Skip to main content
Share Your Experience: Take the 2024 Developer Survey

Questions tagged [chatgpt]

For questions related to the OpenAI ChatGPT model/chatbot, which was trained by Reinforcement Learning from Human Feedback (RLHF).

Filter by
Sorted by
Tagged with
-1 votes
0 answers
8 views

Data presentation graduality and presentation graduality (pages) speed of depth (how fast the data in pages is presented) [closed]

I would like to ask, how does artificial intelligence navigate knowledge, to determine the most suitable, presentation, and presentation gradualità, of data. In books, normally, diagram present a ...
Joselin Jocklingson's user avatar
-2 votes
0 answers
11 views

Eliminating images from AI responses in ChatGPT

I am using chatgpt to reason and memorize. However, as of lately it seems to be forcing me to use a chat with images. However, images, means I must immerse myself in the symbolic content of the image, ...
Joselin Jocklingson's user avatar
0 votes
0 answers
10 views

Best Searchbots that explain code

Of all the LLM based available searchbots which ones are best at explaining code from Java, Python, Golang or Javascript? ChatGPT, Bing Copilot, Claude, Groq or Le Mistral?
user721025's user avatar
0 votes
1 answer
43 views

How does ChatGPT assign confidence level?

How does ChatGPT assign confidence level to its answer? What is the mathematical description of it? Here is my guess. It produces many answers from auto-regression. It already has a probability ...
Hans's user avatar
  • 101
0 votes
0 answers
13 views

Unable to Save Generated Data to JSONL File - Always Resulting in "Wrote 0 examples to finetuning_events.jsonl" Message

Issue Description When attempting to generate JSONL data using Llama Index, the process works well until the final step where the results are saved to a JSONL file. However, every time I try to save ...
gluck0101's user avatar
  • 101
2 votes
1 answer
67 views

What are these special "AI chips" actually used for?

To make an AI / LLM, like ChatGPT, you need two things: To create the LLM. This includes training it, etc. Very expensive from computation perspective. Run the LLM to answer user queries. For ...
ineedahero's user avatar
1 vote
1 answer
26 views

Discrepancies in the Exclusion of Elements in Image vs. Text Generation

(The following comments concern DALLE, I have not tested it with other image generating tools, but would be curious to hear if the same happens) When generating images, it seems that ChatGPT (i.e. ...
Léreau's user avatar
  • 113
1 vote
2 answers
110 views

How are sentences turned into a vector in LLM

My understanding of Large Language Models like GPT is that they are special kinds of deep neural networks specifically trained to predict the next word, given the beginning of a sentence. I understand ...
Weier's user avatar
  • 131
4 votes
1 answer
784 views

How can Transformers handle random sequences?

I have asked ChatGPT the following: Can you concatenate jfef9230rj2mreg90r23ewfrn02eqwdk and 32ir20r3i2ofg90r32kee? And without any error the model produces: ...
killertoge's user avatar
0 votes
2 answers
112 views

What is an "inference kernel"?

In the recent event where ChatGPT "went crazy", this term was used in the official post-mortem to describe what happened: In this case, the bug was in the step where the model chooses these ...
hippietrail's user avatar
1 vote
3 answers
352 views

How to force LLM (like OpenAI ChatGPT) to output a variable list of values? [closed]

What prompt (or other technique) should I use with an LLM so that The result is guaranteed to be reliably parseable as a list of values (e.g. a Python list of strings) LLM would understand that a ...
Elijas Dapšauskas's user avatar
0 votes
1 answer
81 views

Why is generative QA + RAG so popular when extractive QA models exist that can provide factual information?

If the concern with using generative models for question answering is that these models aren't always producing factual information, why is it that people are using these models with Retrieval ...
Celi Manu's user avatar
  • 103
0 votes
1 answer
120 views

Does Chat-GPT learn from interactions? [closed]

Does Chat-GPT accumulate knowledge through interactions with users in real time? I know it's trained on a massive dataset but does it do online learning?
FourierFlux's user avatar
-3 votes
1 answer
108 views

ChatGPT epic creativity fail [duplicate]

My question to ChatGPT, after reading about a vole (as a German I had to look it up) and immediately associating "mole": "Here are pairs of animal names which differ only in the first ...
Hauke Reddmann's user avatar
1 vote
1 answer
31 views

publically available language models that can be used to train arbitrary language data?

I have sentence data in a language that is not widely in use and as such popular LLMs do not support the language. I want to train some language model such that given some question, it is able to ...
Neijal Kanderbalt's user avatar
3 votes
3 answers
3k views

Do AI-based code-generators guarantee correct output?

I haven't spent much time looking at AI-based code-generators. What mechanism is used to generate code and how is it different than standard NLP?
FourierFlux's user avatar
0 votes
1 answer
93 views

How does chatgpt interpret prompts? [closed]

First of all, my English isn't very good, please bear with me. I've heard that chatgpt is a decoder-only model, which doesn't use any encoder model. How does it interpret our prompts if it doesn't use ...
duh's user avatar
  • 11
1 vote
1 answer
407 views

What is accelerated years in describing the amount of the training time?

As described in this article, it was written that GPT-3 took 405 V100 years to train in 2020. I'm a bit confused about this definition, does that mean the process was accelerated like using a V100 GPU ...
Marziye Hasanshahi's user avatar
0 votes
1 answer
509 views

How does Chat GPT encode a question?

Chat GPT is based on a decoder-only Transformer so it does not have an encoder. Given that, how is a user's question passed as input to Chat GPT's decoder? In a regular encoder-decoder architecture, ...
joan's user avatar
  • 1
0 votes
0 answers
102 views

Intentionally corrupting LLM weights (lobotomy)

It is largely unknown how LLMs work inside. Has anyone scientifically tried to corrupt (open source) model's weights in an organized manner to maybe detect which parts of the model are doing what or ...
Kozuch's user avatar
  • 281
0 votes
0 answers
82 views

Why is chatGPT 4 unable to correct a program given its output?

Recently I used chatGPT 4 to write a small project in Perl which involved reading of an exam file (multiple choice), comparing it to a master exam file, and scoring the student exam including fraud ...
CuriousIndeed's user avatar
0 votes
0 answers
18 views

Could an analysis of GPT4's WAIS score be published?

Similar to this: https://www.scientificamerican.com/article/i-gave-chatgpt-an-iq-test-heres-what-i-discovered/ But more detailed and in depth (subtest breakdown, including image analysis, etc.), WAIS-...
BigMistake's user avatar
1 vote
1 answer
800 views

How LLM keeps the context of a chat/thread

How an LLM keeps the context (what has already been entered by the user) of a chat/thread? For reference, in chat.openai.com, for each chat we create (or a Thread according to their API), the LLM ...
Wenuka's user avatar
  • 111
1 vote
3 answers
72 views

Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?

Imagine we have some sort of "next token predictor," either with transformer architecture, LSTM, or just a HMM (though the terminology I use here will be less aligned to HMMs, I believe the ...
BigMistake's user avatar
0 votes
0 answers
42 views

When using Reinforcement Learning with Human Feedback to train a transformer, how do I propagate the feedback through the transformer?

I'm basically trying to replicate the processed used to create Chat GPT: Am I supposed to backpropagate? How can I do that when these aren't really errors, but rather ranking several response? Can I ...
Austin Capobianco's user avatar
1 vote
0 answers
194 views

What is 'system card'?

What is 'system card' in these context: https://ai.meta.com/blog/system-cards-a-new-resource-for-understanding-how-ai-systems-work/ Additionally, individual model developers may provide ...
Vy Do's user avatar
  • 111
27 votes
4 answers
15k views

Why do ChatGPT “jailbreaks” work?

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the ...
TylerDurden's user avatar
0 votes
0 answers
79 views

Are "Custom Instructions" injected into the context window repeatedly?

ChatGPT (the conversational front-end to GPT 3.5 and GPT 4) includes user configurable custom instructions. They allocate 1500 characters to "what you would like chatGPT to know about you" ...
Althea Delwiche's user avatar
0 votes
0 answers
70 views

claude 2 doesn't know basic math? [duplicate]

Sometimes, when I see answers like this from large language models, it makes me feel disgusted: Me: Does Voyager 1 have enough velocity to escape the solar system without using Jupiter's gravity ...
Mr Saw's user avatar
  • 1
0 votes
0 answers
45 views

What is the reason that OpenAI implements complex context management in ChatGPT but does not use it for their API?

According to this discussion How does ChatGPT retain the context of previous questions? it is clear that OpenAI already has implemented some serious engineer to ensure that the ChatGPT experience is a ...
erotsppa's user avatar
  • 101
-2 votes
1 answer
31 views

Dynamic text completion [closed]

I am using the get_completion function to generate response to a question. Since generating response takes a long time (~5 seconds) I would like to display the response text as it's generated (...
afshi7n's user avatar
  • 97
1 vote
1 answer
106 views

Why do current language models no longer generate to long or short texts?

One of the biggest strengths of ChatGPT is that it generates fitting text with respect to the input query. It usually stays on topic, anwers the question completely and especially does not start ...
Ricu's user avatar
  • 11
1 vote
2 answers
450 views

Tips and tricks when training a very large language model?

Have never trained a (very) large language model, so I am wondering if the process is the same as training a (regular) language model, i.e. you prepare the data, set up the architecture, ...
information_interchange's user avatar
0 votes
0 answers
55 views

How to get GPT to complete all tasks before ending its turn?

I'm trying to figure out how ChatGPT and Code Interpreter (or anything else) gets GPT to complete an arbitrary number of actions before it ends its turn and hands it back to the user. I'm using a ...
coinmaster's user avatar
0 votes
0 answers
74 views

How does query of LLM/GPT models work?

Training of LLM aka GPT models is clear on how is trained but can't find any info how is "mapped" query to internal tokens and generates response tokens more precise inference phase which ...
n1tk's user avatar
  • 101
3 votes
0 answers
283 views

What strategy does ChatGPT use to manage its context in very lengthy conversations?

I'm asking specifically about ChatGPT4, but the question could apply to either that or 3.5. When you use the ChatGPT API, it's of course up to you to manage conversation history and include that in ...
Ascendant's user avatar
  • 131
15 votes
6 answers
7k views

Why do many AI bots feel the need to be know-it-alls?

Having used various AI bots often over recent months, I noticed that often it will claim to know something, even if it doesn't. It would then either explain something which is clearly nonsense, or by ...
ben svenssohn's user avatar
0 votes
1 answer
81 views

Noob crafting a simple "Zero-Shot Classifier" Using an API . How can I avoid passing the categories every single request? [closed]

I have a collection of 700 categories, all potential classifications for articles. My current need is to create a system that can dynamically categorize short texts or articles according to these 700 ...
Advanced's user avatar
  • 109
0 votes
1 answer
107 views

Randomness in Google Bard answers [closed]

I tried Google Bard now recently for the first time after we got into here in Finland too. And to my surprise it gives different answer each time I ask the same question. Is this a feature of LLM or ...
harism's user avatar
  • 125
2 votes
2 answers
344 views

Are LLM hallucination necessarily a bad thing?

I've been pondering over this for a while now: is the so-called hallucinating necessarily a problem in LLM or in AI in general? What it stands for anyway, maybe the model is trying to crunch so much ...
harism's user avatar
  • 125
2 votes
1 answer
110 views

Could hallucinations be the demise of the AI hype? [closed]

For quite some time now, I have been evaluating ChatGPT's capability to deliver accurate and helpful responses. While its performance is undeniably impressive, the issue of hallucinations poses a ...
machine_1's user avatar
  • 133
1 vote
2 answers
235 views

How is LLM generated content moderated?

I'm looking for references (articles) about how LLM generated content is moderated. From a technical point of view, what makes the difference between a so-called "uncensored" LLM such as ...
StashOfCode's user avatar
3 votes
2 answers
4k views

How to Formulate a realiable ChatGPT Prompt for Sentiment Analysis of a Text, and show that it is reliable?

I have a dataset which consists of like.. 400000 sentences and I want give each sentence to ChatGPT so it classifies each sentence as positive or ...
cnmesr's user avatar
  • 131
0 votes
1 answer
151 views

Does the output of LLM's affect their neural weights?

When an LLM creates an output, it seemingly has no way to check if its output was valid. Therefore it wouldn't be able to back-propagate any changes to the weights is used to create that output. ...
Seph Reed's user avatar
  • 103
1 vote
2 answers
107 views

Is it possible to have a ChatGPT bot that can answer questions about sensitive information without using external servers?

We have a lot of internal documentation that contains sensitive information. Is it possible to have a ChatGPT bot that can answer questions about this information, to my used by users with clearance ...
BanksySan's user avatar
  • 111
0 votes
0 answers
206 views

ChatGPT request/prompt structure: Put Persona into the "system" field. Add or replace?

On  playground.openapi.com   we see a more advanced view of the chat window that chat.openai.com offers (that's the more well-known GUI shown in countlerss screenshots and tutorial videos). On the ...
knb's user avatar
  • 165
0 votes
0 answers
274 views

Extract multiple records from raw text using open AI API function calls

Trying to extract records from pdf. The plan was to convert pdf data to raw text and use open AI api calls to extract the data in a desired format (csv). This is because the pdf data is very ...
viraj jadhav's user avatar
1 vote
1 answer
57 views

What is an appropriate tool to use that takes in a large knowledge base in string form and can answer questions based on the knowledge base?

I have an issue where I'm trying to use the openAI API to input a very large custom knowledge base (exceeding 1GB) that allows the user to ask questions based on that base to receive intelligent ...
Hou Wan's user avatar
  • 11
0 votes
0 answers
27 views

Does ChatGPT have access to real-time data? [duplicate]

I wanted to see if ChatGPT knows the current time or not, and it persisted that it does not have access to any real-time data and its knowledge is limited to the year 2021 and before. But how does it ...
Shayan's user avatar
  • 101
1 vote
1 answer
387 views

Why is ChatGPT fast on some questions and slow on others?

When using ChatGPT i have noticed it is fast on some questions and slow on others. Why is that? Based on my understanding of the transformers architecture, the user prompt is tokenized and the vector ...
morpheus's user avatar
  • 294