@MangoCats@feddit.it
member since 5 Feb 2025 19:10
comments
- on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 2d ago
-
on Thanks FedEx, This is Why we Keep Getting Phished in c/technology@lemmy.world · 3d ago
I don’t know if this ties in well or not, but many times over the years I have talked with otherwise reasonable people who had already, or were about to, make really stupid decisions, and I called them out as such: “this is a really stupid thing to do” - to which they all responded “are you calling me stupid?” - I never succumbed to the temptation of “well, if the shoe fits…” - truth, and what I said, was: “about this particular decision, yes.” They always had some particular goal in mind which overrode all other considerations in their mind, and they couldn’t step back and see how their goal wasn’t 100% all important overruling all other considerations.
-
on Thanks FedEx, This is Why we Keep Getting Phished in c/technology@lemmy.world · 3d ago
fascism genreally is stupid
Strange thing about sociology / political games: stupid works.
In the runup to world war II both the UK and USA were studying Fascism as a potential way of “getting more” from their populations to compete better in the coming conflicts…
-
on Thanks FedEx, This is Why we Keep Getting Phished in c/technology@lemmy.world · 4d ago
Couldn’t be much worse than what we have today in the real world…
-
on Thanks FedEx, This is Why we Keep Getting Phished in c/technology@lemmy.world · 4d ago
they made me pay import fee on the value of the listed items instead of on the price I payed (there was a 40% discount).
All this discount / special deal complexity needs to stop. Now the tax-men are scamming us declaring everything to be taxable at the retail rates when nobody pays the retail rates.
One price, for everybody, all the time. One tax rate, for everything, all the time.
-
on Thanks FedEx, This is Why we Keep Getting Phished in c/technology@lemmy.world · 4d ago
The solution is: if it looks scammy, get on a different device altogether and use your normal login to the institution to access the issue through the normal channels instead of their “convenient link” through the sketchy service which may well be skimming your data even if they are under contract to your bank.
Unfortunately, a lot of the institutions’ own interfaces suck so badly it’s sorely tempting to use the quick link.
- on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 4d ago
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 4d ago
You’re starting to catch on…
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 4d ago
The surge in unmaintainable vibe coded AI slop open source projects is well discussed.
Hard disagree. Internet discussion glosses over little things like: quality control, discarding of garbage, reverting to better solutions when they are available. Some irresponsible morons will indeed muck up their production code base with slop and be unable to let go of it when they realize their mistakes, but the majority will be able to try again and replace the bad with better.
Agree: a lot of slop has been produced in the last year, that doesn’t mean anybody is using it.
Better software translates to easier, more automatic processes for a lot of white and blue collar work.
This is what I’m getting at. I’m yet to observe any of this.
I’m living it, but then, for the past 30 years I’ve been building systems that make existing processes more automatic, repeatable, less labor and less mistakes. I’m just building those systems faster and easier than ever before now. This isn’t the only advancement in productivity I’ve seen since I started programming in the 1980s - just one in a long history of significant advancements.
-
on Startup Claims Ocean Uranium Could Power Earth for 50,000 Years in c/technology@lemmy.world · 5d ago
If you don’t run any water overnight then turn on the cold tap (preferably first thing in the morning) and take temperature readings as it runs, you can (likely) spot if you’ve got any cold spots / weak insulation against outside cold, assuming it’s a lot colder outside than inside that night.
-
on Startup Claims Ocean Uranium Could Power Earth for 50,000 Years in c/technology@lemmy.world · 5d ago
Now pipes freeze at 32, so that is a pretty outrageous amount of manadatory wiggle room --23 degrees. I honestly don’t know enough about plumbing or insulation to suggest a fix
If the inside of your apartment is at 55, and the outside is at 9, and the insulation between the pipes and the inside/outside is equal, that puts your pipes at 32. In theory the pipes should be “closer” to the inside temperature, but plumbers don’t always put pipes in with an aim to avoid future plumbing work…
-
on Startup Claims Ocean Uranium Could Power Earth for 50,000 Years in c/technology@lemmy.world · 5d ago
With cheap, clean, safe magic (fusion?) power, you can turn CO2 from the atmosphere back into jet fuel.
-
on Startup Claims Ocean Uranium Could Power Earth for 50,000 Years in c/technology@lemmy.world · 5d ago
And using breeder reactors that 50,000 year figure could be pushed up to 5 million years.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
That’s the thing, at least right now, AI is dependent on new data centers, excess capacity built just for it - it’s not going to “escape” to the banking system and the tractor navigation chips, if it could do that they wouldn’t need to be building all this capacity for it.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
They’re talking, they want other people to become more afraid, but is anyone actually afraid - or just latching on to this delusion of power to push their own agendae as if we all should be afraid?
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 5d ago
how will they sell literally any garbage, how do they get you to buy that any garbage, and how do they make you actually want that any garbage above anything else. its mass manipulation from start to end,
“We could sell horse piss if we put it in an aerosol can!”
Johnathan Lute played by Orson Welles in the 1967 feature film: I’ll Never Forget What’s’isname
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 5d ago
So far, every target is different - like the one with the 3.5" touch display built in, that has its own display driver module. Then there’s Windoze vs Ubuntu vs Raspbian OS, and the Pi Zero 2W has a few different considerations than, say, a Pi 4 or 5, and basically every place I have deployed this so far has had something unique that needed custom attention. Once that’s all worked out, sure, ansible or whatever, but customizing for each target isn’t something “last year’s tools” did as easily as the new agents.
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 5d ago
45K of those lines are documents, specifications, testing results… It’s an overbloated mess bull-headedly pursuing a couple of arbitrarty goals of mine that not many other people have pursued (use of Disk At Once (DAO) audio files with passages defined as sub-sets of the file, 71 dimensioal passage “flavor” determination for next track selection using the now offline AcousticBrainz algorithms, deployment on 5-6 so far various hardware/OS platforms adds a bit as well…)
On the bright side: synchronization of 2 independent players is “coming together” - got some decent performance in the steady state case last night, now chasing the edge cases for faster convergence at startup, etc.
-
on Everybody's Lost Their Minds in c/technology@lemmy.world · 5d ago
running
sudo apt update && sudo apt upgrade -y
Is the really hard part.
That’s not the hard part to do, it’s the hard part to get other people to do, particularly those who can’t just run the package manager or let in-doze play patch roulette every Tuesday.
Security through obscurity isn’t going to cut it in the future, much less than it already didn’t in the past.
Security through air-gapping is still pretty good.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
Apologies. In Westpondia nobody knows what Romani means…
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
The loss-leader pricing is still really distorting perceptions.
I’ve been a $20/mo Claude subscriber for about a year. My work uses Cursor “auto” agent selection is by far the most efficient option in there, and I can burn $80 in a day on Cursor doing the same kind of stuff I’m doing on Claude for less than $1 per day.
Then there’s the Google Pro Gemini access at $4.99 per month for 3 months, then $20 per month thereafter, and while the Gemini 3.8 isn’t quite as sharp as Claude Opus 5, it feels like Google is showering far more token access than Claude does in this “basic” subscription tier.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
Token processing and image processing share similar roots, but I’d say each is a specialized branch of a common ancestor rather than either being derived from the other.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
it’s about replacing the last remaining manual tasks
Some factories already run “lights out” - but there will always be manual tasks… deciding what it is the factories produce in the first place being one example.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
just a continuation of the same automation that already started back in the 80s.
The 1780s, that is.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
The whole political stance that “anybody can do anything if they just put their mind/body to it” is… bunk.
It’s not just in the world of identified “impacted people” with injuries, or congenital differences - we are ALL unique, different, and have differing abilities in differing areas.
The political stance is valuable in terms of preventing discrimination and prejudice. Women can be great scientists and mathematicans, but an honest statistician/sociologist would tell you: it’s not just societal discrimination and prejudice that puts more men in these fields. Then you have the upside-down prejudices where there are more men in middle and upper management, even though, statistically, in a society that doesn’t discriminate based on prejudice, women tend to be better at the actual skills used for good management / people skills.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
can we bruteforce any of the Millennium problems related to cryptography
Cryptographic theory says: no. The whole basis of cryptographic security is that brute forcing doesn’t work (in any reasonable timeframe.)
Theories are overturned, from time to time.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
the transition won’t be thought out at all and will be devastating for the working class.
The transition is rarely, if ever, thought out. Daring risk-takers go too far too fast and fail. Over-conservatives ignore the new and get left behind. There is a sweet spot in the middle, but exactly where in the middle isn’t planned, can’t really be planned - life and business and politics and the economy and the ecology and unforeseen signifiant contributors to the situation mean that the sweet spot is unpredictable - and as long as we continue living by the golden rule: “He who has the gold, makes the rules” it will continue to be unpredictable, otherwise Wall Street could be rigged and those with the inside information would get all the gains - and then the losers would quit playing, not even by choice, but because they’ve bankrupted and have nothing left to play with.
There are alternative approaches - investing in people instead of greed as the ultimate goal is one great alternative that some countries are pursuing more than others, but it’s hard to compete in a global economy where some players are only playing for maximization of financial returns when you are not.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
sounds kind of sane and plausible, but it’s not really borne out by the reality.
I think a realistic case for that is that the AI tools that come out in the next few years will be good enough to do a fair amount of white-collar work
That’s just not what I’ve seen.
What I have seen is that AI tools make software development significantly easier, faster, cheaper - pick two, and as long as you aren’t picking cheaper we’re going to get better software coming out faster over the coming years.
Better software translates to easier, more automatic processes for a lot of white and blue collar work. It doesn’t do everything, but it does a lot.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
I have seen a similar curve in software development - 18 months ago it was highly debatable whether application of AI tools was a net-positive or not. 12 months ago the rate of improvement was very clear and the net-positive wasn’t much of a question anymore. Today, the net positive contributions of LLM agents to software development and maintenance are undeniable, and as you say - there seems to be some plateauing, maybe - it’s hard to tell.
Where I think things are going to continue to “improve” at a slower pace is application of the LLM agents to do better software development and maintenance. I’ve seen more serious Linux kernel bugs discovered - and patched - in the past 6 months than in the previous 5 years. That’s a shift in the landscape, the older OSs aren’t as secure for as long as they used to be, but once we’re through this transition the newer OS versions should be significantly more secure than before - getting all the old stuff updated is going to be a painful transition.
Some of the continuing improvement is in using LLM agents to build better software building tools - as those come online and start to shed their sloppiness, they should genuinely accelerate a lot of aspects of software development. They’ll never accelerate the process of extracting from users just what it is they need, but the turn around from having a product idea to having a product to try continues to shorten - as it has been shortening for 60+ years - but LLM agents have resulted in a significant speedup compared to previous progress.
I’m not worried about a rogue AI unleashing some bioweapon or launching a nuclear attack.
(In Yoda delivery) You should be. We all should be, not because AI will do it autonomously, or in retrospect unexpectedly, but because careless people may let this happen through AI where we have prevented it from happening up to this point.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
Living under a bridge in a box sounds like a better life.
It’s the Gypsy lifestyle of the new world. Gypsies prefer their life to the alternatives.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
disasters that were unintended and didn’t need to happen.
As you say, every “scientifically based” industrial innovation / breakthrough has had the potential to cause new kinds of mayhem, and most of them did to some degree or another. Burning rivers and CO2 overload in the atmosphere spring to mind, but industrial “accidents” are part and parcel of industrial activity, always have been.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
can be so unreliable, it might kill us by incompetence.
Same can be said of Homer Simpson manning the console at a nuclear power plant.
AI is a tool, irresponsible use of a tool is… irresponsible. Just like people puttting “not-self-driving” cars into “supervised driving assistance mode” and taking a nap at the wheel at 80mph.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
any kind of intelligence
A photocell that turns on a streetlamp after sundown, or when a dark cloud passes over the sun, is a kind of intelligence.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
either accelerate humanity to new heights or kill off the species
Arguably those are two ways of describing the same event.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
Once is a win…
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
Unlike a bio-virus that has evolved for a billion years across all the niches of our ecosystems, when AI “escapes the lab” it’s entirely confined to man-made infrastructure, it’s not going to infect a flock of migrating birds and hop to the other hemisphere, it’s going to be in systems we built, mostly within the past 30 years or less, mostly in the past 30 months for the powerful ones.
When AI starts demonstrating “copying itself” through DNA encoding infecting living beings without killing them (too quickly), and/or “running” on something more ubiquitous than massive data-center hardware, that’s when it’s over.
-
on AI staff 'genuinely frightened' for humanity's future, ex-Anthropic researcher tells BBC in c/technology@lemmy.world · 5d ago
I think that they’re seeing all the scary movie stuff start to come true - but missing the essential plot holes like that one: just unplug it.
People complain about AI slop - well, before AI slop there was lazy human slop, but lazy humans generally gave up before writing too many words or painting too much mess, or digital clone-stamping too many generic things… Truth is: if you put in 1/2 the effort of making something great without an AI tool into making something great with an AI tool, you can usually get something much better out in the end - if you’re sincerely trying to use the tools well.
It’s the people who don’t know / don’t care whether the result is slop or not who are putting in 1/10th (or less) the effort of making something great who are putting all the slop out there.
I’m not afraid of the machines taking over (yet), but I am afraid that the same explosion in copy-pasta document vomit that came with word processing 40-ish years ago is going to explode again into a docpocalypse with people using AI to drown each other in supposed “legal written” communications that are only even vaguely understandable using AI tools to read them.
-
on Labor Market Outcomes for AI-Exposed College Majors: Graduating in AI Era Is Like Large Recession for Starting Pay in c/technology@lemmy.world · 5d ago
Supply and demand… will we have to return to slavery before the owning class starts investing in their human capital again?
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 6d ago
I’m just about to run my first test of the “echo mode” where each player plays its own local files, synchronized to one player’s play list (a few issues of delay/clock rate synchronization to deal with in that approach). After that, I discovered I need to do a project rename (I’ve duplicated another project name from 2021, so… time for a different name - on 100K lines of stuff…) then remind me and I’ll give you a pointer to the (new, renamed) repo.
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 6d ago
In University, I drilled a hole in my dorm closet wall to my neighbor’s room so we could run a wire between our stereo systems and I could play whatever he was playing through my speakers. This is like that, for the digital-networked age.
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 6d ago
How “techy” are you? Do you have a couple of Raspberry Pis or similar laying around basically unused? Can you clone a git repo, open an LLM coding agent and get reasonable results out of the chat interface?
The ultimate goal is to get this 100% AI/LLM free, but for now the LLMs are still doing a lot of the heavy lifting of configuring the target devices to install the player.
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 6d ago
if you do something people don’t like they are free to choose a product where they get what they want
That’s ideal capitalism. I find ideal capitalism to be about as real as the concept of “fair” is in adult life.
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 6d ago
I’m evolving a “music player” system which basically consists of a fleet of individual players, each with a full copy of the music library because, even at today’s storage prices, why not? Storage for 10,000 songs at higher fidelity than a brand new LP vinyl album costs less (adjusted for inflation) than an album of 8 songs did back in the 1980s, and only 2 of those 8 songs were usually any good…
So, have a music player in every bedroom, living room, family room, kitchen, car, patio - turn them on when you want, synchronize them when you want - split off and listen to your own playlist when you want - and every player contains a synchronized backup of all the music so you can just drive off with one, go completely off-grid and never interrupt the playlist. The only network traffic is from your phone interface to choose your playlist or synchronize with players nearby - or across the planet.
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 6d ago
storage prices keep climbing
This is just another oscillation cycle in the generally declining cost per bit of storage. We recently went through an oversupply price crash: 2023 prices of $40 per TB and less were an aberration due to supply creating a glut beyond what market demand would consume at any price.
Now we’re hitting a double spike both from production ramp-down after the 2023 over-supply, coupled with an unanticipated demand spike with LLMs in 2025 and beyond…
How long before we’re back down below $40/TB ? If you could predict that, you could make so much money on Wall Street that you woudn’t care about the cost of storage anymore.
-
on People Are Pissed Off and Ready to Own Their Shit in c/technology@lemmy.world · 6d ago
To take the title literally: people have stopped wanting to own their shit since the advent of the flush toilet. In the days of the privee, you’d own your shit, you’d muck it out and maybe do something of value with it. But with the flush toilet, your shit belongs to someone else, they deal with it.
In the digital services economy ‘your shit’ could be considered to include your profile information, what do you use, where do you go, when do you do it, how often, how much do you pay? That ‘digital shit’ has about as much value as what you flush down the toilet, individually, but combined into representative market statistics it’s digital gold - predictive information about what will sell, how much of it will sell at what prices, where and when.
Personally, I’d trade my ‘digital shit’ for advertising. Yes, you can track me, if I don’t have to listen to, see, read or receive ANY marketing materials that I do not specifically actively seek for myself. Unfortunately, that’s not the way the current models work and there’s about zero incentive for the advertising world to change.
As for “streaming” vs “owning” digital content, streaming is the ultimate form of tracking - besides the hook of making you pay per view or listen or read - a huge value (to the sellers) in streaming is that tracking is built-in 100% effective.
Then we can devolve into the world of “durable consumer goods” being led by fast-fashion straight down the toilet. Own a car? Actually maintain it and keep it running for 30, 50 or 100 years? Inconceivable in the world of corporate profit maximization. That’s as backwards as clothing that you buy once and wear for decades, mending and tailoring as needed.
-
on Cult of Anthropic Insiders Rumored to Be Worshipping Claude as a God in c/technology@lemmy.world · 6d ago
pledge allegiance to AI safety and undergo a psychological profiling test, per The Information.
And according to a rumor that, per The Spectator‘s Sean Thomas, is running rampant in Silicon Valley these days, some Anthropic engineers are going as far as to “worship” the company’s AI model Claude.
It would seem that the AI safety psych profiling test should be screening out / rejecting those who would give an AI “whatever it wants.”
-
on Cult of Anthropic Insiders Rumored to Be Worshipping Claude as a God in c/technology@lemmy.world · 6d ago
Just a danger on the bus trynna make it his home…
-
on Enjoy owning your devices while you still can. in c/technology@lemmy.world · 6d ago
PCs can last decades.
They can, but how much of that longevity is in your control? My last round of Intel NUCs all died within a month of each other at 4.5 years of age - I have NUCs that I ran for 6 years before them that still work fine, but that’s now 11 year old hardware and remarkably underpowered compared to today’s options…
People in the US would just hoard used components.
Some would, some already do. Most?
And piracy still exists even though there was real effort to end it.
How real? Piracy still exists because it was too politically costly to end it.
I guess the jailbreaking/right-to-repair community would eventually get around the limitations.
They already do for the current limitations. How big is that community vs the broad market?
black markets always won.
Did they? When I traveled through the former East Germany in 1990 my bicycle was 40 years of design above and beyond anything any East German had seen before. I stayed with a “wealthy” retiree in his apartment filled with the latest/greatest of what he could obtain on that black market: a reel-to-reel tape player, a 9" color TV, basic Hi Fi gear - nothing resembling a computer.
The firearm situation is a bit exceptional
Thankfully.
-
on Everybody's Lost Their Minds in c/technology@lemmy.world · 6d ago
I will say, we’ve been deployed on Ubuntu 18.04 for 8 years now and tracking the CVEs against our configuration watching for potential exploits that could really matter to our systems, and it wasn’t until the past few months that those exploits actually started to get meaningful ability to compromise us.
What that says to me is: the LLMs are finding meaningful vulnerabilities that “the best minds” missed for years and years. And they’re also generating functional patches for these vulnerabilities far faster and more easily than the patches came out in the past.
I’m not loving the changed landscape, but I have to acknowledge that LLMs are making a significant difference.
-
on Enjoy owning your devices while you still can. in c/technology@lemmy.world · 6d ago
I don’t think it’s coming, but if they really do “go there” what it will look like is: extreme tariffs on “open” processors, $1000 for a Raspberry Pi where you can get a new Intel Core NUC class system for $500. And, IMO, it would be worth the premium for the freedom of operation, but, then, you’ve also painted a target on your forehead by being one of “those nutjobs” who are willing to pay so much more for something that “only criminals need.”
I will say: the US is more likely to take away our right to free computing before they take away our right to privately own firearms.
So, the music player rename migration is done - I don’t think too much broke in the process.
The source repo is here: github.com/MangoCats/Lempi
In theory, it speaks for itself. In practice, this has been an evolving project and I believe my current automatic song end finder for fade outs is not as good as a previous generation that I built most of my collection with. You can edit each passage’s lead in / lead out points separately and it’s not a half bad editor, but it’s still clumsy and very time consuming.
If I were introducing this to a new music collection, I’d fire up an LLM agent, have it read the project documentation, tell it where the player (Pi) is on the network (give it ssh key access, and have the music files in-place on the Pi for it to find), and tell it to go through the database induction / setup process. That may take most of 24 hours on a collection with ~10,000 songs…
Once it’s setup, you should be able to define the kind of music you want to hear at particular times of day by choosing 5 to 8 representative songs, the “Program Director” will then queue up similar songs automatically and play them through.
I’ve just barely got the “multi-room” setup going, it has several rough edges, but once it gets synced up it appears to be working pretty well.
If you like to play with LLMs for coding, this is an interesting project to try them on. I find it’s right about at the threshold of what a model like Claude Opus 5 can handle / make forward progress with. If anything about how it’s working bothers you, feel free to ask your LLM to smooth those rough edges in ways that make sense to you, you can at least maintain your own branch and maybe we can merge together a “best of both” situation someday.