I have a tampermonkey script that downloads any files that the prompt returns... a python script locally to watch for file changes and extract the contents to the projects working directory and it can work both ways, if I edit my prompts.txt local file, it passes that data to openai’s currently opened chat and renames the file and creates a new empty prompt.txt
You just prompt it directly or with a file, and it applies the changes to your file system. There's also a templating system that allows you to reference other files from your prompt file if you want to have a shared prompt file that contains project conventions etc.
The vscode extension builds are including your full source code and node_modules directory which makes it 21 mb. You can reduce the size (and potentially keep your code less easily reversable) by excluding those from the final package
Seems like a cool thing, I'm definitely interested as my work provides us with an API key to use. However I can't find anywhere that lists all the functionality offered. Maybe I'm missing something? It might be premature to launch the app before listing what it does.
You can also use the ifdef-loader module to have code that is conditionally included in the output build, allowing you to have debug code not make it into prod builds. The `rc-dev-` license keys being a good example of that.
This is kind of interesting because the primary point of having eng/DS for data analysis in my mind is them being domain experts on the data. If you can perform adhoc analysis without any further domain knowledge, how much value would those hires have brought even disregarding ChatGPT?
In 2003, the best AI could do was the MS Word grammar check giving unnecessary false positives about sentence fragments and Clippy asking if you wanted help writing $template[n]. 20 years from now, I would not be surprised if the job title "programmer" (etc.) goes the same way as the job title "computer".
As a data scientist, I’m happy that most data continues to be so terribly formatted and inconsistent as to break and confuse AI. But for how long that’s true, who knows!
Unfortunately, there are still many ways to “fix” things that have a lot of trade-offs or downstream consequences for analysis. For most basic cleaning tasks, LLMs are also still way too slow.
So basically, you are happy to use AI because it benefits you and you are also happy training it to replace other people since you will not be the one replaced.
We don't have to be happy about it, but we can't stop this new technology any more than we could stop the invention of the steam engine or the printing press. Technology always displaces jobs; that's largely the point of inventing it. By reducing the human labour required to produce something, it allows us to produce more using fewer resources and frees up the labour to go work on something else. This is why we went from 96% of people needing to work in agriculture to 4%.
I might lose my job over this at some point in the future, so yeah, I'm worried about my personal well-being. But you can't put the genie back in the bottle and avoiding use of ChatGPT today isn't going to help.
I disagree. Not using ChatGPT can be the start of a coalition of people that do not use it. I already have two principles: (1) to not use generative AI, LLMs and other AI tooks, and (2) to give preference to people and businesses who do the same. It's simple. If I find that websites use ChatGPT to help generate their content, I stop visiting and supporting them. If I find businesses using AI, I stop supporting them. I already got one other self-sustaining business to at least pubicly declare not to use generative AI and in my personal business, I do so as well.
If such a coalition grows large enough, then AI tools can be extinguished or at least made sufficiently prohibitively expensive so that they are strangled.
It won't. People have never defeated a useful new technology that destroys jobs. People widely like using these tools. You'd need to ban their use worldwide. If the US bans AI, China and other countries will become dominant in AI. Assuming AI continues to improve, there's an extreme advantage for any country that has it.
Holy smokes the code interpreter functionality has been a complete game changer for my workflow.