Lots of blaming LLMs but I think the root cause lies elsewhere, I’m not even sure whether dismissing it as “capitalism” or “profit motives” would do it justice, because in general it feels more like the world that we live in lacks humanity.

Even in a capitalist world, a company could take a stance and decide not to purposefully screw people over, but in the world that we live in instead they look for ways to better screw over people and extract more money from them. It doesn’t matter whether your customer support is handled by someone from India, a crappy telephone tree or some voice model, when the incentive is the same - to do the bare minimum for customer “support” (in practice, just getting you to fuck off). Same for handling insurance claims and “dynamic pricing” of things - it doesn’t matter whether it’s some proprietary algorithm or just an LLM making crap up when the goal is to screw you over.

Blaming “AI” for all of this would be barking up the wrong tree (without that tech they’d just find other ways), though one can definitely acknowledge that this technology provides another convenient scapegoat, same as how you can lay employees off and just say cause it’s because of AI when in actuality it’s just greed and wanting to make your books look better.

  Assisted-by: AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2]

At the same time, I feel bad for all the people that have to deal with low quality AI slop submissions, in any project out there.

The rules for projects that allow AI submissions might as well state: "You need to spend at least ~10 iterations of model X review agents and 10 USD of tokens on reviewing AI changes before they are allowed to be considered for inclusion."

(I realize that sounds insane, but in my experience iterated review even by the same Opus model can help catch bugs in the code, I feel like the next token prediction in of itself is quite error prone alone; in other words, even Opus "writes" code that it has bugs that its own review iterations catch)

I remember having this old Dell Latitude, where you could easily swap out the battery pack with a button/tab thing on the back, without having to open anything else up - I even got a spare bigger capacity battery, but it would work without one altogether when connected to the power brick.

I unironically think that all laptops should be built like that.

It's nice that it works for the author, though, and OpenRouter is pretty nice for trying out models or interacting with multiple ones through a unified platform!

They might not include anything but the Jira ticket number, if the environment is truly lacking.

I feel like there’s a bunch of factors for why it will never be the same for many folks, from the models and harnesses, to the domains and existing tests/tooling.

I feel bad for the people for whom it doesn’t work, but Claude Opus has written most of my code in 2026 so far. I had to build some tools around linting entire projects and most of my tokens are probably referencing existing stuff and parallel review iterations and tests, but it’s pretty nice and even seeing legacy code doesn’t make me want move to a farm and grow potatoes.

It might be counter productive to be like: "Oh, just do X!" which works for the person suggesting it, and then have to do "But have you tried Y?" when it doesn't for the other person, if it just keeps being a never ending string of what works for one person not working for another.

0 A.D. is like a free Age of Empires and is lovely to play!

I'd probably also put Luanti up there, and maybe OpenTTD (despite the niche UI).

I don't wholly disagree, but personally it's still the tool I use and it's sort of fine. Perhaps not entirely for the money that's behind it, as you said, but it could be worse.

The CLI experience is pretty okay, although the auth is kinda weird (e.g. when trying to connect to AWS Bedrock). There's a permission system and sandboxing, plan mode and TODOs, decent sub-agent support, instruction files and custom skills, tool calls and LSP support and all the other stuff you'd expect. At least no weird bugs like I had with OpenCode where trying to paste multi-line content inside of a Windows Terminal session lead to the tool closing and every next line getting pasted in an executed in the terminal one by one, that was weird, though I will admit that using Windows feels messed up quite often nowadays even without stuff like that.

The desktop app gives you chat and cowork and code, although it almost feels like Cowork is really close to what Code does (and for some reason Cowork didn't seem to support non-OS drives?). Either way, the desktop app helps me not juggle terminal sessions and keeps a nice history in the sidebar, has a pretty plan display, easy ways of choosing permissions and worktrees, although I will admit that it can be sluggish and for some actions there just aren't progress indicators which feels oddly broken.

I wonder what they spend most of their time working on and why the basics aren't better, though to Anthropic's credit about a month ago the desktop Code section was borderline unusable on Windows when switching between two long conversations, which now seems to take a few seconds (which is still a few seconds too long, but at least usable).

After having used MS Office for a while, I have to admit that LibreOffice just feels more pleasant to me, when I don't need exact MS compatibility - the UI is customizable, Calc doesn't mess up CSV files when I open them, Writer also has most of the features you need and exporting PDF files is nice and has none of that OneDrive bullshit with them almost trying to hide your local file system as some secondary target.

That said, in some hardware configurations LibreOffice has slow and laggy rendering (you have to mess around with rendering settings, hardware acceleration and Skia and so on), some features like bibliography have broken on me in odd ways, and Impress can be a bit slow for larger presentations. OnlyOffice feels like it has more polish in regards to how approachable the UI/UX might be to a MS user, but feature wise isn't that far off.

I personally wouldn't reach for MS Office unless I wanted it as a part of their overall groupware - mail, Teams, AD and a bunch of other integrated stuff (though aside from AD, most other things feel a bit jank, like the new Outlook or Teams in general when compared to Slack).

OnlyOffice also seems to have a lack of clarity in regards to the ownership of the org (https://news.ycombinator.com/item?id=47100599) but in general I think they're in the right here - you can't just ignore parts of a software license selectively because you feel like it. Oh and I liked their software when I did try it out, except LibreOffice seems like a slightly safer bet (though I'm also not as sensitive to the way its UI is).

I dread the flip side of this which is dealing with obtuse bullshit like trying to understand why Oracle ADF won’t render forms properly, or how to optimize some codebase with a lot of N+1 calls when there’s looming deadlines and the original devs never made it scalable, or needing to dig into undercommented legacy codebases or needing to work on 3-5 projects in parallel.

Agents iterating until those start working (at least cases that are testable) and taking some of the misery and dread away makes it so that I want to theatrically defenestrate myself less.

Not everyone has the circumstance to enjoy pleasant and mentally stimulating work that’s not a frustrating slog all the time - the projects that I actually like working on are the ones I pick for weekends, I can’t guarantee the same for the 9-5.

For example, my blog runs on Grav and I write articles in Markdown on my local PC (more convenient than admin UI for me) and even on the server it all remains file based - it’s reasonably simple, reasonably fast and still allows for dynamic behavior at render/cache time.

Compare that to the slop you get when you have a slow as fuck WP install with a crapload of plugins and the whole thing is brittle and slow and nobody has any idea how to fix it without breaking the current site. If people try applying it to every problem, that’s how you get bad attempts at building complex and bespoke ERP/CRM/e-commerce solutions in a stack that will never be easy or pleasant to work with in those domains.

But surely there is a middle ground - use CMSes where they make sense, reach for other stacks when you need a more generic web app (AI or not). Or heck, use the CMS headless for some parts of the overall thing. Actually, in that regard, I also kinda love Django Admin cause you get a lot out of the box.

Like an API key on a subscription that could be used for 3rd party tools would count 2x towards usage when compared to the same model when used through Claude Code.

Or it’d count the same towards weekly or 5 hour limits across all models BUT would have a separate API keys under subscriptions limit that’d be more grounded. A bit like how they already have a separate Sonnet usage counter.

That’d both allow them not to go broke and also not lose so much community goodwill AND give subscription users an alternative to paying for their enterprise-oriented (overpriced) tokens.

That said, it got its list of feeds from the repo that someone made which hasn't been updated in a few years, so even if new blog content gets pulled, the list of blogs doesn't change. Oh well, wasn't a super serious project.

That makes me feel even more strongly about throwing proprietary and predatory codecs in the trash and opting to use AV1 et al wherever possible, it's better anyways and surely close to a decade after coming out, we'd expect devices to support it well enough.

Now, whoever worked on Oracle DB or Oracle Forms, or Oracle ADF, now those are some products I hate for a variety of reasons!

An entirely new internal system with LLM code review, DB migration tracking, time tracking, standups and Teams integration.

A new system that trains neural nets to recognize crops based on Sentinel-2 satellite data (the neural net works okay, mowing and ploughing is harder with a mostly heuristic approach since I don't really have labels).

A new system to migrate somewhere between 1000-2000 forms between proprietary solutions where a team of people have spent a year with limited progress, whereas I'm generating the codegen tool that does most of the work, with the remainder being left up to AI.

A new project linting tool with Go + goja to allow writing rules for validating project stuff in ECMAScript, a bit like ESLint just stack agnostic and can be deployed as a 10 MB executable, to also control stuff like architecture and project conventions that the other tools aren't really geared towards.

Also wrote an OpenAI/Ollama/Claude proxy that allows using on-prem models running on another server through Ollama/llama.cpp and also using AWS Bedrock models when permissions are configured.

Also a bunch of Ansible configuration for stuff like a self-hosted Sentry instance, debugging that piece of shit would be so hard and annoying without something that I can throw logs at (because for some reason they think that having 70 containers running for what should amount to one piece of software is okay).

Also wrote a personal tool that lets me use VLM and Whisper and PySceneDetect and some other stuff to produce EDL so I can take a 3 hour long video and cut it down to 1 hour with LLMs using the transcripts/timestamps (aligned with words, so not too many awkward cuts) that I can then import into DaVinci Resolve for further editing.

Also migrated the apps I host from Contabo VPSes to Proxmox VMs (Hetzner dedicated server from the auction) and went from Docker Swarm + Portainer to pure Docker Compose, also moved from Drone CI to Woodpecker CI and also got rid of the old deprecated Bitnami container images.

Also migrated my homepage from an ancient Ruby and Rails version to more modern ones.

Also wrote a few scripts to replace YOURLS with just an Apache install, the config for which I can automatically append new shortened links to.

I don't even need worktrees or custom skills for most of this, just Claude Code and a subscription, since paying per token would make me go broke.