@emilstridell@ajambrosino Low tokens/sec doesn’t prove bad infrastructure, and fewer tokens/task doesn’t prove efficiency if the answer is worse. A slower model can finish sooner by needing fewer tokens and retries. Measure time and cost per correctly completed task.
@emilstridell@ajambrosino Having low tokens a second means it's effective. Quality of tokens and quantity of tokens are 2 different things. That's why Openai models are cheaper then Anthropics.
Day 25/
We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today.
We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage.
And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
With Intelligent UI, GPT‑6 can now compose responses using text, visuals, and interactive elements, choosing how they fit together based on your question.
Responses can include graphics and charts to help explain an idea, along with tappable buttons, forms, and interactive experiences you can use directly in your conversation.
GPT Astra vs GPT-6.1 Sol vs Sonnet 5.5 vs Opus 5.5.
Which AI understands 3D best?
I gave all four the exact same task: build an AK-47 from scratch.
Same prompt. Same environment.
Which one wins?
@promptyx_ai This on 1 prompt, if you wanna "vibe code" you got to have more then 8gb of ram. And CPU can go up to 90% easily if I have more then a couple prompts open.