Replying to @Doctorthe113
The best thing about this is that OpenAI doesn’t actually serve the variant they forced me to be so heavily compressed.
After upload they recode it from PNG to PNG and then only use theirs for 22 742 bytes instead of 9900 bytes with no benefit whatsoever.
Replying to @alexatallah
I love integrating OpenRouter in web apps, but there is a very annoying issue with your backend configuration, probably unintended.
Can you please look into it and/or delegate it to an agent? 🥺
Jaid retweeted
Damn, this is insane! Try Arrow 1.1 @QuiverAI
Jaid retweeted
if ur worried about ur data and privacy peter highkey has good tips here 😂🙏🌹❤️🩹❤️🩹
scalemogging
Replying to @PostgreSQL
@PostgreSQL has long powered core @OpenAI products like ChatGPT and the API. Over the past year, our production load grew 10× and keeps rising. Today we run a single primary with nearly 50 read replicas in production, delivering low double-digit millisecond p99 client-side latency and five-nines availability. In our latest OpenAI Engineering blog, we unpack the optimizations we made to to scale @Azure PostgreSQL to millions of queries per second for more than 800M ChatGPT users. Check out the full post here: openai.com/index/scaling-pos…































