3
- My Forums
- Tiger Rant
- LSU Recruiting
- SEC Rant
- Saints Talk
- Pelicans Talk
- More Sports Board
- Coaching Changes
- Fantasy Sports
- Golf Board
- Soccer Board
- O-T Lounge
- Tech Board
- Home/Garden Board
- Outdoor Board
- Health/Fitness Board
- Movie/TV Board
- Book Board
- Music Board
- Political Talk
- Money Talk
- Fark Board
- Gaming Board
- Travel Board
- Food/Drink Board
- Ticket Exchange
- TD Help Board
Customize My Forums- View All Forums
- Show Left Links
- Topic Sort Options
- Trending Topics
- Recent Topics
- Active Topics
Started By
Message
Knew it was coming. I'm screwed now.
Posted on 11/2/26 at 8:49 pm
Posted on 11/2/26 at 8:49 pm
OpenAI plans to merge ChatGPT's Chat and Work tabs into a single experience
Aka CAD's unlimited code writing loophole using gdrive to write unlimited files for free is going away.
Dammit. No way I'm going to be done with this project by then.
quote:
Starting in December, Plus, Pro, and Business plans will have a shared usage allowance across ChatGPT and Codex, according to OpenAI's updated support page. Usage will be measured in tokens, the units of information AI models process and generate. More demanding tasks and advanced models will generally consume more of that allowance.
Aka CAD's unlimited code writing loophole using gdrive to write unlimited files for free is going away.
Dammit. No way I'm going to be done with this project by then.
Posted on 11/3/26 at 6:46 am to CAD703X
quote:
OpenAI says Instant chat won't draw from the shared allowance.
The interface will try to switch me to work for stuff I've been doing in non-work for months. Then when I ask my instance about it, it tells me to keep submitting those requests through the non work version (Classic.) Typical results of vibe coding
Posted on 11/3/26 at 6:56 am to LemmyLives
It's annoying. New chats under a project are always in work mode on the windows app so I have to start the chat in a browser them switch to the app so it stays in chat mode.
Knew they wouldn't let this go on forever. I'm way too productive right now with unlimited use. If I have to go to codex I'll have about 15 minutes worth of coding before I'm out for 4 hours.
This is a killer for that massive TV station I'm writing. Going to push hard to get the skeletons of all the shows in before Dec then at least I'll have a baseline for the TV schedule.
Knew they wouldn't let this go on forever. I'm way too productive right now with unlimited use. If I have to go to codex I'll have about 15 minutes worth of coding before I'm out for 4 hours.
This is a killer for that massive TV station I'm writing. Going to push hard to get the skeletons of all the shows in before Dec then at least I'll have a baseline for the TV schedule.
Posted on 11/3/26 at 7:24 am to CAD703X
Open WebUI and DeepSeek API is the cheapest solution I've found, but I'm not nearly as reliant on it as you
Posted on 11/3/26 at 8:23 am to bluebarracuda
quote:
Open WebUI and DeepSeek API is the cheapest solution I've found, but I'm not nearly as reliant on it as you
This is probably correct. Openrouter was great a few months ago because they seemed to always have a free alpha model that was super capable but that is drying up so basically just API pricing with a little competition discount here and there.
I only code hard at home maybe a day or two per month and those days will be $3-8 with deepseek flash. Maybe a few 50 cent days fixing small stuff so openrouter still works fine for me. I also put my home assistant agent and fish audio custom TTS through openrouter. Those add maybe a dollar, very compact and near zero turning/thinking or “safety”.
Posted on 11/3/26 at 10:14 am to CAD703X
With all due respect, CAD, just build yourself a local model on all that hardware you own.
#Thankmelater
#Thankmelater
Posted on 11/3/26 at 10:47 am to Ace Midnight
quote:its on the radar but down the road. going to need my NAS drives and another 32GB of RAM first and that's fricking expensive right now.
With all due respect, CAD, just build yourself a local model on all that hardware you own.
Posted on 11/3/26 at 10:51 am to CAD703X
quote:
If I have to go to codex I'll have about 15 minutes worth of coding before I'm out for 4 hours.
How are you managing context? This doesn't sound right at all.
Posted on 11/3/26 at 11:22 am to Brisketeer
Probably using Astra for everything, if I were to guess.
Posted on 11/3/26 at 11:54 am to Brisketeer
quote:building and deploying TV stations; graphics, audio, news feed sources, visual fonts, rebuilding the app where i can remotely change fonts & adjust ticker speed, etc.
How are you managing context? This doesn't sound right at all.
Posted on 11/3/26 at 11:55 am to Vrai
quote:Sol 6.1 i believe
Probably using Astra for everything, if I were to guess.
Posted on 11/3/26 at 1:42 pm to CAD703X
If you are running out with sol 6.1 in 15 minutes that is impressive
Astra is the one that times me out for usage consistently. good product though
Astra is the one that times me out for usage consistently. good product though
Page 1 of 1
Popular
Back to top
Follow TigerDroppings for LSU Football News