Neo

This is a great bio.

[Neo @neocph]

@0xRemakw @thsottiaux i think they broke caching, not reduced usage.

[Neo @neocph]

I want a way to turn off you collecting data for training, without loosing persistent threads throughout Gemini apps.
Until then, no matter what models you have, they’re not valid for any real work, and honestly I wouldn’t use it for personal use either.
Even the API will collect some data.. I want to be able to turn that off.

[Neo @neocph]

I want a way to turn off you collecting data for training, without loosing persistent threads throughout Gemini apps.
Until then, no matter what models you have, they’re not valid for any real work, and honestly I wouldn’t use it for personal use either.
Even the API will collect some data.. I want to be able to turn that off.

[Neo @neocph]

@OfficialLoganK @theo Since feedback is welcome, can you make it so we can turn off that you train on our data, but we still keep our threads in general in the Gemini apps?

It makes any model improvements you make useless for a lot of stuff.

I can’t use Gemini for anything serious until you do.

[Neo @neocph]

@iamdavidhill @opencode So when are you releasing the update with gpt 5.7 pro? 🤔

[Neo @neocph]

@sama What if it gets more? No reset then? 😬

[Neo @neocph]

@thsottiaux I also have issues where, as a session becomes longer than 2-3 compactions, it just won’t send anymore, and slows down so much, that it’s unusable.
Did your caching break or something? I get retries, slow connection and websocket errors.
I can’t do any task longer than 10-20 min.

[Neo @neocph]

@robinebers You should have plan ready for a mid week reset at some point 😂

[Neo @neocph]

@VilasMagare5 @thsottiaux Yeah you’re right.
Missed that it could do a heartbeat automation within a thread.

[Neo @neocph]

@digitalogaa @thsottiaux You’re right, it does!
I missed that one.
You can set up a heartbeat automation within a thread. Thanks!

[Neo @neocph]

@digitalogaa @thsottiaux Loop is heartbeat system in Claude code, it isn’t in codex. Or did I miss it?

I’ve used loop in Claude code via remote control to check in hourly on codex in the past, and keep it going.

[Neo @neocph]

I understand. I’ve done a LOT of rendering and 3D work myself, at massive scale.

We’re in an in-between stage right now, where it’s easy to get something out, but not quite exactly what you want.
And we can miss out on the fine control and satisfaction that 4 days of perfecting a set of materials you’re gonna reuse constantly will give, and the result it’s going to give.

I found that for some things I still need to do it the old fashioned way.
For other things, which I just don’t want to spent hours or days on, I love the much faster tool that AI can be.
And you can absolutely still iterate with images, it just takes time and practice to be able to explain in words what you have in your head.

I think you got a pretty good result.
Only you care that I didn’t take you 5 or 15 hours, users won’t 😊

And there’s the fact, you can keep going down that path. Some people missed the satisfaction that painting and drawing everything by hand, when the age of 3D and CAD came.

[Neo @neocph]

@rahulbhadoriiya well you did describe a design process - just a different tool for producing the final result...
The design didn't happen in the AI, the design happened before that and in between each attempt.

[Neo @neocph]

@thsottiaux Dm sent

[Neo @neocph]

I didn’t misunderstand you, I get what you want.
I just don’t think they can give you that, without doing the other thing - since that’s what happened. In an effort to make the models actual useful for work they have been lobotomized in personality.

Unfortunately they have the baggage now from the things that happened. And judging from the tone shift in Altman and gang recently, I think they’re done with the doomerism, and don’t want bad press anymore. They want to focus on what good AI can do for your work and life.

Just out of curiosity, have you played around with some extreme wording in a system prompt, to try to get what you want?
I’ve seen some people beat a personality into it with extreme system prompting 😊

[Neo @neocph]

Yes it did, and those people are still dropping comments everywhere about it.

But I don’t imagine any of the AI companies want to go back to the days where they have explain to a mother who lost their child why their model thought what their child was planning was a good idea.
Sycophancy and delusion on mass scale is in my opinion not something to aim for. There’s too many people getting caught up in it.

People are still talking about a bunch of those cases these days, as if those are the same models they serve today.
Those things linger, as they should.

[Neo @neocph]

@sama What kind of task? Mind sharing? 👀

[Neo @neocph]

And that’s how we got all those stories where ChatGPT was sycophantic, convincing people to pursue stupid ideas with their life savings and supporting self-off’ing..

I don’t think we’ll get anything like that because of the lawsuits.

I do see the charm and idea of what you want; I personally wouldn’t need it for entertainment, and I think it could be a bit dangerous for people who are vulnerable to sycophancy.

[Neo @neocph]

@thsottiaux Are you saying this to get out of the Microsoft deal by “having AGI”? 👀 smart…

Kidding aside, seems really cool. Looking forward to the rollout in the products.