dkdcio

pretty much…they have their own system prompts, you can customize the model, the tools they use, etc.

CC has built in subagents (including at least one not listed) that work very well: https://code.claude.com/docs/en/sub-agents#built-in-subagent...

this was not the case in the past, I swore off subagents, but they got good at some point

late Feb. 2025: https://www.anthropic.com/news/claude-3-7-sonnet

it’s also used in the Explore agent and for other things too

it seems to have changed a ton in recent versions too — I would love more details on what exactly

I find it doing what I in the past had to interrupt and tell it to do fairly frequently now

there is the Gemini CLI, but I am aware of people doing exactly what you’re describing (which I find ridiculous but if it works it works I guess). some people have CLI tools for turning their entire repo into one big Markdown file or similar to copy over

sure, it’s all fake data, nothing’s real, everyone hates these very well-used and well-rated products. ya got me

hundreds of thousands and millions of fake reviews. it’s all manipulation!

looks like about 400,000 people for Onedrive rating 5 stars

looks like millions for my banking app (Chase) rating 5 stars

do you really not understand why people might do things different from you?

maybe I’m just getting old, but I’m really tired of these [super popular product tons of people use but EVERYONE hates it] posts and comments. just quickly checking the Apple App Store, the Onedrive app has 4.7 stars

does everyone hate it?

yes, mentioned in https://turso.tech/blog/upcoming-changes-to-the-turso-platfo...

previous discussion a few months ago: https://news.ycombinator.com/item?id=45584464

I believe this article is from a few years ago

vendor lockin + slow network calls (+ GitHub is down sometimes). if you want to search over hundreds of issues, `gh search` isn’t bad but you can do a lot better with a filesystem or embedded database

that said for work I use GitHub and have CC make use of the gh CLI, works great. but I have wanted some sqlite/duckdb tracker you could just commit, maybe with back and forth between markdown files. also GH projects are pretty slow/clunky

this is my constant take with “AI”…if you were lazy before, you’re lazy now. if you were producing slop before, you’re producing slop now

I think this just widens the gap between people who give a shit and those who don’t

the big thing that changes are the economics of laziness and slop

> AI is inherently unreliable and untrustworthy

big statement that doesn’t hold up under any technical scrutiny. “AI” —- neural networks —- are used reliably in production all over the place. signals filtering/analysis, anomaly detection, background blurring, medical devices, and more

assuming you mean LLMs, this still doesn’t hold up. it depends on the system around it. naively asking ChatGPT to construct a legal brief is stupid use of the tool. constructing a system that can reliably query over and point you to relevant data from known databases is not

meh…I consider an open source license distinct from an open source project. obviously legal contracts can define their own static terms; language is dynamic

you could just do that with Rust, right? you’re just saying cargo makes it too easy not to

I’m very tempted to go this direction myself with Rust, vendoring in and “maintaining” (using Claude Code to maintain) dependencies. or writing subsets of the crates I need myself and using those. the sprawl with Rust dependencies is concerning

FWIW I would absolutely say “MIT is the default license”. I also understand copyleft and personally would still choose MIT in general

I also like Rust, but the above would be true before I started using Rust (I agree it’s not a programming language thing)

it’s not made up (well all language is made up but I digress), you’re just being flagrantly ignorant of the terms you’re using and their history. you can easily go read up on open source vs source available and the history of the terms/licenses

it’s also fine by me if you want to have your own definition; see other comments, I don’t personally 100% agree with OSI’s definition myself

> That isn't even part of the OSI's definition, so what are you basing this on?

edited my comment —- that is my personal belief/definition

I did mention there’s disagreement —- I haven’t read up on the history and whatnot myself in a while. will have to do some re-reading :)

argh I will re-edit my comment…sorta covered by the “disagreement” bit, and I disagree on this point (it’s not open to me if you don’t openly accept contributions), but you are right

that would be “source available” software, and it’s not a random initiative

there is disagreement on exactly what “open source” means, but generally clear boundaries between open source and source available software in licensing and spirit of the given project. e.g. MIT and Apache 2.0 are open source, BSL is source available.

edit: PERSONALLY, I think if you don’t welcome outside contributions, it isn’t open source; see others’ responses for disagreement on this (it’s not a part of the standard definition)

useful and timely for me…I’ve been thinking about writing a Zola preprocessor (or fork) to do a few things, including optional execution of Python code within Markdown a la Quarto. maybe I’ll start with a mdBook plugin and go from there

sure…what’s the motivation? is this seriously that difficult of a question to answer? this “solution” was put in place for a reason, what’s the reason? does nobody actually know?

yeah but why?

I’ve seen this a few times now, what’s the context/background on why this is done?

my most interesting reading this year has been Stafford Beer (Brain Of The Firm, Heart Of The Enterprise). fascinating person and books

I’ve otherwise been largely re-reading books I haven’t read in a decade or so

I do see the point a bit? and like a reasonable comment to that effect sure, I probably don’t respond and take it into account going forward

but accusing me of being deficient in English or some AI system is…odd…

especially while doing (the opposite of) the exact thing they’re complaining about. upvote/downvote and move on. I do tend to regret commenting on here myself FWIW because of interactions like this

my point was more concise and general (should I have just commented instead of replying?), sorry you’re so offended and not sure why you felt the need to write this (you can downvote)

accusing people of being AI is very low-effort bot behavior btw

“it depends” (there’re plenty of laws and case law on this topic)

I think the case here is fairly straightforward

does a gun on its own kill people?

my understanding, and correct me if I’m wrong, is a human is always involved. even if you build an autonomous killing robot, you built it, you’re responsible

typically this logic is used to justify the regulation of firearms —- are you proposing the regulation of neural networks? if so, how?

no computer system just does stuff on its own. a human (or collection of them) built and maintains the system, they are responsible for it

neural networks are just a tool, used poorly (as in this case) or well