"I saw her duck" - how much would you be willing to bet on the intended meaning of this sentence?
English isn't a good programming language if you want to trust that the output will be as you want it to be. High level code has no room for ambiguity - that's why we use it. It's a concise, very explicit language to tell the compiler exactly what to do.
Dealing with an LLM is a fundamentally different thing. The reason it's able to speed us up is because it makes assumptions for us and reads between the lines. The only world where we trust the output is one where it can literally read our minds. That's not coming any time soon
I think an isolated and ambiguous sentence like the one you provided with zero surrounding context is perhaps a bad example. English can be very ambiguous. It is also possible to write unambiguous English, as far as deciphering intention is concerned. I think LLMs have shown us just how far English can go as a medium to get quite good results. And as others mention, there are other tools, like compiled programming languages and static analysis tools and unit tests, that can do more of the heavy lifting on our behalf.
I thought about doing that with Todoist.. and then just decided I'd rather pay the $4-5/mo or whatever to not have to use unpolished apps and sync server
I keep paying for Obsidian for the same reason. It's central to the way I work and has an ecosystem of stuff-that-understands-Obsidian making it useful.
But, for example, I did replace IRCCloud with my own custom setup. Been daily driving it for ... three months now? Took me two to three evenings to get an MVP and 3 months of iterating while using it to get it Just The Way I Like It.
I was also a paying customer of Hazel[0] for two major versions, I didn't use the majority of features so I made my own that does the things from Hazel I needed plus a few extra things that nobody else is going to care about but make my life easier.
All of these are just for me, they are open source with a permissive license, but I have zero intention of making a "community" for any of them or trying to make them into commercial offerings.
They do what I want and if someone likes them as-is, they're free to use them. If they need something else - that's why we can fork repositories =)
That's funny, I felt the exact opposite and found it fun to research how to make things sync properly and architect the solution for my LLM to then build. Currently I'm using Loro for the syncing.
> exactly how the unit and integration tests are made
There should be enough detail in the spec that it's pretty obvious. And unlike - many - human devs, agents don't shy away from writing tests. Add a coverage guardrail and tell them to use red/green TDD and you're already a good way there. The main thing is to ensure shared understanding, so they also know business expectations and write appropriate tests. And... nothing here is really specific to an agent, as a human dev also needs sufficient guidance (tailored to their experience level).
This is just pure vibe coding and trying to convince yourself it's quality work. AI can't be trusted to go from an English written spec to tests
Here[0] we have benchmarks for AI writing tests for code that already has the correct behavior. Best case scenario is that they're at 67% with Fable, and that's with the highest quality specification we could possibly have (code). English is far more ambiguous
Maybe you don't trust them to, but they can go from spec to tests; I've made them (even if it initially took extra prompting and scrutiny). And ultimately tests are just a proxy to checking that X works, written by devs for devs; actually trying X is something to be done by QA and/or project/product manager before shipping.
Black-box e2e testing isn't suitable, or practical, for a lot of applications. Unit and integration tests generally require you to understand the code you want tests for, to know what to actually assert
Makes a lot of sense to me. If you're young and things aren't going so well then at least you can have hope that you'll be able to turn it around. You have time on your side. That all goes away when you start to get to middle age. You're locked in by your earlier choices.
Now I'm here staring at AI with the reality that if it makes my skills irrelevant I'll have no fallback, and I'll be at an age where reskilling is extremely hard and I'm still nowhere close to retiring.
> Reviewing code is still way faster than writing code.
Writing code results in a much better understanding of the code than reviewing it
In fact I would say that in large complex codebases, in order to develop the same understanding of what the code is doing might actually take longer than writing it from scratch would have
That's fine with me actually. I recently had an appointment where the doctor asked if he could use AI notes, I said yes, and meeting was so much nicer than before when the doctor is typing half the time. We can have a real conversation, nothing I say is missed, and later on the doctor can use AI to cross reference results or whatever else with our past discussions. That's win-win all around.
The cases I've heard of where AI doctor notes went badly, is in recording numbers that another doctor relies upon. If it's just a casual conversation, it's probably okay. If it's about cancer treatments, maybe ask for manual notes.
I've had doctors write horribly-incorrect notes in my digital chart after appointments, so please don't think I'm trying to be a Luddite.
Register your own domain and use that for your email, and you'll no longer be held hostage by Google. Takes almost no effort and will cost you a few dollars a month.
While I agree with your suggestion (that's what I've doing for years), I'm not sure the "almost not effort" point is helpful or realistic when it comes to a huge majority of users.
Apart from people who are knowledgeable or at least curious enough to search for alternative options, I suspect many people don't even know what a domain is or that they could register one for them to use. The jump from "why pay for email if Gmail/Outlook is free?" to "register a personal domain and use it for your emails" is too big.
I don't have the ideal solution but what I've suggested to friends and relatives is they should consider paying for their personal email accounts. Most of them don't care but some do and, as a result, at least try to understand what they want or need and are willing to pay for.
Even if your time is worth $0, you're paying far more than a few dollars a month to have a google account. Price discrimination from third party vendors is probably running you 5-10% of your credit card bill every month.
Democracy is the style of ruling where majority's ignorance dominates over the vulnerable. You will be eventually forced to use internet and forced to use the way your government wants you to use it.
Yeah, fair point. They're certainly trying to push it in that direction but so far there are still alternatives. I've seen age verification get a hell of a lot of pushback so that's encouraging.
I can set up all of the personal services I want. The average person does not want to do that. They do not have the skills, and it does not add value for them to do so 99.999999% of the time.
The tools and offerings we're given are built to fulfill the needs of the greatest number of people. For better or worse, those people are not people who want to mess with the infrastructure around their email.
Because when most people use the one email host, they neglect all other users. Even my yahoo email is regarded as second grade citizen now. A hospital straight told me they refuse all yahoo addresses.
I mean, that's certainly retarded, but most businesses aren't that stupid in how they choose to run things. I've never, not even once, run into a business who cares what your email is. They will use any address you want, whether you have a known provider, or self host.
I know this ^ seems unreasonable, but I know you’re right.
Mostly because of conditioning: it’s been 25 years now that free webmail is the way Gen-X, Y, Z, and future generations do email. Boomers and the older Gen-Xers may still be hanging onto an ISP address, if they haven’t moved too much since the 1990s.
After all that, plus with their email addresses being the opposite of portable, there is no limit to how much crap people will take, when the alternative is learning a little bit about domain registration and DNS, and paying $60 a year for Fastmail or whatever. Email, they believe, is supposed to be free as in beer.
Sad but true. Also, confession: I used to use first name @ full name . com and got tired of the confused looks and typos when I had to give it out, so now I use a six-character Gmail with numbers so that it’s just like people expect.
But what do you actually use as the email host? If you just set up your own mail server, you're almost certainly going to have everything you send go straight to spam.
You still need to register with someone like google, or Proton, etc.
> you're almost certainly going to have everything you send go straight to spam.
I run my own email server on DO, nothing I send goes to spam. (I normally follow up on nearly all emails in case you're assuming some flavors of sample bias.)
Believe it or not, email service providers actually exist.
Rollernet.us is a good one. They have excellent deliverability, reasonable prices, and everything you could want related to email.
They have a few minor other services, like DNS management, but they are not a cloud compute provider.
Another option is to use a cloud compute provider like AWS. You don't need to run the VM yourself to use SES for email messages. The hard part is the webmail access: you have to choose between a poor interface (an S3 bucket) or running a managed VM to host something like Roundcube.
Yeah, but you're not beholden to them. There are 100 different hosts you can use if you own your own domain. If a host changes in a way you don't like, just move your domain elsewhere. If you're using Gmail, you're stuck with Google. Being independent of any one host is the important part to me.
Personally I have my own mail server and use smtp2go for sending which handles the deliverability issue. I'm not sure it's worth it going this way but I found it fun and its been 0 maintenance
I have done as OP suggested and the main benefit is that I can move my email elsewhere.
For now my email is with Apple, since they offers email hosting as part of the icloud+ (or whatever its called). If they decide to die/enshittify, then I can move to another host without having to change any contacts.
One the other hand, since I did use my bare gmail for some years, I am still stuck with it, in case I have some service that depends on it.
I switched from self-hosting to Apple’s servers a year or so ago and it’s been splendid. No issues sending to other servers, decent spam filtering, and no nickel-and-dining for having more than one domain, or more than one user, or adding email aliases. If you’re already paying for iCloud+, there’s no extra charge for it.
I don’t wanna sound like a salesman. It’s just that it’s been a surprising good experience for my family, especially for the price tag of $0. And if it ever does start to suck, I can point our domains at a different server.
Not at all. As a KDE Plasma user, I love and donate to open source.
I'm arguing that the current climate of "vibe code a startup a day" is unsustainable, terrible, and should NOT be the thing people strive for. Instead of appeasing VC firms, that energy can be better spent on passion projects or contributing to other open-source projects like KDE / Linux / GrapheneOS / etc..
They're different goals though. Someone selling software is doing it to put a roof over their heads and money in their retirement accounts. If you straight up replace that with working on passion projects and giving them away you get.. homeless people.
I'm not sure the starving artist is an ideal to strive for, either. Surely there's a middle ground?
JetBrains' lifetime "subscription" which gets locked at the version you paid for seems fair to me
I don't see why you can't work on something you're passionate about and make money from it. For those of us not retired, the money is essential to make it sustainable.
English isn't a good programming language if you want to trust that the output will be as you want it to be. High level code has no room for ambiguity - that's why we use it. It's a concise, very explicit language to tell the compiler exactly what to do.
Dealing with an LLM is a fundamentally different thing. The reason it's able to speed us up is because it makes assumptions for us and reads between the lines. The only world where we trust the output is one where it can literally read our minds. That's not coming any time soon