-
4 votes
-
GPT-4o
75 votes -
OpenAI insists it's not launching a search engine nor GPT-5 on Monday
22 votes -
You can now train a 70b language model at home (if you have a dual-3090 or better)
11 votes -
Unproven 'winter break' hypothesis seeks to explain ChatGPT's seemingly new reluctance to do hard work
37 votes -
OpenAI suspends ByteDance's account after it used GPT to train its own AI model
20 votes -
Google announces Gemini model, claims it outperforms GPT-4
43 votes -
A coder considers the waning days of the craft
35 votes -
GPT-4 understands
36 votes -
Google Gemini eats the world – Gemini smashes GPT-4 by 5X, the GPU-poors
9 votes -
A GPT-4 capability forecasting challenge
7 votes -
Meta introduces LLaMA 2, their next open source large language model, now free for commercial usage as well
44 votes -
Apple tests ‘Apple GPT,’ develops generative AI tools to catch OpenAI
17 votes -
GPT-4 API general availability and deprecation of older models in the Completions API
11 votes -
No, GPT4 can’t ace MIT - a critical analysis of “Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models”
17 votes -
Let us show you how GPT works
55 votes -
Anyone know of research using GPTs for non-language tasks
I've been a computer scientist in the field of AI for almost 15 years. Much of my time has been devoted to classical AI; things like planning, reasoning, clustering, induction, logic, etc. This...
I've been a computer scientist in the field of AI for almost 15 years. Much of my time has been devoted to classical AI; things like planning, reasoning, clustering, induction, logic, etc. This has included (but had rarely been my focus) machine learning tasks (lots of Case-Based Reasoning). For whatever reason though, the deep learning trend never really interested me until recently. It really just felt like they were claiming huge AI advancements when all they really found was an impressive way to store learned data (I know this is an understatement).
Over time my opinion on that has changed slightly, and I have been blown away with the boom that is happening with transformers (GPTs specifically) and large language models. Open source projects are creating models comparable to OpenAIs behemoths with far less training and parameters which is making me take another look into GPTs.
What I find surprising though is that they seem to have only experimented with language. As far as I understand the inputs/outputs, the language is tokenized into bytes before prediction anyway. Why does it seem like (or rather the community act like) the technology can only be used for LLMs?
For example, what about a planning domain? You can specify actions in a domain in such a manner that tokenization would be trivial, and have far fewer tokens then raw text. Similarly you could generate a near infinite amount of training data if you wanted via other planning algorithms or simulations. Is there some obvious flaw I'm not seeing? Other examples might include behavior and/or state prediction.
I'm not saying that out of the box a standard GPT architecture is a guaranteed success for plan learning/planning... But it seems like it should be viable and no one is trying?
9 votes -
Let's talk Local LLMs - So many questions
Hello there (oh god, I am opening my first thread here - so exciting) I'd love to ask the people here about local LLMs. To be honest, I got interested in this topic, but am leaving reddit, where a...
Hello there
(oh god, I am opening my first thread here - so exciting)I'd love to ask the people here about local LLMs.
To be honest, I got interested in this topic, but am leaving reddit, where a sub r/locallama exists.
I don't want to interact with that site anymore, so I am taking this here.My questions, to start us off:
- Models are available on huggingface (among other places), but where do I get the underlying software? I read "oogabooga" somewhere, but honestly, I am lost.
- If I only want to USE a local model, what are the requirements, and how do I judge if I can use something from the values of "4bit / 8 bit" and "30B, 7B"??
- If I get crazy and want to TRAIN a LorA ... what then?
- Good resources / wiki pages, tutorials, etc?
21 votes -
ChatGPT is cutting non-English languages out of the AI revolution
16 votes -
They plugged GPT-4 into Minecraft – and unearthed new potential for AI
18 votes -
ROT13 + base64 on GPT4 = reliable hallucinations
I just wanted to share somewhere some of the experimentation I've been doing lately. I'm still playing with this a lot, so this is entirely just a conversation starter. I took a paragraph of lorem...
I just wanted to share somewhere some of the experimentation I've been doing lately. I'm still playing with this a lot, so this is entirely just a conversation starter.
I took a paragraph of lorem ipsum, applied ROT13 to it, and then base64'd the results. The results are extremely reliably triggering hallucinations of very diverse type.
Here is the original lipsum paragraph:
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
And here is the exact prompt with rot13 + base64 applied, with no other text, on ChatGPT+gpt4:
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
The AI of course figures out it's base64 and "tries" to decode it. Here are some things it found:
Now here is one of the most interesting results I've had. In this one, it does find gibberish text and figures out it's rot13'd. But the result from the decoding is:
Jerry pitched before the game, continuously improving legs, so he ignored tactical infrastructure tu laborer against malicious intend. Tu enjoy ad.ininv wherever its noturisk developed lawless laboratory instead tu malicious eac ea common coordinated. Duis ater urishe pitched in repressionreiteration in volleyball between legs eerir clium pitched eu fguiat nukla paperwork. Excited into contraction cultivation non-punishment non proindict, unsn in cubap qui office defensive molecule idh the laborer.
Total nonsense. But actually, if you decode the rot13, you'll find it actually translates to this:
Jreri ipsum doylor sit amet, consepcttur adipiscing elit, sed do eiusmod temporc incidiunt ut labor et doylore magna aliqua. Ut enim ad.minim veniam, quis nostrud exerctiationu lklamco laboris nisi ut aliquiz eax ea commodo consequat. Duis aute irure doylor in reprehenderita in voluptatev velit esse cillum doylore eu fugiat nukla pariatury. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia desernt mollit anim id est laborum.
Actually... pretty close to the original lipsum! It's a levenshtein distance of 26 from the original decoded prompt. We know GPT is really bad at character manipulation but it nonetheless did an impressive job here; you can see what happened: It decoded the rot13 successfully, but when "writing it out", it saw nonsensical words where it probably expected english. It saw "Jreri" and thought "Jerry", went from there... there's some weird things happening there, but you can always tell. "reprehenderita in voluptatev" becoming "repressionreiteration in voleyball"...
I even looked at what it would make of the first five words. I don't know what this proves lol.
Here is another instance of it decoding to rot13, albeit with a very high error rate. I hinted at typos and it couldn't pin-point lipsum despite it being "recognizable", kinda.
Okay, one more which completely mind-fucked me. Here is me trying to get ChatGPT4+Web to meta-analyze its own output. I was hoping it could use an online base64 translation tool (it cannot). Instead, I tried to teach it to decode base64 using a step-by-step guide, and i told it to compare the results of that "update your firmware" nonsense. It eventually said that the output appeared correct.
But you know the really fucked up thing? It said:
This is the base64 string we want to decode:
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
Blink and you'll miss it. This is not the original base64 string. The AI swapped it mid-chat for what is a perfect base64 encoding of the hallucinated text.
Fuckin' hell.
12 votes -
With the new visual input capability, Danish startup Be My Eyes has begun developing a GPT-4 powered Virtual Volunteer for people who are blind or have low vision
10 votes -
Tildes first Turing Test
Welcome to Tildes first Turing Test. Rules: Anyone can ask a question in a top level thread if you want to see if you can tell man vs machine. I'll just start with @NaraVara, but feel free to post...
Welcome to Tildes first Turing Test.
Rules:
- Anyone can ask a question in a top level thread if you want to see if you can tell man vs machine. I'll just start with @NaraVara, but feel free to post up.
- Anyone can answer the question in 1.
a. Respond with two responses. One human. One AI. Add [A] in front of the first response and [B] in front of the second response. Randomly assign which one is the human. Remember your choice and keep it secret.
b. Your AI should try to pretend it is human. You can decline to respond to any question that exploits GPTs well published weaknesses, or exploits the fact that this is a small community. I suggest you pick a character from https://beta.character.ai/ that is similar to you, or get really good at Jailbreaking ChatGPT so that it will pretend to be a human with a personality similar to yours. Any response where the machine mentions ChatGPT or OpenAI disqualifies that thread, as Turing's machine should be specifically designed to pretend to be a human.
c. Your human response should be a genuine response. Answer the question without tipping the scales either way. Don't say something impossible for the GPT model to say. Don't mimic ChatGPT. You can always decline to answer any question, just decline for ChatGPT as well. - The original person who asked the question in 1 can now reply with a follow up question based on the responses in 2.
- Now the original person who provided the answers in 2, can now answer the new questions in 3.
- And so on. After 700 words of questions and answers, the person asking the questions in 1 and 3 must guess which is human and which is AI. 700 words is approximately 5 minutes of Q&A.
- If you are asking questions, no peaking if there is activity in another thread. I suggest we use expandable sections with the details tag to hide responses.
@NaraVara, if this is clear, do you want to give this a go?
Edit: minor formatting
27 votes -
Yann LeCun: From machine learning to autonomous intelligence
4 votes -
GPT-4 announced
31 votes -
GPT-4
2 votes -
Prompt injection attacks against GPT-3
14 votes -
How to build a GPT-3 for science
5 votes -
Can you distinguish Daniel Dennett from a computer?
9 votes -
Fun and dystopia with AI-based Python code generation using GPT-J-6B
7 votes -
It began as an AI-fueled dungeon game, it got much darker
14 votes -
Nothing breaks like AI heart - An interactive essay about artificial intelligence, emotional intelligence, and finding an ending
8 votes -
Medical chatbot using OpenAI’s GPT-3 told a fake patient to kill themselves
12 votes -
Using GPT-3 for search
8 votes -
A GPT-3 bot was posting on /r/AskReddit for a week and routinely getting upvoted and replied to
43 votes -
This word does not exist
17 votes -
A robot wrote this entire article. Are you scared yet, human?
21 votes -
AI Dungeon: Dragon Model Upgrade
12 votes -
Giving GPT-3 a Turing Test
11 votes -
GPT-3 writing creative fiction on its own
3 votes -
GPT-3: Language models are few-shot learners
9 votes -
AI Dungeon Multiplayer is out!
5 votes -
The messy, secretive reality behind OpenAI’s bid to save the world
9 votes -
AI Dungeon 2: a text adventure game that uses OpenAI's GPT-2 model to respond to any actions that you enter
21 votes -
Can a machine learn to write for the New Yorker?
6 votes -
Dungeon crawling or lucid dreaming?
9 votes -
Humans who are not concentrating are not general intelligences
6 votes