This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.
Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.
Rules:
1: All Lemmy rules apply
2: Do not post low effort posts
3: NEVER post naziped*gore stuff
4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.
5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)
6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist
7: crypto related posts, unless essential, are disallowed
I find it very accurate for cooking related tasks. I find it to be 90-95% on even the wildest recipes. And developing flavour profiles is something it’s also very good at.
I know that’s not a huge thing for most people but recipe sites are so terrible and flooded with trash I appreciate the time saved. I bring this up because the article suggests it should only be used as a starting point.
Well done, appreciate the sharing of knowledge. Kinda wish you would’ve dove into Stabble Diffusion image generation as it’s one of the most popular and powerful techniques out there, although it’s not a GPT. Maybe some other time! Looking forward to your next work 😊
This article is full of errors!
At its core, an LLM is a big (“large”) list of phrases and sentences
Definitely not! An LLM is the combination of an architecture and its model parameters. It's just a bunch of numbers, no list of sentences, no database. (Seems like the author confused the word "LLM" with the dataset of the LLM???)
an LLM is a storage space (“database”) containing as many sample documents as possible
Nope. This applies to the dataset, not the model. I guess you can argue that memorization happens sometimes, so it might have some features of a database. But it isn't one.
Additional data (like the topic, mood, tone, source, or any number of other ways to categorize the documents) can be provided
LLMs are trained in an unsupervised fashion. Just sequences of tokens, no labels.
Typically, an LLM will cover a single context, e.g. only social media
I'm not aware of any LLM that does this. What's the "context" of GPT-4?
software developers have gone to great lengths to collect an unfathomable number of sample texts and meticulously categorize those samples in as many ways as possible
The closest real thing is the RLHF process that is used to fine tune an existing LLM for a specific application (like ChatGPT). The dataset for the LLM is not annotated or categorized in any way.
a GPT uses the words and proximity data stored in LLMs
This is confusing. "GPT" is the architecture of the LLM.
it is impossible for it to create something never seen before
This isn't accurate, depending on the temperature setting, an LLM can output literally any word at any time with a non-zero probability. It can absolutely produce things it hasn't seen.
Also I think it's too simple to just assert that LLMs are not intelligent. It mostly depends on your definition of intelligence and there are lots of philosophical discussions to be had (see also the AI effect).
One quick typo I noticed: "For reference, one letter is a byte and a gigabyte is roughly a trillion bytes". That's billion of course.
Otherwise, great article!
1,073,741,824 bytes to be exact - not to brag, but knowing that number off by heart is my personal nerd street-cred.
that's a gibibyte
a gigabyte is 10^9
It was a gigabyte first, before those heckin' marketing people came around.
But yes, you're right.