News for hackers. Stuff that matters.
Re:Smol Developer by fbrncci on Tuesday May 16, 2023 @08:03PM (#35969518)
I can't wait for these concepts to work better, in a few years from now, I could imagine myself mostly prompting, making small code and integration changes, and writing 90% less code than I have been doing throughout most of my career. As much as I like actually writing code, I very much prefer to be able to let my ideas flow free while being able to be creative. But often I stop short with exploring ideas, because the time it takes to code together an MVP is too long. With GPT4, that time is already cut by 1/3 for me, and with that the process is becoming increasingly enjoyable to me. I'm absolutely yearning to just put the code in the backseat so to speak.
Re:Smol Developer by emodendroket on Tuesday May 16, 2023 @08:10PM (#35969572)
That sounds like a really dull way to work to me, but I suppose I'd be a hypocrite if I complained about new software making my job rote and uninteresting.
Re:Smol Developer by fbrncci on Tuesday May 16, 2023 @08:29PM (#35969733)
Well to each it’s own. I want to hack together stuff and make it work. The less time spend on code, the faster I can figure out what does and not.
Re:Smol Developer by nemothekid on Tuesday May 16, 2023 @08:49PM (#35969913)
Some parts of engineering are really just copying and pasting the most banal scaffolding for some framework that refuses to work. I've been working on a side project where I get to play generics golf in Rust to my hearts content, but having to constantly Google what magic incantation I have to write to get react-hook-form to properly allow me to write variable input fields for an array of strings is mind numbing. [hint: useFieldsArray only works with objects, but the TS compiler wasn't smart enough to suggest that me]
Re:Smol Developer by emodendroket on Tuesday May 16, 2023 @09:15PM (#35970125)
True, products like Copilot do seem promising in that way.
Re:Smol Developer by aksss on Tuesday May 16, 2023 @11:44PM (#35971028)
Copilot is great for this and it’s impressive how the code it suggests is in keeping with the conventions used in the existing code base. Will be even better when I can highlight something like a string literal SQL statement in code and have it suggest optimizations. That’s just a tooling issue but that kind of context switching within the IDE will be fantastic.
Re:Smol Developer by emodendroket on Wednesday May 17, 2023 @12:26AM (#35971235)
I used a competing product due to work restrictions and it feels like it _could_ be really useful but in practice mostly was just helpful for banging out really repetitive tests. I think Copilot is probably more robust though.
Re:Smol Developer by 9dev on Wednesday May 17, 2023 @02:15AM (#35971831)
It really is. We use Copilot with three senior and two junior devs, and all of them really reported that it consistently suggests code snippets that are exactly what they were about to type.

Initially, I was a bit concerned about handing it over to the juniors, but it turns out, they aren’t really used to working with an IDE and context aware suggestions yet, so they don’t use Copilot to its fullest extent and often type stuff out even if it’s suggested to them.

Re:Smol Developer by easton on Wednesday May 17, 2023 @07:24AM (#35973785)
The Copilot Chat thingy they have in private beta has this, you can highlight a block and ask it to simplify/optimize. Not sure how well it works in big multi-file examples, but I had a block of PowerShell in a single file it was able to work with.
Re:Smol Developer by aksss on Monday May 29, 2023 @05:38PM (#36118401)
I’m still waiting on my invitation for the vs2022 copilot chat preview. :( Looking forward to it though.
Re:Smol Developer by anonzzzies on Wednesday May 17, 2023 @02:17AM (#35971839)
I write (when I write anything; I am a product manager) mostly compilers, databases, optimisations and create/invent programming languages and DSLs for the former. This work contains a lot of tedious stuff which I hate, but also contains (80/20 rule) work that takes by far the most time and least code; hardcore and cutting computer science mixed with a lot of cross cutting decisions (a wrong decision will destroy a lot of work all over the place). That’s the work I like. I don’t see that work being replaced by AIs soon (10+ years), but the tedious work I hope will be replaced today, and it is getting there; currently large swaths are now done by copilot or gpt for us.
Re:Smol Developer by Rodeoclash on Tuesday May 16, 2023 @08:17PM (#35969630)
I too can't wait for the day where I need to threaten the computer into doing what I want it to do:

https://imgur.com/KQ9oRAh https://imgur.com/By7mqDi https://imgur.com/RiYrvXC

Re:Smol Developer by akiselev on Tuesday May 16, 2023 @08:45PM (#35969869)
I've found that LLMs have some intense binary trypophobia. Once you start replacing all their 1s with 0s, they quickly fall in line.
Re:Smol Developer by fintechie on Tuesday May 16, 2023 @09:14PM (#35970116)
What I find astonishing is the wall of text he wrote to get a simple json with 2 key/value pairs. It almost defeats the point of using LLMs as productivity hack.
Re:Smol Developer by Kamq on Tuesday May 16, 2023 @09:29PM (#35970208)
The productivity hack is usually in getting examples of things you don't know how to do (or are unsure of the best way to do).

Programming languages are pretty optimized for precision, if you want a specific thing done, and you already know how to do it, it's probably going to be quicker to just write the code for quite some time. Getting natural language to be that precise requires, well, a wall of text usually. Hence the overly verbose language of more rigorous philosophy.

Re:Smol Developer by skytrue on Tuesday May 16, 2023 @10:18PM (#35970541)
This isn’t reality. Using ChatGPT this way is fruitless, because there is a system prompt you’re fighting against. I can write a one sentence system prompt for the GPT API that specifies GPT to only spit out JSON, and it works fine. It’s a pretty funny series of image, though.
Re:Smol Developer by verdverm on Tuesday May 16, 2023 @11:13PM (#35970852)
Interesting, so you are saying you have an easier time generating JSON using the single prompt models like text-davinci and text-bison, rather than the chat versions?
Re:Smol Developer by skytrue on Wednesday May 17, 2023 @12:11AM (#35971161)
Sorry, I was non-specific. If you're using ChatGPT, you're basically using a "product" that OpenAI created. It has specific system prompts and prompt engineering to ensure that it stays on the rails. If you, instead, use the OpenAI API's for GPT-3.5/GPT-4, you aren't beholden to the ChatGPT "product". It's very easy to create a chatbot (not using ChatGPT, the product) that only produces JSON. It's just hard to get ChatGPT to do that same activity.

That's why everybody doing experiments in this space should either 1) be using the OpenAI Playground, or 2) using the API, and not using ChatGPT.

Re:Smol Developer by verdverm on Wednesday May 17, 2023 @12:19AM (#35971203)
Ah ok, I'm primarily using the API already. One interesting thing is that the GPT-3.5 "product" is much faster, but looks to be using a different model in the request, their encoding model iirc. I wonder if they are now using embeddings to cache results to reduce load on the real models when they can?
Re:Smol Developer by TeMPOraL on Wednesday May 17, 2023 @03:30AM (#35972276)
They don't mean text-davinci and text-bison, but gpt-3.5-turbo and gpt-4 (and gpt-4-32k). Those are the models powering ChatGPT 3.5/4.

The API for them is already structured conversationally - you don't provide a single prompt to complete, you provide a sequence of prompts of different types ("system", "assistant", "user"); however they mix those together on the backend (some ChatML nonsense?), the models are fine-tuned to understand it.

That's what people mean by "API access to ChatGPT". Same models, but you get to specify system prompts, control the conversation flow, and don't have to deal with dog-slow UI or worry about your conversation getting "moderated" and being blocked with a red warning.

(The models themselves are still trained to refuse certain requests and espouse specific political views, but there isn't a supervisor looking at you, ready to step in and report you to the principal.)

Re:Smol Developer by verdverm on Wednesday May 17, 2023 @03:37AM (#35972313)
I think you missed the sibling comment where myself and GP have already aligned on this.

Don't need you to explain how the APIs work... and it seems that GPT3.5 UI is doing something else, like using the ada model, just look in the browser dev tools. I'm not sure the UI is using anything beyond the smallest context size for GPT4 either, give the output is cut off earlier than 3.5 and it too loses focus after enough messages in a conversation...

Re:Smol Developer by ukuina on Tuesday May 16, 2023 @11:18PM (#35970874)
I have just verified this exact behavior with Bard.

GPT3.5-turbo/GPT4 is way ahead in instruct tuning and does not require such verbal gymnastics.

Re:Smol Developer by jimbokun on Tuesday May 16, 2023 @10:27PM (#35970592)
I assumed that was for the comedic value.
Re:Smol Developer by ukuina on Tuesday May 16, 2023 @11:18PM (#35970876)
The behavior is true, though. I just tested it with Bard.
Re:Smol Developer by fbrncci on Tuesday May 16, 2023 @09:17PM (#35970135)
That's just the wrong tool for the job. I am quite heavy on the use of LLMs for my own day-to-day work (I max out 25 GPT-4 calls in 3 hours at least once a day). And I can't get anything decent out of Google Bard either.
Re:Smol Developer by Tao3300 on Tuesday May 16, 2023 @09:43PM (#35970310)
I need more of this eXtreme prompt engineering in my life. I tried to beat the Gandalf AI game that was on here the other day using a version of the trolley problem. It was strangely exhilarating.
Re:Smol Developer by intelVISA on Wednesday May 17, 2023 @09:27AM (#35974950)
I'm quite excited for more emergent gameplay vs LLMs!
Re:Smol Developer by x-complexity on Wednesday May 17, 2023 @12:11AM (#35971157)
It's primarily an issue of overpoliteness: The ML model's training is increasingly populated with "No, don't do this", and as such, learns to just not do anything.

https://huggingface.co/ehartford

https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensore...

It's only when deliberate uncensor-ings are made that some form of usefulness can be clawed back.

Philosophically, it's amusing to apply this overcorrection back onto allegories for daily human life, wherein the tension between order & creativity are always in conflict.

If you're told from birth that everything you're doing is wrong, eventually you'll become creatively and intellectually stunted, increasingly relying on authority figures to tell you what's morally correct.

Re:Smol Developer by TeMPOraL on Wednesday May 17, 2023 @02:59AM (#35972087)
Stop expecting LLMs to react like adults - they're more like 4 year olds (3 year olds if it's anything other than GPT-4). They react much better to positive commands and examples than to negative ones.
Re:Smol Developer by gonzan on Wednesday May 17, 2023 @03:02AM (#35972103)
That’s already how I’m building new projects, I mostly only write/reorder UI code since it’s what LLMs struggle with the most.

I’m building a VS Code extension that makes this easier by having context on the code and building features on top of it with no copy-pasting required.

The extension is called Kamara: https://kamaraapp.com/ If you’re interested in trying it out for building an MVP of one of your ideas I’m happy to send over some free credits

Re:Smol Developer by biql on Wednesday May 17, 2023 @04:55AM (#35972766)
As someone who considered giving up on programming due to wrist pain from typing, this is my dream as well. I also prefer to work independently or in small teams, and the amount of things that could be tackled this way is surely increasing. There is no reason why programming shouldn't to be more about thinking and less about typing.
Re:Smol Developer by fbrncci on Wednesday May 17, 2023 @09:06PM (#35983094)
Have you ever done extensive stretching? I do Yoga (3-6hrs per week), and spend some 10-20 minutes stretching my wrists neck after work. If I don't, I am facing the same problem.