Benchmark is not designed for the red team testing. I don't even think it make sense to "fix" the issue the article is suggesting. Yes, you can break the running contest by driving a car. Does this mean we need to make running contest car-proof?
100% agree. it not only applies to the training time but also applies to the inference time. Domain specific context and skills will be the only moat for companies
Select to translate is almost a standard feature for translation software. Not sure if the situation gets better now, but back then the software was written, using clipboard as temporary storage is a very robust and maybe the only way to implement such feature.
Trivia: It's likely sending Ctrl+C and reading clipboard to get the selected text. No easy cross-platform API for this lol.
Also note that the software is very old and poorly maintained.
Some context for ppl who are not paranoid, it's a very old software and not very maintained since very long time ago. I'm pretty sure HTTPS was not common at the time. And the selection scanning a very common and wanted feature in many alternatives for windows, browsers, etc.
If there's anything we can learn from it - don't use obsolete software.
It's ads that makes the market efficient. Potential customers should know the corresponding producers so that the information assumption of a ideal market stands.
I don't think so. Ultimately there's not enough information in prompts to produce "correct" code. And any attempt to deliver more information will result in a worse programming language, or as it is now, more iterations.
Agree.Maybe users with sketch in their hand are more interested in using this tool. I'm not a designer but I suppose people using Blender/AutoCAD already know what material/style they want.
Every post that claimed using ChatGPT to achieve non-trivial tasks turned out to have non-trivial human intervention.
> (from the original article) In fact, I found it better to let ChatGPT generate a toy-ish version of the code first, then let it add things to it step-by-step. This resulted in much better output than, say, asking ChatGPT to generate production-quality code with all features in the first go. This also gave me a way to break down my requirements and feed them one at a time - as I was also acting as a code-reviewer for the generated output, and so this method was also easier for me to work with.
It takes a human who really knows the area to instruct ChatGPT and review the output, point out silly mistakes in the generated non-sense, and start next iteration. This kind of curated posts always cut off the most part of the conversations and the failed attempts, and then concatenate successful attempts with outputs of quality. Sure, it will be helpful as a super-IntelliSense. But not as helpful as the post suggested.
I've tried to do something like in the post, but I was quickly bored with waiting output, reviewing, all the iterations. One important aspect about programming is that reading code may not be easier than writing code. And in my case, it's more painful.