rapiz

IMHO it's better than those vibing thousands of lines and claim it's something ground breaking and production grade.

Dang I made the same thing the same day https://news.ycombinator.com/item?id=48374308

fyi https://github.com/multica-ai/multica

US seems to be learning from China very quick. Congrats.

The graphics looks nice. What's the difference from other AI towns thought?

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

Just for fun. I asked Claude to build an online rater using the rubrics https://yujqiao.github.io/bs-index/

And yes, that IS the expected behavior.

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.

what's the benefit of using cgdb while you can use gdb layout src?

Is this another metaphor in the game Superliminal?

For simple use cases, I found animate.css[1] very handy.

[1] https://animate.style/

We're talking about a product and you present a story.

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.

Do you have a presentable demo? LLM augmented by static code analysis sounds very interesting

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.

Sometimes it's really hard to say "damn many prompts" is better than writing on your own.

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.

llama 7b in full precision requires 28GB of GPU ram. I know little about AI. Can I estimate that a 770 model takes ~2.8GB? It means vast devices can run the model locally.

> who are good at leaning into the latest innovations,

maybe not true.

There are many threads where new products got comments of "useless" and then launched. HN users are smart, picky, and not representative for crowds.

It's actually chisel. But github marks it as scala because chisel is based on scala.

Other HDL based on scala includes SpinalHDL.

These two HDL are pretty welcomed because of opensource and usability. You can find lots of projects in them. Notably rocket-chip, which is also in chisel. https://github.com/chipsalliance/rocket-chip

They're around for a while but still young and some people are pushing for adoption.

This is part of the China's effort to have its own IC industry. The project is now owned by BOSC, Beijing Open Source Chip Research Instiutute[1]

[1] https://www.bosc.ac.cn/yjyjs

I found the main content generated, which are the campiagns, plain and too generic to be useful. And I doubt the effort needed to pull out a better result, even with better models. The article does provide some inspiration on what will the AI-enhanced workflow look like, but also shows the weakness. All results look like pretty generic and skeleton and further polishing from pros is needed. IMO, the future will more be like everyone do their job better with the help of AI, instead of that everyone do all the work with AI and no one is really needed.