Eh, that’s not quite true. There is a general alignment tax, meaning aligning the LLM during RLHF lobotomizes it some, but we’re talking about usecase specific bots, e.g. for customer support for specific properties/brands/websites. In those cases, locking them down to specific conversations and topics still gives them a lot of leeway, and their understanding of what the user wants and the ways it can respond are still very good.
Depends on the model/provider. If you’re running this in Azure you can use their content filtering which includes jailbreak and prompt exfiltration protection. Otherwise you can strap some heuristics in front or utilize a smaller specialized model that looks at the incoming prompts.
With stronger models like GPT4 that will adhere to every instruction of the system prompt you can harden it pretty well with instructions alone, GPT3.5 not so much.
I’ve implemented a few of these and that’s about the most lazy implementation possible. That system prompt must be 4 words and a crayon drawing. No jailbreak protection, no conversation alignment, no blocking of conversation atypical requests? Amateur hour, but I bet someone got paid.
Remember when Internet Explorer/Edge was only used to download Chrome. Well, ironically these days I only use Chrome to make video calls.
Better host it yourself, because the managed version of Ghost has the lovely dark pattern that you cannot cancel your plan without them immediately deleting everything, no matter if your plan is still paid for for another few months or not. Really left a bad taste on my mouth.
The Huthis have been launching ballistic missiles across country lines and target (among other things) international shipping lanes somewhat recently. They’re not soldering up IEDs in caves to fend of a US invasion force, so I’m not sure how apt the comparison with Afghanistan is.
Don’t fuck with global trade. Your cause can be a shining beacon of righteousness, but take out trading routes you get the big boy stick. Always has been like that.
Big fan of Huel (or whatever other Soylent-like floats your boat) for that reason. 2-3 minutes to make and gulp down 500kcal with all required macros/micros.
Much less activation energy needed compared to prepping a real meal, and healthier than reaching for the next bag of crappy snacks (or the next bag of nothing).
Tell me what you’re driving without telling me what you’re driving.
Saw it today in Germany. Cancelled my sub. Ads is a line in the sand that won’t be crossed no matter what.
Wenn die Wehrpflicht zurückkommt dann aber bitte Geschlechterübergreifend. Wir haben damals 9-12 Monate verbraten während die Mädels schonmal im ersten Semester saßen.
ChatGPT, explain it to em like I’m a lobotomized 2 year old.
4 Bitcoins for an 8th? Bargain!
Let’s just hope for Gabe to live a long life still. Valve is a private company and not nearly as much in danger for enshittification as a public company would be.
You’re also boiling water with gravity.
deleted by creator
Ah yes, the authoritarian government of current day checks.notes Germany?
Yeah, love all the armchair political commentators on lemmy. I live in Berlin, what’s happening in the Neukölln district of Berlin has nothing to do with peaceful protests. It’s a whole bunch of “kill all Jews” mixed with a hefty dose of “burn it all!”, and somehow it’s always a giant mob of violent men in their twenties, who aren’t exactly paragon of empathy and diversity, imagine that.
But no, not like that. Clearly they need to find a way of materializing money from thin air.
Windows is the one where I need an account to install and that spies on me and throws ads in my face, that one?