It could be aggressively persistent without sounding like a psycho, too, no? I mean, I have no frame of reference, but I sort of assume that constant reminders would work as well as constant belittling reminders. Maybe I’m wrong.

Come to think of it, an application threatening, shaming, and guilt tripping you into coming back might not be the healthiest thing ever.

I see some problems here.

An LLM providing “an opinion” is not a thing, as far as current tech does. It’s just statistically right or wrong, and put that into word, which does not fit nicely with real use cases. Also, lots of tools already have autofix that can (on demand) handle many minor issues you mention, without any LLM. Assuming static analysis is already in place and decent tooling is used, this would not have to reach either a human or an AI agent or anything before getting fixed with little resources.

As anecdotal evidence, we regularly look into those tools on the job. Granted, we don’t have billions of lines of code to check, but so far it’s at best useless. Another anecdotal evidence is the recent outburst from the curl project (and other, following suite) getting a mountain of issues that are bogus.

I have no doubt that there is a place for human-sounding review and advice, alongside other more common uses like completion and documentation, but ultimately these systems are not able to think by design. The work still has to be done. And can’t go much beyond platitudes. You ask how common the horrible cases are, but that might not be the correct question. Horrific comments are easy to spot and filter out. Perfectly decent looking “minor fixes” that are well worded, follow guidelines, and pass all checks, while introducing an off by one error or suddenly decides to swap two parameters that happens to be compatible and make sense in context are the issue. And those, even if rare (empirically I’d say they are not that rare for now) are so much harder to spot without full human analysis, are a real threat.

Yet another anecdotal… yes, that’s a lot. Given the current hype, I can only base my findings on personal experience, mostly. I use AI-based code completion, assuming it’s short enough to check at a glance, and the context is small enough that it can’t make mistakes. At most two-three lines at time. Even in this context, while checking that the generated code matches what I was going to write, I’ve seen a handful of mistakes slip through over a few months. It makes me dread what could get through a PR system, where the codebase is not necessarily fresh in the mind of the reviewer.

This is not to say that none of that is useful, but if it were to be, it would require extremely high level of trust, far higher than current human intervention (which is also not great and source of mistakes, I’m very aware of that) to be. The goal should not be to emulate human mistakes, but to make something better.

Please. I had a cassette with built-in storage, that could play in a cassette deck player AND had an headset jack plugged in for music on the go.

The more Ukraine do that, the less everyone else have to do it. Good.

And what if there’s no photograph of myself online?

He’s jealous?

I’m not sure… as my current washing machine don’t have one. It’s a top-loader. I do see washing machines with a round door, though. Maybe the difference is that the whole door is the glass part, so there’s no seal to make with the rest of the “door” part, but that’s not satisfying.

I’d be curious to ear from an expert about this.

I’m self-hosting my mails; no need for another third party that will decide whatever whenever. The major difficulty is the decades of things that are reliant on the old one.

And I just said that google works fine for search, despite people claiming it’s on the decline, broken, unusable, etc. That’s not to move toward qwant, who are no less shady, burn money (sometimes coming from public money…), and despite wonderful claim of an autonomous index, completely stop working when Bing is down. As far as recommendations for search engine goes, google (and Bing for that matter) are far less disingenuous. All usable search engines these days are backed by the big ones anyway. Something like https://openwebsearch.eu/ would be a better alternative, assuming it follows on its promises.

The two thing I use most, by far, from Google, is gmail and basic search.

Gmail, I’m looking to move away from it now, but I currently have every little addition to it disabled. Basic inbox and tags, no automatic filtering, no categories, no nothing.

Search, my browser is set to open the “web” tab with the query, no transformation, no summary, no “for you”, no AI garbage, no “we thought you wanted video so there’s only video in the replies”. It still works fine.

Basically, none of what they added for years… maybe decade at this point, had held a glimmer of interest from me. It feels like this trend will continue. I just want something very basic that works.

Knowing how “fun” it is to make a truly watertight window, even with low pressure, matching both cold and hot and detergent and whatever’s flying in there, I’m glad there isn’t a glass pane to view into the dishwasher.

Also, I’m usually doing things that are not reliant on seeing what’s happening in a dishwasher when it is running, so the cost effectiveness would not be great there.

Oh, so it’d be ok to get movies, pictures, books, etc. without asking the right owners for us too? GREAT.

The dickvid potential is there.

I’m mainly interested in Japanese, so I’m currently looking at https://www.renshuu.org/ . In addition to just throwing random stuff at you, it gots some more in-depth training, explanations of stuff (something that never happened in duolingo), additional hints for alphabets including some mnemonics, and years of dedicated experience in the language. I can’t tell how it would feel long term, but so far even having some basic explanations is a great improvement.

People are unfair with this “CEO”. Its statement helped me move on from duolingo, which has seen significant decline in quality while never going beyond “a moderately bad way to start learning”, toward better, more developed, more cared for, cheaper, solutions.

So, thanks for that.

On the phone (well, teams call): “Just open the windows app…”

It could be nice. People complaining about it being web based are missing the point of such tools.

I’ll grant you vertical tabs. Unfortunately, the new focus of Mozilla is AI everywhere and advertisement, so I’m mildly concerned.

Shutting down two things that had no business being built in their browser, to replace them with more stuff that have no business being built in their browser.

Mozilla really embraced the “corporation must corporate” motto.