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.
Saw it today in Germany. Cancelled my sub. Ads is a line in the sand that won’t be crossed no matter what.
ChatGPT, explain it to em like I’m a lobotomized 2 year old.
Because… why?
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.
One finger is not enough for that, could be ESC, F2, F12, DEL or whatever else the bios manufacturer landed on when they threw a dart at the keyboard.
But no, not like that. Clearly they need to find a way of materializing money from thin air.
The AI agrees with you.
It runs alright on my 2021 M1, but I play it via GeForce Now these days, where it really screams.
Yep. What they should have written:
“We recognize that our recent runtime fee policy announcement wasn’t well-received. We genuinely apologize for the oversight and any confusion or concern it caused. Your feedback is invaluable to us. We are actively discussing the policy with our teams and the community and will be revising it based on your inputs. Please bear with us as we work through this, and expect an update soon.”
PR is hard, let’s go shopping!
I mean, we’re talking curl here, I don’t think a lot of suffering of consequences is happening. And man pages are often also not a great resource, throw everything at you, often don’t contain examples. If I’m building an app that integrates curl or libcurl, oh yes I’m reading the doc. If I just need curl to do something quickly, the LLM output is perfectly fine.
I recently watched the 3.5-hour workshop Mastering the curl command line by Daniel Stenberg, the author of curl
I commend the author for watching and subsequently summarizing this into a blog article, but in the age of LLMs like ChatGPT I cannot be arsed anymore to memorize any of the arcane command line arguments of curl, ffmpeg and the like.
deleted by creator
Video in question: https://youtu.be/sGKCrcNsVzo?feature=shared
Reminds me of the colours in the movie Her.
Windows is the one where I need an account to install and that spies on me and throws ads in my face, that one?