The fact that companies with access to SOTA non-public AI keep having these kinds of dumb bugs in something as simple as a chat app helps validate my disbelief of people claiming AI is ready to replace all software development.
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.
> 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.
I feel like this is the kind of substantial change to your product that you would need to tell your customers about. It would be simply disrespectful to your customers to not disclose this upfront.
Our 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.
The fact that companies with access to SOTA non-public AI keep having these kinds of dumb bugs in something as simple as a chat app helps validate my disbelief of people claiming AI is ready to replace all software development.
AI is ready to replace both jobs and companies.
The companies you see struggling are ripe for disruption.
Wow, 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.
It’s really cool that we have this proof that US companies are half year behind Chinese models in architecture.
What is the proof?
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
> 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.
I feel like this is the kind of substantial change to your product that you would need to tell your customers about. It would be simply disrespectful to your customers to not disclose this upfront.
It depends on who they consider the customers. Shareholders and govt are the customers, not users.
Users is the product.
Our 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.
It's already mentioned in the issue...
It’s in a comment halfway down the page. It’s not in the issue description.
If enough comments are added to the discussion, it might end up being collapsed.
"causing" -> "costing", right?
Way to bury the lede..
Something is wrong with the codex app too, burning usage like crazy lately.
There haven't been any free resets in the past week, there were 4 in the first half of the month
indeed it has anybody know whats going on at openai ??
Maybe preparing for their IPO?
Funny how it is always more charges but never less or no charges.
"Random" accidents that always go against you, too biased to be random.
But don't notice that too much, you might start to see patterns here and there that you're not allowed to, might get you banned from places, etc.
I wonder if it's related to Codex wearing out SSDs.
Loaded question: would an openrouter or similar solution caught this before the $BigProblem showed up?