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.
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.
I don’t notice this, Firefox on Mac, YouTube Premium. Do they only do this for YouTube Free? Yep, seems like it. Terrible nonetheless of course but it explains why I never experienced this.
Isn’t everyone looking at it for 2 seconds anyway before slapping on a case?
Alexas are all that, but also dumb as a rock. With ChatGPT im conversation mode I can talk aviut anything, Alexa falls on its dumb face almost immediately. Hope they inject some gen AI into their home assistants Stat!
Mobile induction charging battery packs, I use one every single day and the only way those make sense is with magsafe.
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.
I just asked GPT-4:
What’s 7 * 8 divided by 10, to the power of 3?
Its reply:
Let’s break this down step by step:
First, multiply 7 and 8 to get 56.
Then, divide 56 by 10 to get 5.6.
Finally, raise 5.6 to the power of 3 (5.6 * 5.6 * 5.6) to get 175.616.
So, 7 * 8 divided by 10, to the power of 3 equals 175.616
Well, if I try to use Photoshop to calculate a polynomial it’s not gonna work all that well either, right tool for the job and all.
The fact that LLMs are terrible at knowing what they don’t know should be well known by now (ironically).
These LLMs generally and GPT-4 in particular really shine if you supply enough and the right context. Give it some code to refactor, to turn hastily slapped together code into idiomatic and well written code, align a code snippet to a different design pattern etc. Platforms like https://phind.com pull in web search results as you interact with them to give you more correct and current information etc.
LLMs are by no means a panacea and have serious limitations, but they are also magic for certain tasks and something I would be very, very sad to miss in my day to day.
It’s a language model, I don’t know why you would expect math. Tell it to output code to perform the math, that’ll work just fine.
Bard is kind of trash though. GPT-4 tends to so much better in my experience.
Same, oh well. An import modal at bootup asking for settings transfer would probably a good idea.
I gotchu.
I don’t know what OP is talking about, by the time the S7 came around the bloat was already heavily reduced, I’m on an S10E still and think it’s one of the best phones ever, apart from the lackluster battery maybe. But current day Samsung Android I don’t consider bloated.
I believe that’s true for most markets, it sure is in central Europe.
Imo foldable makes a lot of sense for tablets. They are huge 10+ inch honkers, being able to fold it together to something more carryable, I’d be down for that. Of course, this will cost $3k and will be abandoned by Google after one revision, so no thanks, but in principle I’d be down.
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.