RE: https://neuromatch.social/@jonny/116324676116121930
On reading this thread, I think that Anthropic subscribers who use Claude Code have a very strong case for fraud on the part of Anthropic, given there are multiple redundant - and token-expending - calls to the API baked into this, combined with a lack of ability to choose one's own front-end interface, thus mandating the inefficient and costly expenditures, artificially pumping up usage.
Not to mention there are several things highlighted here which are implemented exactly wrong.
e.g. requiring multiple API calls to generate JSON (instead of having a process that deterministically generates valid JSON - annoying to write, but very possible)
and having a regex for sentiment analysis (instead of calling the LLM that is advertised as capable of performing sentiment analysis)
This entire thing is ass-backwards.
And that's even before the "system prompt" backdoor they put in there.
They are inline signaling a backdoor.
This is flat-out fucking disgusting.
These 'strong protections' that Anthropic advertises appear to be implemented as begging the LLM to do the correct thing, in-line.
So this is not security at all.
This is what I would describe as "kayfabe" and it is entirely unsuited for any kind of production load.
Fi 🏳️⚧️
mx alex tax1a - 2020 (6)