Oltan Akin (@GeorgetownQuant) profile picture
Joined October 2024
Replying to @thsottiaux
The reset, por favor @thsottiaux
79
Having fun with 6.2 Astra right now
39
Replying to @sama
Thank you @sama, may we please have a banked reset to celebrate? @thsottiaux never replies
12
Replying to @thsottiaux
Thank you and the entire team! I’m excited to try out 6.2 Astra and Sol. @thsottiaux
86
@thsottiaux is there any way the team can focus on how Dot + Codex could work more smoothly together? I am trying to get Dot to manage my project and the necessary Codex work/chats, and it is nothing short of painful.
1
400
Replying to @thsottiaux
Better integration with dot - dot struggles with firing up codex chats, steering the work, and providing independent review. Why can’t dot access the same workflows that codex can? Network blocks that dot reaches out to support for….
16
Replying to @thsottiaux
Thank you for your hard work. Dot runs into too many hiccups, such as access issues/network restrictions, inability to manipulate and manage codex, and requiring handholding. We need new models! Ty for listening.
51
Replying to @ChatGPT
@thsottiaux I am so frustrated and disappointed with dot. It cannot reliably manage codex for me, runs into countless issues, and the chat that it did manage to create keeps retiring out for me (AbsolutePathBuf deserialized without a base path).
58
Replying to @thsottiaux
Excellent - I think another 28 days is in order. Resets and new models, please!
32
Replying to @thsottiaux
Commence another 28 days, Tibo. Do it now.
4
Replying to @thsottiaux
THANK YOU, TIBO!!
2
272
Replying to @thsottiaux
Save the $200 plan, don’t cut usage :(
42
6,174
Replying to @argofowl
Claude max plan switch date - no other choice.
21
Replying to @Mr_nexp
I will more than likely switch to Claude max plan and move away from OpenAI entirely. Token burn with basic mistakes, usage getting cut, seeing my project’s codebase bloat while getting less done than ever. Opus 5.5 is too good to ignore.
2
5
324
Replying to @thsottiaux
Thank you for the reset. Sadly I may have to move my entire workflow elsewhere. Usage for 200 plan getting cut and no answer to Opus 5.5. My codebase is now a mess and token churn is insane with the mistakes. Pandas version# mistake even, no joke.
144
I've been getting dozens of messages from frustrated OpenAI users saying they were caught completely off guard by the Pro plan limits being cut from 20x to 10x. And they're all expressing pretty much the same frustration: "I'm already struggling with the current limits. Imagine having half of that." "I was already thinking about switching to Claude anyway." "They don't have the best model, and now they won't even have decent usage limits?" And plenty of other complaints along the same lines. I think this should be a wake-up call for the OpenAI team. They really need to pay attention, listen to this feedback, and use it to make things better.
60
16
2
420
17,669
My Codex/OpenAI experience since August now: “I’ve been working on this module for the last four hours but it expected the old handoff package and used the wrong pandas version”…. So many hours, refund credits, and tokens burned. Laughable to be upcharged for this starting in a few days. Codebase bloated; progress backwards. @thsottiaux @sama @TokenGremlin
1
60
Replying to @thsottiaux
Opus 5.5 would provide some excellent recommendations, I’m sure.
34