Bryan Patricca

Al Implementation

[Bryan Patricca @bryanpatricca]

@AndrewCurran_ Dammit this is all so stupid

[Bryan Patricca @bryanpatricca]

@lucastohdev Right, its basically no different than being an advanced codex user, which I would argue that you can actually do more

[Bryan Patricca @bryanpatricca]

@VraserX Totally agree. Whats interesting is this the same situation with Opus 5.5 and Fable. I guess scaling laws and distillation works!

Definitely think 6.1 was meant to be Astra Minor and distilled from Astra.

[Bryan Patricca @bryanpatricca]

@The_Alex Do you think it's better than opus 5.5? 5.5 was the first time I noticed full video editing was possible but I may have missed something.

[Bryan Patricca @bryanpatricca]

@gavinpurcell What reasoning effort?

[Bryan Patricca @bryanpatricca]

@RonHendersonGTR @ah20im I figured I would have to route it codex for anything complicated. The fact that is does count for usuage makes me think it's Astra low.

[Bryan Patricca @bryanpatricca]

@SimonasLTU1 https://t.co/RWTvJhbIQx -This is my site, with my harness, opus is actually worse than Astra and 6.1 Sol at design. So I'm assuming Sonnets okay. But were running different tests.

[Bryan Patricca @bryanpatricca]

I am hoping we can change the model and reasoning effort of dots, that would really set it apart. But it sounds like we wont be able too since the usage is unlimited.

[Bryan Patricca @bryanpatricca]

@theo And fable 5.5....

[Bryan Patricca @bryanpatricca]

@AlphaMFPEFM @VraserX yea, exactly. Totally agree.

[Bryan Patricca @bryanpatricca]

@VraserX Yea, it's pretty cool but you can set an agent to run 24.7 in codex now on any task. And you can direct it with a main thread. So, I guess all of that is just sort of built in now.

[Bryan Patricca @bryanpatricca]

@iannuttall deff - they cranked that out quick

[Bryan Patricca @bryanpatricca]

@testingcatalog idk not much different than codex?

[Bryan Patricca @bryanpatricca]

Dot doesn't seem very exciting? IDK seems the same as voice basically and a sophisticated user maxing codex already.

[Bryan Patricca @bryanpatricca]

@emollick My gosh, that was only a year ago. Feels like it was 3....

[Bryan Patricca @bryanpatricca]

Anth should totally release Fable 5.5 today mogging OAI

[Bryan Patricca @bryanpatricca]

Totally. Hopefully the agent capabilities are payment, passwords, and passkeys are all able to be used well in codex and chatgpt. Since I have a macbook, I have the issue of the agent always needing me to approve my passkey (which I could probably solve on my own). it's all a bit clunky at the moment anyways.

[Bryan Patricca @bryanpatricca]

Thinking OpenAI has something big at devday, so big that it will drive demand even though they reduced the $200 sub right before.

[Bryan Patricca @bryanpatricca]

@AIMelGibson Do you think we'll get access to a preview version of bel or just a demo of capabilities? Definitely think we'll hear about the millennium problems...I bet the hedge conjecture is solved and will be released.