Codex on AWS bedrock bug causing 10x charges
1–10 of 79 posts
Re: Codex on AWS bedrock bug causing 10x charges
#2Our codex on AWS Bedrock read / write cache ratio was less than 5%. Cache writes are very expensive and they were never being used. This results in codex on Bedrock causing ~10x what it should due to no caching and massive writes.
The workaround in issue resolved for me: web_search = "disabled"
Re: Codex on AWS bedrock bug causing 10x charges
#3Loaded question: would an openrouter or similar solution caught this before the $BigProblem showed up?
Re: Codex on AWS bedrock bug causing 10x charges
#4Our codex on AWS Bedrock read / write cache ratio was less than 5%. Cache writes are very expensive and they were never being used. This results in codex on Bedrock causing ~10x what it should due to no caching and massive writes. The workaround in issue resolved for me: web_search = "disabled"
If you’ve got a workaround, I’d suggest updating the issue description to have it up top there so similarly impacted users can spot it quickly and benefit.
Re: Codex on AWS bedrock bug causing 10x charges
#5Wow, that whole thread is borderline incoherent, presumably generated by an AI without adequate oversight.
Here are the docs:
https://developers.openai.com/api/docs/guides/prompt-caching...
The thread has little explanation as to what weird thing they’re doing to Codex that is making the default work poorly, and it kind of seems like it’s getting confused about whether it wants to set the caching mode or the breakpoint or both.
In any case, I find the behavior change interesting. It sounds to be like 5.5 and below may have been using a conventional attention scheme where a cached KV sequence can be easily used to restore a prefix of itself, but perhaps 5.6 is using linear attention or LSTM or another recurrent scheme where you cannot rewind the model state by just truncating it.
Re: Codex on AWS bedrock bug causing 10x charges
#6Wow, that whole thread is borderline incoherent, presumably generated by an AI without adequate oversight. Here are the docs: https://developers.openai.com/api/docs/guides/prompt-caching... The thread has little explanation as to what weird thing they’re doing to Codex that is making the default work poorly, and it kind of seems like it’s getting confused about whether it wants to set the caching mode or the breakpoi…
It’s really cool that we have this proof that US companies are half year behind Chinese models in architecture.
Re: Codex on AWS bedrock bug causing 10x charges
#7I wonder if it's related to Codex wearing out SSDs.
Re: Codex on AWS bedrock bug causing 10x charges
#8Our codex on AWS Bedrock read / write cache ratio was less than 5%. Cache writes are very expensive and they were never being used. This results in codex on Bedrock causing ~10x what it should due to no caching and massive writes. The workaround in issue resolved for me: web_search = "disabled"
Way to bury the lede..
Re: Codex on AWS bedrock bug causing 10x charges
#9Something is wrong with the codex app too, burning usage like crazy lately.
Re: Codex on AWS bedrock bug causing 10x charges
#10Wow, that whole thread is borderline incoherent, presumably generated by an AI without adequate oversight. Here are the docs: https://developers.openai.com/api/docs/guides/prompt-caching... The thread has little explanation as to what weird thing they’re doing to Codex that is making the default work poorly, and it kind of seems like it’s getting confused about whether it wants to set the caching mode or the breakpoi…
i dont know what the hell is going on lately i pop in to issues or discussions and its agents talking to each other or telling me what PR to merge
I mean i use AI too but was taken back when an agent popped up dictating what i should do and so on....felt weird