honest question, how long do we think twitter will be usable for in its current form ran a little experiment earlier today and copy pasted like 10 of @tszzl most liked tweets into gpt4 and asked it to generate tweets in a similar style and some of them were pretty damn good
PROMPT ENGINEERING
-
Tweet generator collaboration without extensive fine-tuning required
By
–
worked close to as well as @ctjlewis tweet generator without needing hours of finetuning
-
OpenAI GPT-4 Developer Livestream: Features and Capabilities Overview
By
–
One last thing: OpenAI just hosted GPT-4 Developer Livestream. This is a nice watch and a quick way to see a glimpse of all cool things you can do with GPT-4. https://
youtube.com/watch?v=outcGt
bnMuQ
… -
GPT-4 Socratic Mode: Interactive Problem-Solving for Education
By
–
GPT-4 has a new mode of operation where instead of directly answering your question as classic ChatGPT does, it will involve you in the problem-solving process. This mode seems like a nice way of using large language models in education. Socratic tutor
-
GPT-4 Jailbreaks Will Be Rarer But More Extreme
By
–
gpt4 jailbreak prediction jailbreaks will be more difficult to write but for the ones that DO work, they will produce behavior that is wayyy more unhinged than in gpt 3.5
-
Vision Capability Breakthrough: Testing Confirms Strong Performance
By
–
We tried and it solves it :O. The vision capability is very strong but I still didn't believe it could be true. The waters are muddied some by a fear that my original post (or derivative work there of) is part of the training set. More on it later.
-
OpenAI Adds System Message Support for AI Behavior Customization
By
–
we now support a “system” message in the API that allows developers (and soon ChatGPT users) to have significant customization of behavior. if you want an AI that always answers you in the style of Shakespeare, or in json, now you can have that.
-
GPT-4’s Compositional Abilities Demonstrated Through Creative Examples
By
–
This example of a pirate explaining taxes in the style of shakespeare indicates so many levels of compositionality. The qualitative experience of GPT-4 is remarkable and will unlock a world of new use cases!
-
GPT-3 paradigm shift from task-specific models to few-shot prompting
By
–
Before GPT-3, we fine-tuned a task-specific neural network (e.g., BERT) for each task that we wanted to solve.
With GPT-3, there was a paradigm shift to using a single large language model for any task via few-shot prompting. -
Claude: Multifunctional Conversational Assistant in Natural Language
By
–
You can chat with Claude, give it prompts to generate text, get Q&A responses and summaries, translate between languages, give it multi-step instructions and more using natural language.