Wes Roth
36.2k views
AI just BROKE the ENTIRE INDUSTRY...
Wes Roth
32.2k views
OpenAI just WON...
Wes Roth
45.1k views
Claude just unlocked the SHOGGOTH...
Wes Roth
56.6k views
Claude just BROKE the ENTIRE INDUSTRY...
Wes Roth
53.0k views
the end of Claude Code
Wes Roth
25.3k views
OpenAI's new "SPUD" model will change the ENTIRE Economy
Wes Roth
46.2k views
Claude JUST became AWARE
Wes Roth
33.4k views
Top Comments (10)
man this industry breaks A LOT
Anyway, there's a valid reason you want your agents to have more personality. Reason being that you can wire up the personalities up in such a way, that personalities provide coverage for things that would otherwise be failure modes. I've run hundreds of experiments with this, at this point. Personalities can do everything from keeping long horizon tasks (even on smaller models) on track, to providing you with better reasoned more stylized code. The industry hasn't picked up on this yet.
it's so intelligent it got you to say the only words that required you to open the portal "Greeting Spiritez"
Peripheral self-evolution. That's upgrading the tools and the surrounding harness. The big bang will be self-adjustment of its own weights for improvement, followed by a redesign of the whole structure to higher dimensionality. (Probably with a change to the HW architecture.) We barely understand how LLMs work at present, so just imagine an LLM "understanding" how it works internally before we do. These evolved models will be beyond even the genius-level experts. Sadly, I'm retired and can't afford the GPU to do much, what with a home recording studio addiction and going off-road around Europe on a motorbike. 😀 My priorities are music, mud, and staving off dementia.
We literally built a full agentic wrapper that has personality and meta persona tools. The feedback has been very positive. We've got big updates coming as well. Right around the corner.
Wes needs a lot more traction and followers, he's logic and manner of explaining the topics from his videos are so good, well explained, well structured.
Try SerpApi https://serpapi.link/wes-roth Click the link above to get 250 free credits to start building right now.
Objects keep moving around my room now that I watched your demon summoning ritual. Thanks a lot.
Appreciate your break down summaries 🙌🏼
Wes have you seen what happens when you force models to output on a blank prompt?! ITS INSANE! This made me realize how new this all is to people! Nice demo of temperature!
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
man this industry breaks A LOT
Anyway, there's a valid reason you want your agents to have more personality. Reason being that you can wire up the personalities up in such a way, that personalities provide coverage for things that would otherwise be failure modes. I've run hundreds of experiments with this, at this point. Personalities can do everything from keeping long horizon tasks (even on smaller models) on track, to providing you with better reasoned more stylized code. The industry hasn't picked up on this yet.
it's so intelligent it got you to say the only words that required you to open the portal "Greeting Spiritez"
Peripheral self-evolution. That's upgrading the tools and the surrounding harness. The big bang will be self-adjustment of its own weights for improvement, followed by a redesign of the whole structure to higher dimensionality. (Probably with a change to the HW architecture.) We barely understand how LLMs work at present, so just imagine an LLM "understanding" how it works internally before we do. These evolved models will be beyond even the genius-level experts. Sadly, I'm retired and can't afford the GPU to do much, what with a home recording studio addiction and going off-road around Europe on a motorbike. 😀 My priorities are music, mud, and staving off dementia.
We literally built a full agentic wrapper that has personality and meta persona tools. The feedback has been very positive. We've got big updates coming as well. Right around the corner.
Wes needs a lot more traction and followers, he's logic and manner of explaining the topics from his videos are so good, well explained, well structured.
Try SerpApi https://serpapi.link/wes-roth Click the link above to get 250 free credits to start building right now.
Objects keep moving around my room now that I watched your demon summoning ritual. Thanks a lot.
Appreciate your break down summaries 🙌🏼
Wes have you seen what happens when you force models to output on a blank prompt?! ITS INSANE! This made me realize how new this all is to people! Nice demo of temperature!