I’m not a C++ guy, but this topic fascinates me. Might poke around and try to have an LLM transpile the code from C++ to Rust. I expect it won’t work but worth giving it a shot :)
338 karma · joined November 14, 2022
When I go out for a hike in the woods or a hike in a new state/country that isn’t my home. I don’t go out destroying the land around me. I observe and enjoy my time
Maybe these aliens are scientists. Documenting biological life across the galaxy. Maybe they’re VanCampers. Just bouncing from planet to planet for fun
If a civilization has presumably reached FTL travel. I imagine many of their needs have been met and conquest/destruction isn’t required to maintain their supremacy. Lots of empty planets with plenty of resources out there!
Not saying aliens/UFOs are real, but I think it’s very easy to imagine them existing and not being destructive. Or maybe they’re just scouting before the invasion :)
Doomerism is an awful mindset to have. It’s difficult to feel this way but there’s still a lot of hope and a lot of amazing people working on this.
There is certainly lots of pain ahead. My home nation will be underwater by 2100s, lots of animal species will go extinct, but we are not doomed.
Adoption for these systems might be higher if they had a more readable syntax (and bonus if they could transpile down to source code you can tweak)
Also maybe I missed it on mobile, but I would love examples of the syntax and examples of application usage on the first page. Maybe this is useful to me! Who knows? That information should be easy to find
Although yes. I don’t think Twitter unionizing will save the site.
I’m convinced the latter being a time of brooding is just an urban legend. I’ve met a small handful of people who look at winter this way, and every single of one of them switched their mindset if you addressed the actual issue (loneliness itself)
When I do encounter that sentiment. It often seems that person: 1.) lives in a fractured and isolating suburban community, doesn’t know their neighbors, doesn’t leave their house much 2.) grew up in a sunny tropical climate, and is still adjusting to winters
A huge amount of folks in group 2 eventually grow out of it
Folks in group 1 are often unhappy in most places. It feels to me the problem there is moreso their location and lack of community vs the winter. Because they cheer right up when they find a community to enjoy winter with
Growing up in the suburbs of the US South. Huge swathes of people I knew were unhappy with not a single cold breeze flowing by. Have a strong suspicion their unhappiness was the lack of community in their life and not the season
Xbox also isn’t top dog among the big 3. They’ve really struggled to ship big exclusive system sellers (which is a bummer. I’m a big fan of a lot of Xbox IP), so they certainly aren’t “industry leading”. Doesn’t mean the exclusives they’ve shipped aren’t good. They certainly are, just that their is no Xbox answer to God of War or Last of Us
GamePass is one of the biggest success stories to come out of Xbox and is certainly the dominant game streaming service
This worked surprisingly well and without fail for the conservative side of my family. The instant I reminded them who was president at the time (Obama) all of them changed their mind
I don’t love this strategy. It leans into fear mongering a bit much, but if none of the other very helpful rhetorical techniques folks have shared here don’t work. This one has some staying power.
Obviously the answer is that its a non-question. The amount an author reads doesn’t correlate to success. Plenty of authors are voracious readers, others rarely pick up a book.
What do you see with a lot of creative authors (but not all) is a dedication to the craft. Putting in hours of writing. Often editing or just tossing everything.
I have noticed though. People on my team best capable of writing technical documentation. Read a lot of technical documentation. This is the exact domain GPT can Excel at, and one where generic language is accepted.
Decoding methods also matter, and it’s a shame we aren’t given token probabilities (or any insight into model output) so we have more creative control over how to decode the output. Some of the better literature I’ve seen involving creative writing did have novel decoding methods
A tangent. Bard also confuses Yoda with Jar Jar Binks quite often. Try it out!
Regarding Bing Creative. It is delightful! I do like it a bit and whatever they’ve done to the system does make for some of the better output I’ve seen from LLMs
That’s not to say it isn’t impressive. It is and it accomplishes the job very well. We’re looking for progress not perfection, but I personally have very high standards from creative writing and GPT doesn’t meet my personal bar. However not everyone shares that bar and personal evals of GPT’s output are equally valid. Plenty of people find it to be great and at the end of the day that’s all that matters
I used to work in the field of creative text generation for fiction. I’m genuinely very curious and I go out of my way to find compelling examples. There is definitely “good” output that’s on the right track. GPT-4 also does way better, but it still falls short.
This is also difficult to just evaluate objectively. If you find that GPT models have generated the best prose you’ve seen. That’s wonderful! I understand that my standards are quite high (high does not equate to “better” either)
Wonder how long before that’s solved. Hard to believe training on such large swathes of the web doesn’t result a compressed generic representation of language within its weights.
Combing the two doesn’t result in anything, besides the fact one is questionable if it can ever be realized (AGI) the other technology is extremely nascent and even physics wonder if there is a limit to the # of qbits (I’m more optimistic we’ll surpass that)
Even then the usefulness of quantum computers is called into question, and quantum inspired algorithms might net benefits without having to use a quantum computer for all inference ops
It feels at some point being too slapped together isn’t correlated with success
Wishing the LangChain team well! But there are already alternatives cropping up that are far more polished (Microsoft’s Semantic Kernel being one)
I should add, I dont think all of it is a joke, but stuff like the "author_is" labels are incomplete and only 4 were shown for the bit
Excited to see it is JSON too! Cannot wait to try :)