I was trying out an IDE plugin for local LLM integration, but it would just make totally insane edits instead of what I asked for.
It turned out that the LLM-runner's default setting for handling queries that were too long was to silently delete the middle of the query. So the LLM saw the beginning of my ask, and the tail end of the code context, and nothing else.
I've run Japanese windows software under Wine, and with no configuration it was a sea of crashy mojibake. With the right locale configured, it worked fine.
It's all in aid of some streetsweeper being able to add "contributor to X, Y, Z projects!" to their GitHub résumé. Before LLMs were a thing I also received worthless spelling-incorrection pull requests with the same aim.
Are spelling correction PRs not welcome? I'd never put it on a résumé but if I'm following a README and I see a typo, I'll generally open a quick PR to fix that. (no automated tools, not scanning for typos, just a human reading a README).
I think a true spelling correction would be welcome. But I think the kind BS attitude the GP is describing often leads to useless reformatting/language tweaks, because the goal isn't to make the repo better, it's to make a change for making a change's sake with as little effort as possible.
Kind of like how on the Salesforce support forums, there are a lot of incorrect answers from people who don't appear to have understood the question, but they all have "Please mark my answer as helpful" at the bottom. (And this started long before AI.) If there's an incentive to "contribute," even if it's something as small as being able to put "Salesforce support volunteer" on your LinkedIn page, and it's very easy to do so, you'll get a lot of low-effort (or worse) contributions.
I’ve always wondered how salesforce and Microsoft get such huge numbers of supporters doing that unpaid work for them. They’re often Indian sounding names so I suspect that one or more of the big consultancy or outsourcing companies uses it as a hiring signal.
A real improvement to the documentation or readme is welcome, even if it is only a minor improvement. I have put in small grammar PRs on some documentation myself.
On the flip side, I used to get a lot of spam PRs that made an arbitrary or net neutral change to our readme, presumably just to get "contributor" credit. That is not welcome or helpful to anyone.
Ah, you're right, I totally missed that! But tbh that makes less sense to me. If this was pre-LLM then this is suggesting that humans were opening pull requests that change correctly-spelled words to incorrectly-spelled words? Is that some weird attempt at steganography?
Nope, just a large number of people who don't know English. As an example in context, someone might run a spell check and decide "incorrection" is an error, removing the humor.
This means you should still have the email from legal@, right? In that case you can solve the mystery of how they managed to pass DMARC by sharing the headers from it.
This directive only apply if you are trading (aka making money) with the app. Why does Google force-collect all this information when you can opt to not be a trader (no in-app purchases, no ads, etc)?
Interestingly when I asked GPT-4o (at least that's what it said it was):
>According to the instructions, which UnicodeCIDFont fonts should be used when generating PDFs?
It replies:
>When generating PDFs using reportlab for East Asian languages, you must use specific UnicodeCIDFont fonts depending on the language. According to the instructions, use the following:
>Korean: HeiseiMin-W3 or HeiseiKakuGo-W5 or HYSMyeongJo-Medium
>Simplified Chinese: STSong-Light
>Traditional Chinese: MSung-Light
>These fonts must be registered using pdfmetrics.registerFont(UnicodeCIDFont(font_name)) and applied to all text elements in the PDF when outputting those languages.
This list also has the Japanese fonts merged with the Korean list.
