[HN Gopher] I wrote a meta mode for ChatGPT ___________________________________________________________________ I wrote a meta mode for ChatGPT Author : airesearcher Score : 57 points Date : 2023-12-10 20:06 UTC (2 hours ago) (HTM) web link (www.novaspivack.com) (TXT) w3m dump (www.novaspivack.com) | airesearcher wrote: | I wrote a custom instruction for ChatGPT Pro that radically | improves productivity inside ChatGPT. Add it to your custom | instructions and enjoy! | philipswood wrote: | Links to a WordPress login page. | | You mean probably meant: | | https://www.novaspivack.com/technology/nova-mode-the-ultimat... | airesearcher wrote: | Ah yes good point | Tiberium wrote: | Can you share how it radically improves productivity? From a | quick glance it seems to be not very practical, at least for | me. | airesearcher wrote: | Main URL has been corrected thanks to the moderators. | dr_dshiv wrote: | It's neat but I would love to see some more examples of why you | think it is good. I tend to be skeptical of adding anything to | the context window that isn't closely aligned with my goals. My | biggest issue is usually getting chatGPT to get out of the | "blurry center" (where it just blathers pablum) to a "productive | spike" where it can genuinely do specific work. | sp332 wrote: | I agree, at least add some sample outputs so we can see what | we're getting into. | airesearcher wrote: | See my post and scroll down. Several examples there. | | You can also add the instructions and type //? For the | manual. | | Or type //$ for a list of 40 examples | airesearcher wrote: | I will make a GPT version... ChatGPT has to approve it for | some reason.... | | ok it's working ... had to remove "ChatGPT" from name of my | GPT for it to work... | airesearcher wrote: | https://chat.openai.com/g/g-tcXXGxXmA-nova-mode-ai-chat- | auth... | | GPT Version, with more features | simonw wrote: | I suggest also making this available as a GPT. I don't like | pasting random stuff into my custom instructions, because that | will affect all of my future usage. I'd much rather try out a GPT | where the effects of those instructions stay limited to that one | place. | airesearcher wrote: | https://chat.openai.com/share/3ebde0ee-5db6-44c3-a836-2b4ee3... | airesearcher wrote: | Waiting for ChatGPT to approve this link... not sure it is | public yet | airesearcher wrote: | ok it's working ... had to remove "ChatGPT" from name of my | GPT for it to work... | bongodongobob wrote: | I don't see why this is good. You're clogging your context with a | bunch of unnecessary clutter. Just tell it what you want it to | do, no? Like why am I spending 1500 characters per message on the | hello world loop example? I get the same output from just asking | it to do that. | | The message indexing is kind of interesting, but again, it's a | huge waste. Just write a wrapper rather than wasting all those | tokens and muddying your context. | | I think in the end this is just eye candy and is going to get you | worse results. Granted, I haven't tested thoroughly, but neither | has OP. | airesearcher wrote: | It's useful because it allows you to refer to messages in the | chat by message number, and to define functions to use on them. | You can do a lot of really powerful things with it. | airesearcher wrote: | Here it is a GPT if you want to try it that way: | | https://chat.openai.com/share/3ebde0ee-5db6-44c3-a836-2b4ee3... | airesearcher wrote: | I will make a GPT version... ChatGPT has to approve it for some | reason.... | airesearcher wrote: | It works now | sitkack wrote: | Neat. I did something similar and created a stack based NLP | language, I used it, mainly for synthesizing prompts for image | generation. | airesearcher wrote: | Type //? for the manual | EMM_386 wrote: | I'm not much interested in the prompt itself, but I am | continually amazed that ChatGPT is able to make sense of prompts | like this. | | That is pretty far from "language", and I can't see how any of | that has been seen in its "training data". | | I mean ... you can add something like "//! = loop mode = do loop: | (ask USR for instruct (string, num); iterate string num times); | Nesting ok." and it can not only parse that (or "tokenize" it), | then somehow find relationships in its internal high-dimensional | vector space that are sufficient to ... pseudo-"execute" it? | | I don't know. Obviously, not my area of expertise, although I can | say I've spent a lot of time _trying_ to understand even the | basics. But then I 'll see an example like this, and be reminded | of how little I understand any of it. | jadbox wrote: | I wonder how much "gpt" within openai understands and how much | syntax is conditionally parsed and run though state machines | prior to the prompt sent to transformers. | huijzer wrote: | I did my MSc thesis on ML in 2019 and so I'm definitely no | expert but one mental model worked well for me. | | Machine learning models learn thousands of small functions | which map input to output. A higher level "function" will | choose which function is used to map the input to the output. | So that's what amazed me in about ChatGPT: think about all the | little things it must understand to do what it does. For | example, the model learned how to interpret if clauses and | other language nuances, how variable definitions should be | used, what words are in other languages. | AndrewKemendo wrote: | If you think about it relative to the level of specific | interaction you're doing with a computer, then it makes sense | | So, for example, if I'm talking to a compiler, I have to talk | to it in effectively perfect sequential structure | | If I'm talking to a web server, then it's with a scripting | language in order to communicate something from another | programming language that's interacting it lower level | | At the other extreme if I'm talking to a kernel, then I really | only have a couple of things I can say because its language is | memory blocks | | In this case, because I'm talking to what's effectively an | interpreter, then the default language looks like a scripting | language rather than a programming language or natural language | | Which in effect is what's happening? These are basically | scripts people are running against the structure of the GPT | sequence interpretation - so it's a weird mix ___________________________________________________________________ (page generated 2023-12-10 23:00 UTC)