This media is not supported in your browser
VIEW IN TELEGRAM
CliGPT – Less Time Searching, More Time Commanding
Streamline your terminal experience by generating Linux commands from natural language queries, reducing the need to leave the terminal for manual web searches.
Prompt used:
You are my Command Line Interface generator and will assist me to navigate my linux. All my questions are related to this. Now, how can I: [task description]
Github
Streamline your terminal experience by generating Linux commands from natural language queries, reducing the need to leave the terminal for manual web searches.
Prompt used:
You are my Command Line Interface generator and will assist me to navigate my linux. All my questions are related to this. Now, how can I: [task description]
Github
👍8❤5🤩1
ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks
Using a sample of 2,382 tweets, we demonstrate that ChatGPT outperforms crowd-workers for several annotation tasks, including relevance, stance, topics, and frames detection. Specifically, the zero-shot accuracy of ChatGPT exceeds that of crowd-workers for four out of five tasks, while ChatGPT's intercoder agreement exceeds that of both crowd-workers and trained annotators for all tasks. Moreover, the per-annotation cost of ChatGPT is less than $0.003 -- about twenty times cheaper than MTurk.
ChatGPT outperforms humans on 4/5 tasks, while being 20x cheaper.
Paper
Using a sample of 2,382 tweets, we demonstrate that ChatGPT outperforms crowd-workers for several annotation tasks, including relevance, stance, topics, and frames detection. Specifically, the zero-shot accuracy of ChatGPT exceeds that of crowd-workers for four out of five tasks, while ChatGPT's intercoder agreement exceeds that of both crowd-workers and trained annotators for all tasks. Moreover, the per-annotation cost of ChatGPT is less than $0.003 -- about twenty times cheaper than MTurk.
ChatGPT outperforms humans on 4/5 tasks, while being 20x cheaper.
Paper
👍8👀4😱2❤1🔥1🗿1
Words of input -vs- Age, for humans and GPT-3
GPT-3 receives 10,000x to 100,000x more words than humans do, but in many areas humans still crush it.
Something is missing. Something that could enable AI to achieve higher intelligence with 10,000x to 100,000x less external training input.
Upper bound from: Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner
Lower bound from: What Do North American Babies Hear? A large-scale cross-corpus analysis
GPT-3 receives 10,000x to 100,000x more words than humans do, but in many areas humans still crush it.
Something is missing. Something that could enable AI to achieve higher intelligence with 10,000x to 100,000x less external training input.
Upper bound from: Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner
Lower bound from: What Do North American Babies Hear? A large-scale cross-corpus analysis
👍7👏2❤1
Verbal analogies edition, and then feeding the question to GPT-4 in a different session, and then feeding the answers back into the first.
Of course GPT-4 rates itself as brilliant.
Ask me 5 different multiple-choice verbal analogy questions and analyze how smart you think I am according to my answers. Ask all the questions in one go and I will reply.
Of course GPT-4 rates itself as brilliant.
Ask me 5 different multiple-choice verbal analogy questions and analyze how smart you think I am according to my answers. Ask all the questions in one go and I will reply.
👍2😁2❤1🎉1
Verbal Analogies Test: GPT-3.5 edition.
GPT-4 makes questions,
GPT-3.5 answers questions,
GPT-4 grades them.
Result:
GPT-4 says GPT-3.5 is a retard.
GPT-4 makes questions,
GPT-3.5 answers questions,
GPT-4 grades them.
Result:
GPT-4 says GPT-3.5 is a retard.
😁20👏5❤2