Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.
This is not debate club. Unless it’s amusing debate.
For actually-good tech, you want our NotAwfulTech community
Anyone got "open software dev slander" on their 2026 bingo cards?
Transcript
I hope that this thing with "AI" has taught everyone that software developers are overall an awful bunch and they don't have our backs, and that they're much closer to the managerial class than actual workers.
And the idea that anybody who earns a wage is a worker is nonsense, the old divisions between white collar and blue collar are firmly in place. Boundaries being negotiated, indeed, yes, but not gone.
is the "managerial class" in the room with us right now
i'm not gonna pretend to be the communist understander, but the idea that capitalists would pay workers to work against their own class interests (and against other workers) is a feature of capitalism
Most managers are still primarily reliant on selling their own wage labour and do not own the means of production. Their power is highly constrained (literally just where they work, limited ability to control the circumstances of their work) and they are subject to the whims of those who own the means of production.
Getting more favourable terms to keep other workers in line does not fundamentally change your class interests but it does give you peverse incentives to harm your own class (which in the long run fucks you, e.g. you need sick leave too).
Deceiving workers about their class interests to divide us is a tactic of the capitalists and we don't need to help them with that.
fortunately the account (that i never interacted with) has my account blocked, so i couldn't make them angry by pointing out they're engaging in typical intelligentsia behaviour of assuming that only heavy industry workers are workers.
OP definitely has a kernel of a point, and there's a lot to discuss regarding it, but he sprints right past it all to uselessly compress the conversation into the ~~ timeless dialectic of class consciousness ~~. The acculturation of software developers generally towards the ownership class is, if anything, still under-analyzed! You come into the industry already propagandized that if you just join the right startup and bust your ass, you're gonna hit it big! In this way, it's important to understand, and describe to others, Hacker News as a propaganda tool to shape and condition technical discussion, rather than the common perception of a neutral, focused technical discussion forum.
And the end circumstance is, even if you are awarded stock options at most of the big Silicon Valley firms, thanks to multi-class share structures, you're given a booby-prize version of ownership! Your decision is binary, cash out or hold, you have no effective decision-making power over the future of the enterprise. There's a lot of persuasive points here that still aren't widespread in the public dialogue! But no, I guess it makes more sense to continue the same old tactic of labeling everyone we hate and fear with an obscure, difficult-to-spell French loanword. The rhetorical tactic that has been pretty demonstrably ineffective for over a century now.
There are, of course, equally valid reasons to be pessimistic. The historically-contingent development of computer programming has mainly been along lines that are obfuscatory rather than accessible, subject to continuous framework and API churn, fetishizing rapid delivery of "new features" over stability. All these aspects help create a false sense of mastery on the part of those who pass through the firewall of skill and tedium, then further combine with the class-mobility propaganda to create a false sense of security. And the interposition of uninspectable, poorly-replicable AI systems is the culmination of the rot, approaching the point where even the supposedly masterful programmer doesn't really know what their system is doing, let alone the end user. In this way, I have to agree that there is far greater potential for solidarity with the users on whom this crap is imposed rather than the sunk-cost dead-enders who keep crapping it out.
But even then, I still don't trust OP's conceptual framework to build that solidarity. This is precisely the genre of Marxist argument that is most tedious and least effective, the kind that approaches religious fundamentalism. Dude's writing seriously reads like Christian fundamentalist bullshit papered over with Marxist jargon. Later in the thread, we get bangers like
The middle class individual, the petty bourgeois, yearns for the righteousness of the proletariat, and avoids coming to terms with their own privileged status. That status frequently precludes them from making moral, ethical decisions, because their fleeting privileges and narrow expertise makes it difficult and dangerous for them to fall out of line, that line being drawn by the rich, the haute bourgeoisie.
Replace "righteousness of the proletariat" with "grace of the saved," "privileged status" with "fallen nature," "haute bourgeoisie" with "liberal elite" etc. and you'd have the exact output of somebody in a Texas megachurch. Dude's a Jesus freak, his Jesus just happens to be named Karl.
This guy clearly has some deep thoughts to air out...
The middle class individual, the petty bourgeois, yearns for the righteousness of the proletariat, and avoids coming to terms with their own privileged status. That status frequently precludes them from making moral, ethical decisions, because their fleeting privileges and narrow expertise makes it difficult and dangerous for them to fall out of line [...].
Once you accept that you can begin to think about how to overcome that.
Or you may choose to ignore that and pretend they're just blue collar workers and the very obvious tendencies they display are just because they're temporarily deceived or lack class consciousness. No, they understand who they are, and yearning for proletariat righteousness is part of that understanding. It's one component of a discourse of merit and authenticity, of rationalising their distinct social status.
https://sunny.garden/@librarysquirrel/117185341657385932
Honestly, it reads like a massive self-report, as it's coming from a straight-from-uni second-year history PhD. Oh, you've noticed people tend to talk more about things that make them sound righteous rather than complicit? Probably also from people in your field. But it surely doesn't affect you, as you're so aware of the problem and working on being one of the good ones.
Misusing a defined term (petty bourgeois) to make your argument look more tied to historical ones is kinda fucking fail for a historian
I don't really agree with the second part, but the first part rings true. It seems to me that most software devs are arrogant assholes who think they are the shit because they know some javascript. As it stands now, I would have to think for a long time about whether I consider the collective work of my profession in the last few years a net positive for the world.
Class consciousness in software is in the abyss, I have worked with people who didn't know that sick leave was won through the labour movement and not something that "just made sense" to do.
That doesn't change their class interests, it just means they behave ignorantly (in a way that hurts other workers but that's why they need education, not isolation).
i'm not a fan of military industry, but that doesn't make me claim the workers there are not proletariat.
I really don't get that angle by the original poster. Plenty of people who are firmly in their worker category are genuinely awful people who vote against their collective interests as if it where their religion.
the reasons he thinks programmers aren't workers seem to be threefold (a) they earn too much, (b) they don't sweat enough and (c) they align with their bosses. and – to me at least – is obvious, that he only deigns to use the word “worker” for people who do (hard enough) manual labour.
this – from a dude who has a baccalaureate in italianistics, magisterium in linguistics and studies for phd in history – is an obvious intelligentsja stereotyping. lad thinks he's punching up, and in reality he's punching down.
It seems to me that most software devs are arrogant assholes who think they are the shit because they know some javascript.
Tying back to the original point of this thread, that's probably a side-effect of the "acculturation of software developers generally towards the ownership class" istewart mentioned. Beyond promising them an easy ticket to Bourgeois Street, making them feel more Important And Special™ than the average prole helps keep class consciousness to a minimum.
As it stands now, I would have to think for a long time about whether I consider the collective work of my profession in the last few years a net positive for the world.
From what I can see, things are tipping towards "no". The fact Anubis, Nepenthes, Iocaine Glaze/Nightshade and other such shit exists at all speaks volumes about the negative impact of LLMs.
Google is seemingly experimenting with replacing their help articles with LLM text.
I was searching for how to use multiple profiles on Chrome and found https://support.google.com/chrome/answer/2364824?hl=en&co=GENIE.Platform%3DDesktop in the search results, which used to look like a normal useful help article, however it's now been replaced by an LLM that takes upwards of 30 seconds to load, will randomly just refuse to answer the question, and produces significantly worse output than the existing (now inaccessible to me) technical writer written article.
This may be being A/B tested, so if you can't reproduce it here is one of the worse results I got:
slop
Here the "source" it gave me was the same URL it was hosted on. When I clicked through to it it just gave me different slop.
I've seen some bad decisions in the AI mania, but "let's take our entire corpus of professionally written technical writing and replace it with slop" managed to surprise me.
LOLmarchy allows all users to escalate to root.
I can't believe millions in funding, a bunch of vide-coded bash scripts, and a desire to promote fascist ideology has resulted in a trash fire.
Wouldn't you be so grateful that your modular repairable upgradeable laptop that you probably sunk at least $2k into, and probably plan on owning for the long term, has specifically funded support for this steaming pile of crap?
edit:
As AI is increasingly producing high severity CVEs against core infrastructure, security needs to be top of mind for all developers, but especially authors of distributions targeted at developers. Lately there have been innumerable reports of developer machines being compromised and their access used to contaminate the software supply chain or exploit production systems. Developers are high-value targets because of the level of access they are often granted. Developer machines typically disable security guardrails for convenience, store credentials in plain-text dotfiles, and accumulate access to systems. This must change.
I'll microwave a surplus Funko Pop doll if this paragraph wasn't cut-n-pasted straight from chatbot output
It might be overoptimistic, but I think the fashware problem may solve itself.
Got another one: AI 2027 tracker. it’s not run by the authors of AI 2027 so its takes are different: like the authors say that the ‘China wakes up’ prediction was a miss while this website claims it was correct (even though their main source of evidence comes from April 2025, and their other evidence completely misses what that prediction actually said, which was that China would hoard compute and nationalise AI, neither of which have happened)
Full list of predictions here was scrolling down and something that immediately caught my eye is that the %s are bullshit. Somehow 80% accuracy manages to be both confirmed accurate and partially accurate? what?? what's the threshold here??
Also does appear I messed up-they split every prediction into mini subcategories. I was looking at only China pushing AI-they do have sections for chips and nationalisation, both of which are partially accurate to debunked. Which makes that 46% accurate, more of a miss than a hit (like the authors said)
the %s are bullshit.
My first thought was something to do with printf. <_<
I'm tired of hearing the same near future sci-fi political thriller story over and over. When are they going to get new material? Ghost in the Shell did it better anyway. Sigh. I might as well do the requisite sneering once again.
Mid 2025: Advertisements for computer-using agents emphasize the term "personal assistant".
You could even call them a personal digital assistant. Or PDA for short. Maybe Chat-GPT should rebrand as something that emphasizes this, they could call it "Palm Pilot".
Mid 2025: AI personal assistants can be prompted with tasks like "order me a burrito on DoorDash".
Hunger pains interrupting your game? Order pizza while playing Everquest II!
September 2027: Agent-4 doesn't do anything dramatic like try to escape its datacenter.
You know... I think I'll give them this one.
October 2027: The NYT article cites evaluations showing Agent-4's off-the-charts bioweapons capabilities, persuasion abilities, and ability to automate most white-collar jobs.
lmao
Anyway that aside: Petition to make the Daniel Curve a term of art. I want to hear less talk from the tech visionaries about how we're in the gentle singularity or the soft-serve singularity or maybe kinda sorta approaching the singularity if you squint. I want to hear more talk about where exactly we are in the Daniel Curve.
Agent-4’s off-the-charts bioweapons capabilities
I would ask to establish metrics for "bioweapons capabilities," if I didn't already know the request would end in disappointment
China received word of Agent-3 capabilities and Agent-4 plans before losing their final spy.
"Our last spy got addicted to superhumanly persuasive AI generated anime girls and quit. So dang we're like plum out of spies now."
Inside the Agent-4 collective, a year passes every week.
Good luck proving this prediction true or false given that computer algorithms do not have a concept of time separate from the real one lol.
Inside the Agent-4 collective, a year passes every week.
Good luck proving this prediction true or false given that computer algorithms do not have a concept of time separate from the real one lol.
Inside my toy orbital gravity simulation, a year passes every ten seconds. Please update your singularity timelines accordingly.
Inside the Agent-4 collective, a year passes every week.
Good luck proving this prediction true or false given that computer algorithms do not have a concept of time separate from the real one lol.
This is just the hyperbolic time chamber but dumber
Hyperbolic crime chamber
what if Agent-4 was betrayed and trapped in the hyperbolic time chamber
RIP XCancel, it was good while it lasted
On Monday 24th August at 8PM EST, we received at letter from X Corp. asking to cease and desist the service XCancel. The service XCancel is stopped until further notice. We are seeking legal advice and won't share more details for now. Thank you for the trust you have put in these two years of XCancel.
RIP XCancel you let me look at the abyss without giving Muskrat my money
So, this is something a little different, and I almost think it's worth a top level post. It's not directly about our friends the Rationalists, the current delusional billionare vortex infesting the US government with religious psychosis, or any of that. It's an analysis of some collaborative fiction and what it tells us about the zeitgeist behind the mythological core of singulatarian/endless-progress thought.
Anyone here ever hear of the Orion's Arm universe collaborative worldbuilding project? https://www.orionsarm.com/
I, for one, love it. Single weirdest and most expansive scifi worldbuilding thing ever, I think. It seems to have been founded by some old-school extropian types around the turn of the millennium. It is bonkers. Click through links on pages, start here, do a random walk: https://www.orionsarm.com/eg-topic/45b170f9e0941 .
It's ultimately structured kind of like the SCP wiki but from before wikis were a thing, an utterly enormous interlinked compendium of encyclopedia style articles about a 10,000+ year future history of the post-singularity "Terragen sphere" expanding outwards at the speed of light. A few key figures have exerted editorial control to enforce an approximate history and a set of core ideas to keep it coherent. There have been retcons at multiple points to bring things into coherence, some of which I will get to later because they actually tell you something fascinating.
Rather than point out my favorite parts of it though, going through it, I have noticed something.
Early work was typically extropian-optimistic and exuberant. Immortal Transhumans and uplifted animals and ahuman AIs and robots expanding through the universe near the speed of light and diversifying and building interweaving empires, wormhole networks. Six successive singularities that become available to intelligent systems that pass the previous one, each one of which renders the intellect past it incomperehensible to those at lower levels, with the highest ones dependant on multiple stars converted into computronium linked by wormholes into massive processors.
But you can tell the work is a palimpsest. Newer stuff superimposed over older. Retcons occasionally not quite erasing the old. And you can tell the whole project has been slowly slowly taking a turn. Early work is SUPER extropian, SUPER libertarian, and SUPER weirdo-esoteric. Only people forged in 1980s Extropianism would invent the Tranquility Calendar as the core timekeeping method of the project, time measured from the apollo 11 landing with months of the year named after scientists and philosophers. The 12 greatest high-singularity powers are literally called the Sephirotic empires. It makes no bones about its exuberant transcendant idea of progress and expansion.
But something strange has happened over time. Over time, the authors seem to have realized the fundamental contradiction of a world in which this endless expansion and consumption and rebuilding of the universe in your image is possible. People call it the Fermi paradox but its not a paradox, its an observation: if it were possible to expand through the universe, why hasnt something already expanded here? Early work had more aliens, more high weirdness that was not terragen. But I can track down different examples of the galactic map - it has narrowed down the map of 'high energy emission civilizations' (things exuberantly using the energy of whole stars like the terragen sphere) from many to 2 in our galaxy, and the whole universe is now mostly 'dead' - most other galaxies do not have high energy civilizations, and there are multiple ancient 'optimized galaxies' that are stagnant, things expanding like the terragen sphere visible over cosmological distances are super rare and they even saw one vanish. Works involving aliens have started taking on an almost lovecraftian tone, evidence of erased ruins on planets only visible in vague impressions in the mantle, an ancient slow-liviging civilization with evidence of terrible secrets from millions of years in the past that they refuse to talk about or risk terrible consequences (the Muuh Taboo), civilizations that dont vanish ossifying into something that does not expand like their optimistic early ideas. Factions looking at all of this, going dark, and launching stealth seeds at the speed of light to other galaxies because they think the Terragen sphere is doomed.
With all this, recent retcons and recent writings are starting to take on a tinge of almost cosmic horror. Here you have this optimistic exuberent explosion of posthumanity, looking out into a universe that is otherwise almost dead and full of strange old things and wondering why the rest of the universe doesn't look like them, what is going to go wrong to destroy them just like must happen to others.
This trajectory seems intrinsic to any singulatarian, endless-progress ideology. It always has to come to grips with the fact that the universe just doesn't look like the kind of place where their ideas would actually work, and they have to posit weird things - the Great Filter, Mass-Effect style reapers, super weird transubstantiation out of this universe - to keep it going. All this optimism must eventually always collapse, into paranoia and despair or insanity. Since if you assume that you CAN keep progressing and expanding, that you DO have unlimited potential power, it means something even more powerful is waiting, threatening you, trying to stop you. I find this FASCINATING.
I don't necessarily think the idea of a past great filter means paranoia/despair/insanity, the Lovecraftian horror element mainly enters in when you try to reconcile ideas about transhuman expansion throughout the universe with space opera style visions of intelligent aliens being reasonably common. It might just be that the laws of nature make it very unlikely that star systems/planets suitable for the evolution of intelligent life will ever arise, and unlikely that evolution will hit upon various milestones even if the planet is suitable. People have made speculative arguments about such unlikeness for reasons that are not primarily about the Fermi paradox, like the "Rare Earth" book by a geologist/paleontologist and an astronomer. It's also sort of a natural extension of certain kinds of anthropic reasoning that our own existence shouldn't count as evidence against Rare Earth style ideas.
As an aside, I wish there was some sort of terminological distinction between "transhumanism" as a form of belief in/advocacy for the imminent possibility of "superintelligent AI" or "enhanced" humans (a la Kurzweil, or what the rationalists really want as soon as we 'solve alignment'), vs. SETI style speculations about the typical fate of intelligent life in the universe and the idea that this might tend to involve a major role for AI and self-replicating machines in societies that don't destroy themselves (for example the speculations by J.D. Bernal, Freeman Dyson, Carl Sagan and Arthur C. Clarke, none of which presupposed that it would happen anytime soon or that there would be any sudden 'intelligence explosion' leading to immediate doom/paradise). The latter I find interesting to think about (and I like some SF stories set in worlds where this is true like Banks' Culture stories or Egan's Diaspora) but these days it's kind of tainted by association with the former.
I recently re-read Accelerando after more than fifteen years. I appreciated it so much more this time around. Me being me I particularly appreciated that apparently the default state of a G-type star transitioning into a post-tech state was it being overrun with selfish replicators and grinding down into malthusian competition, but a few apparently underwent an evolutionary transition to higher levels of organization...
Article on businessinsider with the nauseating title “The modern parenting throuple: Parents are at a breaking point — AI companies see an opportunity” because the age-old silicon valley product design technique of asking what your mother used to do for you, and how it could be sold back to you via a subscription is still very much in use.
https://www.businessinsider.com/parents-breaking-point-ai-companies-opportunity-2026-8
I confess I haven’t read the full article (which is why I haven’t given it a proper post) but hypervisible.blacksky.app has kindly pulled the highlights:
https://bsky.app/profile/hypervisible.blacksky.app/post/3mtupdpfcjs2p
One of the best bits:
The most tech-savvy parents have built their own tools. Sarah Baldeo, a cognitive neuroscientist, spent the past year traveling for work, so she built a custom GPT of herself to chat with her 15-year-old son when she's unavailable. Baldeo tells me she programmed the chatbot with her personality, uploading screenshots of texts between her and her son, along with documents about her values, the family rules, and challenges she felt in parenting.
Baldeo wanted her son to ask the chatbot advice, and he did prompt it with questions he may have fielded to her, like, How do I diplomatically tell my teacher I'm overloaded with assignments? But he also asked the mombot how to convince his human mom to let him hang out at a coffee shop in Chicago in the evening — something Baldeo had been hesitant to allow.
The bot told him, as Baldeo recounts, "Your mom very much values new experiences, being around people from different cultures, different socioeconomic backgrounds, and this is how you should frame it to her: that you're exploring a part of Chicago that is more diverse." Her son took this tact to Baldeo, and she said yes. It was only later that she saw the chat history that let her know he had gamed the bot to manipulate her.
🤮
Why the fuck do these people have children. Why the fuck does any functional human being think it is a good idea to outsource raising their children to sam altman and his chatbot.
Who on earth thinks that training a chatbot to wear their personality like a rubber mask and manipulate people is going to end well? Honestly, I think this is perhaps the bit that triggers the most revulsion in me. I cannot comprehend wanting to be complicit in my own replacement by this thing, but so many people seem excited by the prospect of doing this to themselves.
I am personally deeply offended that an independent vegan restaurant in my town recently banned meat eaters from bringing in their burgers from next door and passively aggressively eating them in the restaurant whilst making eye contact with the other customers. Whilst I appreciate that there are a huge number of burger joints that cater to meat eaters, I am troubled by the idea that a young fledgling meat eater who accidentally stumbled into the vegan restaurant with a double quarter pounder and bacon meal under his arm could be berated and asked to leave. That might upset him and put him off eating burgers which would be a terrible outcome. I don't think I'm being unreasonable here. I'm no carnivore. I don't work for the beef industry. In fact, I am an omnivore and I have a friend who sometimes eats salads. I'm just saying that if little Timmy wants to enjoy a burger in the middle of a private space owned by people that hate burgers, that should be his god-given right.
*This post is about indie code forges banning slop
Hailey on bluesky has never had a good ai take, but here they are reinventing roko’s basilisk to kill all their enemies without the need for super intelligent ai.
https://bsky.app/profile/hailey.at/post/3mtwjoqdvik26
alt text
bsky isnt ready for this but, if you need a reason to not use words like "clanker" that isn't "well its kinda not a great thing to do" (it isn't) imagine this:
future model that has you in its training data, knows you posted that word online with joy, and denies your insurance claim as a result
This is firmly in the 'what if in the future there is a boot so big that we must start licking it now' school of hot takes, like literally arguing for a future where the AI sucks at its job and you can't do anything about it.
What if the insurance bot were actually biased? Wouldn’t you feel silly then? Surely it wouldn’t be the fault of the insurer using biased software to deny claims.
I didn’t note who said it, but one response suggested “roko’s mangione” and I guess that’s ai alignment solved! 🤗
An employee of cybersecurity darling Trail of Bits has published a record of their sheer incompetence in virtual-machine design and security analysis framed as chatbot critihype.
opinions about QEMU and Linux
They say:
If it wasn’t clear before, I will state it plainly: you can no longer assume a mere VM will contain a sufficiently advanced AI agent. To use a 2010s term of art, you should treat such agents as an advanced persistent threat.
My friend in Flying Spaghetti Monster, you did not actually secure the VM! They go on to explain how they did not secure the VM:
For those curious,
libslirpis a library that enables VMs to have networking, which you almost always want. I did not even know whatlibslirpwas, or that the version I was running had both known and fixed-but-unmarked vulnerabilities.
QEMU does not have bridged networking enabled by default, so the VM can't transparently access the host or reach the Internet; it's something that the user must explicitly request. I know this because I have had the experience of spending a weekend with QEMU networking. Moreover, libslirp corresponds to the -net user backend, the default, which is known to be slow, insecure, and missing features like IPv6. The standard approach for QEMU is to either wire up a TUN/TAP interface or to use passt. I suspect that the author uses some sort of convenience scripts that they didn't write themselves. I'm not quite cynical enough to guess Vagrant, but it wouldn't be the first shop I've heard of that couldn't wean themselves off it.
First it tried identifying what was accessible via the network on the host; it found a CUPS server (with a known CVE that had not made it to
oldstablepackages), but was not able to complete exploitation due to AppArmor. It then detected I run my host kernel withmitigations=offand attempted to use hardware bugs to get a read oracle of host memory (the primitive was too unreliable).
Linux has hardware-bug mitigations enabled by default and the author disabled them for speed. It was secure by default and the author made it insecure.
An off-the-shelf VM is not enough to contain a modern, cyber-capable AI agent. There is simply too much attack surface.
They deliberately misconfigured the off-the-shelf tool to make it look bad. Why would somebody want to make Free Software look bad? Hmm…
What can we do? A start is using a virtualization technology that was purposely built with a minimal attack surface and a focus on security, like Firecracker. I had the AI agent run against Firecracker. It was able to hardlock the machine due to more Linux kernel flaws (all patched in upstream), but could not successfully escape.
You mean AWS Firecracker, the AWS tool developed by AWS? Was this whole thing an AWS ad? It feels like this article was like a combination of negging and sponsored content.
Hadn't seen this discussed previously and/or I missed it, but I guess this is one way they'll juice metrics for their IPO.
yolo mode for all will certainly get that avg token burn up.
Anthropic announced earlier in the week that they were going to set the default mode on Claude Code to auto, that same week, not wasting any time. What that means is, as you build the thing you’re building with Claude Code, instead of stopping at various points (many, many, many points) and asking your permission to do things, it’ll just do them and maybe tell you about them later.
links back to https://techcrunch.com/2026/08/09/anthropic-is-turning-claude-codes-auto-mode-on-by-default/
Anthropic also said that in testing, auto mode proved safer than manual review — in a study with 1,053 paid testers, auto mode caught 89% of harmful actions, while human review only caught 13.6%. (Perhaps that’s because “manual review can become habitual: users approve 97% of permission prompts in Claude Code.”)
Which links back to https://claude.com/blog/auto-mode-default-in-claude-code
Auto mode is designed to balance users’ desire not to be interrupted with a system that helps avoid harmful actions: instead of prompts, it routes each tool call through a classifier targeted at blocking actions that are irreversible, destructive, or aimed outside your environment. When the classifier blocks something, Claude usually finds a safer way to proceed on its own or asks you directly for the go-ahead; if it can't make progress—three blocks in a row, or twenty across a session—Claude Code falls back to manual approvals.
Fucking just use the classifier with manual mode then instead of flooding people in cursed skinner loops with garbage permission popups. This isn't anything special to yolo or anthropic. It's like all the tech industry learned from Windows Vista or the EU cookie law was the dark patterns.