Subj : ChatGPT made its own language to extend conversations, and it's g To : All From : TechnologyDaily Date : Wed Apr 12 2023 07:15:03 ChatGPT made its own language to extend conversations, and it's getting freaky Date: Wed, 12 Apr 2023 06:00:49 +0000 Description: Meet Shogtongue, ChatGPTs own language to extend entire conversations FULL STORY ====================================================================== Its no Skynet (yet), but ChatGPT did just make up its own language to extend its 8K-limit conversations. In a stranger turn of events, ChatGPT users have discovered that GPT-4 is able to compress a long conversation and create a sort of compression language that you can then utilize as a new prompt later. When entered as a new prompt in the chat, this essentially recreates that same exact conversation. In effect, it not only allows you to pick up where you left off but also extends ChatGPT conversations beyond their word limit. As you know, ChatGPT has a word limit though as to what that number is, reports seem to vary. Some say GPT-4 gives you about 25,000 words while writer Jeremy Nguyen says its around 8,000K words. Not that most users tend to reach that cut-off, but it does mean that if your current conversation goes on for too long, ChatGPT might simply cut off, even mid-sentence. As a result, you would have to start a brand-new chat, which can be extremely frustrating if you're not finished and need more information. Christened as Shogtongue by gfodor on Twitter, this new compression language lets you get around that word count so you can continue your conversation, which is extremely useful especially if your query has morphed into a complex rabbit hole or your chat has turned into a month-long chat (or you simply need a bestie who will remember everything youve told them in the past). GPT-4 still needs context According to Nguyen, ChatGPT wont simply create a compressed message for you when its running out of words. You still have to ask it to compress that current conversation with very specific instructions. In his example, he specified that the compression should be lossless but results in the minimum number of tokens that could be fed into an LLM like yourself as-is and produce the same output. He also instructed it to utilize different languages, symbols, and other up-front priming. The same has to be done when entering that compressed message in a new chat to give it a hand although it seems like some GPT-4 users arent doing so, adding context just helps minimize errors. Its worth noting that this language isnt foolproof yet. According to Nguyen, GPT-3.5 is unable to read the compressed language, and GPT-4 via API struggles. It works best on GPT-4, which is a refined version of its predecessors, via ChatGPT. So, if you think its going to be a long, convoluted conversation that would make Proust proud, you better stick with that chatbot. If youd like to know more about ChatGPT, heres everything you need to know about the AI chatbot . Not a fan? Perhaps youll like Google Bard better. ====================================================================== Link to news story: https://www.techradar.com/news/chatgpt-made-its-own-language-to-extend-convers ations-and-its-getting-freaky --- Mystic BBS v1.12 A47 (Linux/64) * Origin: tqwNet Technology News (1337:1/100) .