I mostly write lean4 now and emit proof-carrying System F Omega via rfl. It's the right level of abstraction when the droids have been pinned to theory laden symbolisms. It's also just pleasant to use.
Whoops, I literally did the same thing as this guy earlier this week, but did the testing using `claude -p` so I can identify when Claude Code would (or would not) load Skills for a particular prompt, so that I could improve the skill definition.
Who knew that using Claude to introspect on itself was against the ToS?
I've had AI write ~100% of my code for the last 7 months, but I acted as the "agent" so the AI had very high levels of direction, and I approved all code changes at every step, including during debugging.
Mostly Gemini Pro 2.5 (and now Gemini Pro 3) and mostly Clojure and/or Java, with some JavaScript/Python. I require Gemini's long context size because my approach leans heavily on in context learning to produce correct code.
I've recently found Claude Code with Opus 4.5 can relieve me of some of the "agent" stuff I've done, allowing the AI to work for 10-20 minutes at a time on its own. But for anything difficult, I still do it the old way, intervening every 1-3 minutes.
Each interaction with the AI costs at least a $1, usually more (except Claude Code, where I use the $200/month plan), so my workflow is not cheap. But it 100% works and I developed more high-quality code in 2025 than in any previous year.
And I would argue speadsheets still created more developers. Analytics teams need developers to put that data somewhere, to transform it for certain formats, to load that data from a source so they can create spreadsheets from it.
So now instead of one developer lost and one analyst created, you've actually just created an analyst and kept a developer.
Citizen developers were already there doing Excel. I have seen basically full fledged applications in Excel since I was in high school which was 25 years ago already.
If anything, there were a bunch of low barrier to entry software development options like HyperCard, MS Access, Visual Basic, Delphi, 4GLs etc. around in the 90s, that went away.
It feels like programming then got a lot harder with internet stuff that brought client-server challenges, web frontends, cross platform UI and build challenges, mobile apps, tablets, etc... all bringing in elaborate frameworks and build systems and dependency hell to manage and move complexity around.
With that context, it seems like the AI experience / productivity boost people are having is almost like a regression back to the mean and just cutting through some of the layers of complexity that had built up over the years.
The WIDGET model of "working geniuses" is one possible answer, it does explain a lot of team dynamics in my experience.
Since no one has all six working geniuses, and you're only a genius at two, it takes a collection of people, proportional to the work that needs to be done, of each type.
It's maybe slightly less trivial to do, but still incredibly common to buy awards, recognition, press releases, positive reviews and commentary in publications.
You might be shocked to find out how much the performers being written about in magazines or discussed on TV shows is a direct line to the production company promoting them. Similar for awards.
> You might be shocked to find out how much the performers being written about in magazines or discussed on TV shows is a direct line to the production company promoting them. Similar for awards.
I mean Payola as a term literally came from bribing DJs on radio stations to play your / your artist's music.
> What would be amazing is if some distro would just ship native LLVM with all the things working out of the box.
Omarchy could/should do this, nice low-hanging fruit.
@dhh, if you're listening, the other good thing Omarchy could do is support the VFX Reference Platform specs maintained by the ASWF. That would bring in all of the Linux-based VFX software to Omarchy in a clean way.
It's a problem with pretty much anyone. Things are bad from a fundamental structural failings for decades, elect new person, don't see immediate turn-around, they're massively unpopular.
The only way out of this is if you successfully blame $marginalised_group for the peoples problems. Or spend decades undoing the damage, but nobody ever gets decades in power.
Most don't want any of the options presented to them. Almost all the parties don't really serve the electorate, so a large number of people are abstaining.
I appreciate this in an anecdotal but I've spoken to quite a few people I know in my family, that saw it as their civil duty to vote and they told all told me some variation of "there is nobody worth voting for", "I don't think it matters who I vote for".
There are good options I think for most people. I did not like labors party policy, so I voted for the Lib Dems in a large labour area, did it achieve anything for them? No, did I do my civil duty?
I am sure many green voters felt the same way for many years and now they stand a decent chance of getting many seats!
Your best option in your area was a protest vote, but you still believe there are good options. To me that sounds like cognitive dissonance.
I don't vote. There are many reasons I don't vote. However the biggest reason I don't vote is that the whole premise or at least how it is presented to you is false. The way it is presented to you both in school, media etc. is that you are supposed to read the manifesto, consider the candidates arguments and history etc. etc.
People don't do that, they vote for their team. People have their political teams, much like Premiership Football it often comes down to the "Reds vs the Blues" (literally Man U vs Man City).
That might be true, but the votes (not seats, first past the post, almost guarantees people aren't represented):
Labour: 9.7M
Conservatives 6.8M
Reform: 4.1M
Liberal Democrats 3.5M
The point clearly stands that had Reform not been a thing, 2024 would have been a conservative landslide.
What we got was a Labour landslide, what we should have got was some coalition.
As the sibling comment said. You are making the assumption that every Reform voter would have held their nose and voted Conservative instead. A lot more people would have stayed home I think. I don't think anyone thought the Conservatives could win and that includes the Conservatives themselves.
Yes, though I'd be careful about assuming that votes are Conservatives <-> Reform on a left-right median voter model. The other aspect that Reform has (and will have at least until it forms a government) is anti-system/populist credentials. Labour had a little of that last time (they are a deeply establishment party, especially under current leadership, but they were coming off a period as very public opposition to the government and the current state of things) but will have very little next time.
It's certainly not a given that all the 2024 Reform vote would have gone to the Conservatives: a good chunk of it would have likely been disgusted abstention, another chunk to other anti-system parties (mostly of the right fringe, I suspect, but not excluding the Greens despite wild ideological differences), and likely a further (if smaller) chunk to other parties which were simply not the Conservatives (including Labour and the Lib Dems).
Edit: the best analysis on this is likely to be in the latest volume of the long-standing The British General Election of XXXX series, which has just been published online[0]. I haven't had time to look at it yet, though.
Some of it is deliberately attempting to appeal to Reform voters, in ways which have infuriated Labour supporters while not winning any Reform support.
Which is even more bizarre given appointing someone as divisive and pig-ignorant as Priti Patel the Home Secretary would have the tabloids crucifying a Labour PM. Johnson and his after-dinner speeches about the Mayor from Jaws forgave a lot of blunders during C19.
Remember also that when Sunak stepped down, Priti was put forward for leader. If she had played off her Zionist aspirations just a few years later she'd be right in the current newscycle re proscribed organisations and 'domestic terrorism' charges in the UK, and possibly in the running for the big chair.
Yet these laws and general direction have been in place through half a dozen prime ministers, including ones initially very popular (Johnson especially, but Cameron wasn't particularly unpopular until the brexit mess)
Right. When I'm at a counter-protest facing the local† Nazis (who in this incarnation have decided to call themselves "patriots") among all the rhetoric accusing us of supporting terrorists (no matter where brown people may come from they're apparently "ISIS" or "Taliban" these days) or rapists or any number of weird conspiracies, one thing they often yell about is that Keir Starmer is (to quote them) "a Wanker" and I have observed to other protesters that uniquely this is probably a widely shared viewpoint. Yeah, he is, but, why you are you being so racist, why do you want to terrify my neighbours, what does that have to do with Keir?
† Local in the sense of being the ones who turn up, my guess is that a good number of them travel by car from quite some distance, personally I live five minutes walk away.
reply