4nonverbal-alit

I had a colleague I really enjoyed talking to. Until all the AI hype and them getting into that bandwagon. Now whenever I ask something I get a huge markdown response with unaligned ascii table or being told to ask <llm name here> instead (with much enthusiasm). I am sure they are not doing it with bad intentions or ignoring me. That said I still can’t help but find it cold though. I would rather prefer if they just ghosted my messages

At my current team at a “bigcorp” I have noticed a similar pattern. We use aws not because it’s efficient in any way.

We use it because we don’t want to deal with slow procurement process. It kills all the momentum.

The proof is good enough though.

Even if the code was written by author, not bothering to remove co-signed-by part from the commit message (assuming author did indeed wrote it by himself) let alone not writing their own commit message is an indication of negligence to me

How are you planning to sell it given the market dominance of Excel? The people that would be most willing to pay for spreadsheets are also the people who are already paying for Excel.

Not trying to discourage you, I am curious as to see how you are planning to enter the market as that was something I couldn’t answer when considering working on spreadsheet tools of various kinds or even an excel alternative.

This is not an excuse to let people choose if they allow os downgrades or not. Like bootloader unlock option on android devices.

Also people find exploits on newer OS versions as well. Downgrading makes it easier but not downgrading doesn’t make the device unhackable.

Why everything has to be on the server? ok, Where are you going to store your client authentication tokens or decryption keys. A proper file system isolation is a key if you want a proper application sandboxing

> What % of Android users actually want this? Do they know or care?

Bold of you assuming they're doing for users. It's fear-mongering at its finest - using the threat of security to install more control that has little to no protection against the said threats.

Now you might say it's going to raise the bar for the scammers, but nobody is going to be spending time on writing scam or malware for a few bucks. When the reward is high, they can just pay out already verified developers to distribute their builds under their accounts, or just find a workaround (fake ids?) which could be still way cheaper than the potential revenue potential of a successful attack. It's just an inconvenience that didn't existed before.

This is just a policy directly targeting the legit developers distributing apps to work around some of the platform's limitations (ie. uncrappifying youtube). They were previously free to share the workarounds they've developed for themselves since it was just as easy as sharing your APK. Now with added threat of losing your developer account and probably being perma-banned from google, those devs are less likely to continue distributing their workarounds.

Grammarly even from the start was very distracting to me even as a someone using english as a second language to communicate. I have developed my own taste and way of articulating thoughts, but grammarly (and LLMs today) forced me to remove that layer of personality from my texts which I didn't wanted to let go. Sure I sounded less professional, but that was the image I wanted to project anyways.

Unrelated but surprising to me that I've found built-in grammar checking within JetBrains IDEs far more useful at catching grammar mistakes while not forcing me to rewrite entire sentences.

> ePaper displays are niche, and worse for most personal and business use-cases compared to LCD et al.

Hence we need more resources for R&D to figure out the shortcomings. LCD didn't pop into existence randomly either. It's not a guaranteed win, but neither AI has proven any realized gains in the majority of industries that gambled on adopting it.

Actually true. Thanks for correcting!

They don't have to reinvent electron. They shouldn't need to use a whole virtualized operating system to call their web API with a fancy UI.

Projects with much smaller budget than Atrophic has achieved much better x-plat UI without relying on electron [1]. There are more sensible options like Qt and whatnot for rendering UIs.

You can even engineer your app to have a single core with all the business logic as a single shared library. Then write UI wrappers using SwiftUI, GTK, and whatever microsoft feels like putting out as current UI library (I think currently it's WinUI2) consuming the core to do the interesting bits.

Heck there are people whom built gui toolkits from scratch to support their own needs [2].

[1] - https://musescore.org/en [2] - https://www.gpui.rs

Regarding notifications, both iOS and android doesn't support reading and responding to text messages. The feature works on android because of a workaround: apps create a global notification listener and they can also interact with notification - read UI contents and respond.

I know it's still better than not having a workaround at all like in iOS. But just pointing out that Google probably never meant to let others access notification mirroring.

For claude at least I have been getting more assumption clarification questions after adding some custom prompts. It is still making some assumptions but asking some questions makes me feel more in control of the progress.

In terms of the behavior, technically it doesn’t override, but instead think of it as a nudge. Both system prompt and your custom prompt participates in the attention process, so the output tokens get some influence from both. Not equally but to some varying degree and chance

Let me clear my cache after logging in twice to get the OOM fixed so I can finally login to show you what’s wrong with it over a teams call and hope it doesn’t logout and reload randomly during the call.

TUI may look good on the surface, but I’d really appreciate to see a good descriptive logs instead of a fancy progress bar

Are you planning on releasing the server as a standalone application? Or it will be source available client + proprietary server? I've checked Noor, which looks to have a nice UX and functionalities I'd like to see (chat and realtime voice channels) without gimmicks like threads inside chats, pretending to be forums. I am wondering why you've decided to start over again?

I find the whole idea of context window inefficient. The model that knows more than anyone could, can’t hold a memory of a codebase? I know it’s a limitation of the transformer design, but I find it quite disappointing that most of the investment is being spent on optimizing inefficient technologies rather than rethinking about the design.

That’s something LLMs are also presumably good at. At least I’m seeing more and more push to use LLMs at work for ambitious business requirements instead of learning about the problem we’ve been dealing with. Instead of knowing why you are doing what you’re doing, now people are just asking LLMs for specific answers and move on.

Sure some might use it to learn as well, but it’s not necessary and people just yolo the first answer claude gives to them.

Website doesn't have any info about the product. I don't know which features are there going to be. Screenshots would be cool as well to evaluate UX. Frankly the github readme is more useful than the website in that regard.

> Which probably means we are all going to start to be more like airline pilots:

Airline pilots are still employed because of regulations. The industry is heavily regulated and the regulations move very slowly because of its international cooperative nature. The regulations dictate how many crew members should be on board for each plane type and other various variables. All the airlines have to abide by the rules of the airspace they're flying over to keep flying.

The airlines on the other hand along with the technology producers (airbus for example) are pursuing to reduce number of heads in the cockpit. While their recent attempt to get rid of co-pilots in EASA land has failed [1], you can see the amount of pursuit and investment. The industry will continue to force through cost optimization as long as there's no barrier to prevent. The cases where automation has failed will be just a cost of the business, since the life of the deceased is no concern to the company's balance sheet.

Given the lack of regulation in the software, I suspect the industry will continue the cost optimization and eliminate humans in the loop, except in the regulated domains.

[1] - https://www.easa.europa.eu/en/research-projects/emco-sipo-ex... ; while this was not a direct push to get rid of all pilots, it's a stepping stone in that direction.

used to be. they're becoming microslop 2.0

From what I've seen, if you're depending on AWS, if something fails you too need someone 24x7 so that you can take action as well. Sometimes magic happens and systems recover after aws restarts their DNS, but usually the combination of event causes the application to get into an unrecoverable state that you need manual action. It doesn't always happen but you need someone to be there if it ever happens. Or bare minimum you need to evaluate if the underlying issue is really caused by AWS or something else has to be done on top of waiting for them to fix.

I am not sure if the replies are serious or sarcastic

All aws is selling a web gui on top of free software. You still have to know ins and outs of the software to manage it properly.

Heck their support is shit too. I have talked to them to figure out an issue on their own in house software, they couldn’t help. My colleague happened to know what was wrong and fixed the issue with a switch of a checkbox.

I used to have a middleware that replaced generic http error responses with http.cat pics. One time a VIP somehow got into a URL that returned http 400 response on the website and got mad.

I ended up getting a call to explain why the website is showing middle finger to our VIP customer.

That's the whole point. Websites that try to block scraping attempts will let google scrape without any hurdle because of google's ads and search network. This gives google some advantage over new players because as a new name brand you are hardly going to convince a website to allow scraping even if your product may actually be more advantageous to the website (for example assume you made a search engine that doesn't suck like google, and aggregates links instead of copying content from your website).

Proxies in comparison can allow new players to have some playing chance. That said I doubt any legitimate & ethical business would use proxies.

I wonder if these colors are a kind of a watermark that are hardcoded as system instructions. Almost all slopware made using claude have the same color palette. So much for a random token generator to be this consistent

I think author has a point when he didn’t needed all those extra features.

But then they did made a bad choice for paying for loom. They could have just learned (or used llm) to make a bash script to use ffmpeg for capturing screen to a file. Or OBS is a pretty good solution as well. And a ton others

JerBrains does something similar (after paying for a year I get perpetual license for the version released that year). I’m pretty happy and feel under control. I have been paying them for years now and in case they screw up I will stop my subscription and still can download and use old version. Sure I will be missing on some bug fixes but I have used the software for a year already, I can live with those annoyances. It’s not like the new version will be all bug free either.

Tailwind is just bootstrap with marketing budget