Hacker News: anonzzzies

New comment by anonzzzies in "What it feels like to work with Mythos"

anonzzzies — Wed, 10 Jun 2026 13:17:41 +0000

Been working on my pet project today with Fable; it seems pretty solid but not too far removed from 4.8; same hallucinating, same type of bugs, same focus in large projects on just doing what you ask and just ignoring whatever that may touch/break/influence. Running tests in the beginning but when fuller context, just 'will run later' and never doing it in the end unless you tell it to (using some assorted swear words). I will keep using it but it's incremental as far as i'm seeing, not the OMG OMG OMG Mythos is here!

New comment by anonzzzies in "Cleaning up after AI rockstar developers"

anonzzzies — Tue, 09 Jun 2026 16:19:56 +0000

yep. exactly that

New comment by anonzzzies in "Cleaning up after AI rockstar developers"

anonzzzies — Tue, 09 Jun 2026 16:13:41 +0000

That is also fixing… The client does not care about technical things so indeed rewrite is usually the best way even if we do not tell we did (people are proud of what they made so they do not want to just get told it was thrown away).

New comment by anonzzzies in "Cleaning up after AI rockstar developers"

anonzzzies — Tue, 09 Jun 2026 16:12:05 +0000

As some already said; the real win is into having a business driven prototype; the work to gather those specs is already done and, generally, very costly when done in the traditional way. So from scratch if having to do all of it is more expensive; technical from scratch far less so.

New comment by anonzzzies in "Cleaning up after AI rockstar developers"

anonzzzies — Tue, 09 Jun 2026 16:09:38 +0000

We have be in business for 30+ years; clients find us.

New comment by anonzzzies in "Cleaning up after AI rockstar developers"

anonzzzies — Tue, 09 Jun 2026 16:06:49 +0000

Well, this is not the first project that has this. Depending what llm/harness and how it is yielded, this happens, a lot. How often have you had Opus 4.x note; ‘485 failed tests, but those are not related to my changes so I will not dive into them’? You believe someone who does not know about tests or code or linting or compilers will push back on that? I know that’s not happening for a fact.

New comment by anonzzzies in "Cleaning up after AI rockstar developers"

anonzzzies — Tue, 09 Jun 2026 13:14:42 +0000

I like fixing code made by AIs and others (outsourcing code is similar as someone else said already). Last week we found out some client tried to vibe some departmental tool; the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. Now we have to fix it: its basically free 10k-50k euros over and over again for this type of work. Very easy if you know what you are doing; impossible if you don't. Keep m coming.

New comment by anonzzzies in "The EU Open Source Strategy"

anonzzzies — Mon, 08 Jun 2026 10:18:40 +0000

There is money but it's all vague and hard to get and usually with tax breaks instead of just money. I would opensource everything we built, but I have to eat something so it'll be when I die and/or the company is sold and/or we earned enough to make everyone eat during their life (with some reasonable amounts that assume hyper inflation won't happen) (it is contractually arranged). Many EU gov institutions use our software and would LOVE for us to open source it - they would immediately stop paying.

New comment by anonzzzies in "Is This the Dawn of the Tokenpocalypse?"

anonzzzies — Mon, 08 Jun 2026 07:53:48 +0000

But that will tank literally all AI companies immediately as, sure, some will pay it, but by far most won't. Anthropic will be gone in 1 day, so will OpenAI.

New comment by anonzzzies in "Show HN: NoSuggest – Watch YouTube without the recommendation algorithm"

anonzzzies — Mon, 08 Jun 2026 07:49:37 +0000

I find youtube, but also netflix, prime, Spotify etc some of the weirdest things in tech; for me they all are complete shite. How is it possible? I vote up and down stuff; how can I vote down sappy drama and then get recommended the same drama the next refresh? How can it recommend movies, shows, clips I JUST watched? How does any of this not lead to frustration? I was listening to a generated playlist at a small dinner party and it put in music I literally down voted and hate. There are 1000s of people working at these companies ; I don't know why more than 1 dev and Claude code are working at netflix in IT as it's just complete garbage. Maybe someone can explain it here.

New comment by anonzzzies in "Back end is full of hidden workflows"

anonzzzies — Mon, 08 Jun 2026 07:13:59 +0000

Why is 'workflow' something special? Most/all code is workflows; there are many 70s programming books that show all code as workflow diagrams. How is it hidden? Or did we, as often is the case, change the definition? Not according to Google/Gemini anyway.

New comment by anonzzzies in "Meta confirms 1000s of Instagram accounts were hacked by abusing its AI chatbot"

anonzzzies — Sun, 07 Jun 2026 08:31:18 +0000

Is there a tl;dr? are these people getting their accounts back?

New comment by anonzzzies in "Ten Years of Franz"

anonzzzies — Sat, 06 Jun 2026 07:30:52 +0000

I thought it was the Lisp Franz and wondered what I missed as that's much, much older.

Anyway; I gave this a try (on Mac) and was not impressed; coming in at 1.44GB, immediately very slow and my battery almost immediately flagging it as the app using the most energy, I went through the setup; after the setup was done I was left with a blue empty screen and nothing to click on. So I killed it and started again; that opened my workspace without any messengers added (I added 3 during setup). So I added whatsapp and that resulted in a half screen whatsapp on top of that darkblue again with no options other then to kill the app. After restart, whatsapp was there and working, albeit very slow (franz still consuming most energy); whatsapp is notably slower inside Franz than the separate one (they are both electron I think?).

Not Franz their fault, but I added Slack and literally spent 15 minutes solving Recaptcha's of buses over 50 of them, before it let me in... Wtf. I think Slack sucks at the best of times but this was very terrible.

Anyway; Not for me, but nice work sticking it out 10 years!

New comment by anonzzzies in "The Speed of Prototyping in the Age of AI"

anonzzzies — Sun, 31 May 2026 17:33:54 +0000

Drupal and WP etc all have plugins to switch stuff on in minutes, however, customising and making it as your client wants would take a lot of time. WP shops we work with for clients (we need to integrate some times) take weeks to get some plugin to do what they want by adding tags and config options.

New comment by anonzzzies in "The Speed of Prototyping in the Age of AI"

anonzzzies — Sun, 31 May 2026 17:31:25 +0000

> But is it really any faster than using an already existing code generator/scaffolding tool?

Yes, very much so. Our team was fast with those tools and created many of our own before this LLM AI (we used other AIs though to go faster), however it still took weeks to months from idea to launch; the same complexity now takes days, including everything. We already had rigorous processes and those really help now moving at speed. No way anyone can beat this except better AI.

New comment by anonzzzies in "The user is visibly frustrated"

anonzzzies — Tue, 26 May 2026 07:08:58 +0000

I notice the same. Like you I am not even sure if it really helps, however, every day I find occasions where I see Opus will never do it correctly even though I calmly explain; swearing then suddenly fixes it. I had some issue yesterday where opus kept blaming the api for not sending some field while I knew it was there ; I showed it json, logs etc but it kept repeating that there must have been a glitch; frustration built, I called it all kinds of things in one sentence and the next solution was the right one. This after 10 similar misguesses. It was one of those increasingly rare cases where I should have just done it myself, but I can never know going in how stubborn it will be in continue blaming the (obviously) wrong thing. The around 11 prompts to get to the answer were in a /clear opus 4.7 context (1m) on xhigh.

New comment by anonzzzies in "Why Do We Sleep Under Blankets, Even on the Hottest Nights? (2017)"

anonzzzies — Mon, 25 May 2026 09:27:17 +0000

It is the only reason. I asked my wife one time why she sleeps under blankets when it's boiling hot (I do not); she said because there might be 'things in the night' so I asked if she thought these sheets will protect her; nope, but otherwise she doesn't sleep.

New comment by anonzzzies in "I love my Bluetooth keyboard"

anonzzzies — Mon, 25 May 2026 07:06:13 +0000

The MS Universal Foldable KB is the best I tried. Indestructible and still quite easy to get.

New comment by anonzzzies in "LAN-LOK: The Antarctic DOS Sabotage Game Lost for 34 Years"

anonzzzies — Mon, 25 May 2026 06:22:40 +0000

Agreed, and it was repetitive indeed, to the point of annoyance; for some strange reason there is this though:

> so Mark and Shane may have been Palmer winter-over reserchers.

New comment by anonzzzies in "Scammers are abusing an internal Microsoft account to send spam links"

anonzzzies — Sun, 24 May 2026 12:13:36 +0000

Or, which has worked great for me; just never answer the phone. If people need something they will email or chat. If not then it is not going to be important.