JJdoesTech

It seems like the person who submitted the Community Note didn't even read the post. Yeah, the thing is, the issue they claim to have fixed is still happening.

why is everyone excited for GPT 5.6 Sol at 750 tps when most people are already complaining about GPT 5.6 Sol burning through usage limits? it’s gonna use way more than you’re currently using most likely, unless it’s under a separate usage limit like Codex Spark

i'm kinda sick of 5.6 sol now honestly. yes it's a good model, no it doesn't help me ship as much software as it should. it feels too RL-fried and ends up in all these local minima where it just spins its wheels doing nothing, invents bullshit overly cautious procedures you didn't ask for, doesn't solve your problems, hyperfocuses on tiny details, adds theatrical bullshit like tests/ledgers/hashing/proofs/review loops to "ensure stuff works" (none of it works) and degrades context over long-running threads. 1/3rd of the time it can distil your intent kinda okay and keep it up for a few hours but it will eventually collapse into total slop cannon, no matter how much you steer it. the other 2/3rd of the time it will just misunderstand you and slop cannon. oh yeah and the limits are cooked and it burns 5x the tokens of 5.5 whilst you don't ship. bring on GPT 6.....

Serious work doesn’t have to feel heavy. We built ChatGPT Voice for this feeling: less time tethered to a keyboard, more room to think out loud. It’s finally here. So proud of what this team made.

gpt 5.6 pro is substantially smarter than 5.6 in codex. it is inordinately good at critiquing and fixing 5.6's dumb ideas and implementations. there must be a better way than asking 5.6 codex to write research reports, me pasting into pro, then copying instructions back!