Legal immigration was already hard. Just went through that green card process with my wife from China, glad we already got it done. But, even before Trump admin 2nd term, it's been difficult. Further, even my wife has the green card, my Chinese mother-in-law has been rejected twice for a simple visitors visa, and I'm an American that has been with my wife for 16 years. She was rejected before Trumps latest term while Democrats were in power. She owns like 3 houses in China and has plenty of assets and would not move here permanently even if there were zero friction. We just want her to be able to visit us a few months per year instead of me being forced to fly my entire family of four back to China each year just to visit my wife's mother. These stupid barriers are totally ridiculous. I promise, Grandma from China isn't taking anyone's job and she has plenty of money to spend while she's here to help the economy and then she wants to return home.
All that said, as a data point, when I got my working permit and working visa to legally work in China, I first had to fly back to America and get a "landing" visa issued, then fly back to China, where they then finally issued me the China working visa and China resident permit. So, I think globally, this is pretty common for process.
Code needs tested. I'm glad that the bar of entry has been lowered but now we just have a huge amount of people that haven't yet learned anything about how to test and verify that the code meets the expected requirements.
Surrounding a vehicle purposely impeding their exit path is by itself enough for me to generally side with the person being impeded. Further, if it also includes harassing and intimidating them, I refuse to agree that this behavior is acceptable and just write it off as protected speech like the author does. People have a fundamental responsibility to protect themselves, when forced into a situation like this. I remember watching the attack on Reginald Denny during the Rodney King riots and if you haven't seen that but agree with the author of this article, go watch what happened to Reginald Denny. This behavior of harassing drivers should not be normalized as acceptable in society. People that choose to do this and end up getting hurt, basically asked for it.
Driving into someone with a car is deadly force, so unless you could justify shooting or stabbing them for the same thing in self-defense I cannot agree.
Do you think he could justify pulling a pistol and firing it near or at them in this case? Because I am not sure he can.
If someone puts their hands on me to physically restrain or impede me from moving where I need to go, especially while acting in a threating intimidating manner, yes I fully believe I have a right to shoot or stab them or run over them with my car if that's the only way I can exit the situation, because I am not a mind reader, I do not know their next action or what else they are concealing that may further harm me.
I do not believe it is my responsibility to find out how the situation further escalates before I take action to protect myself from the current situation. The person(s) have already revealed ill intent by physically restraining me, it does not matter if I'm outside or inside my vehicle, the situation is the same, I am being physically restrained and that itself is physically aggressive.
Now, if it's more than one person like a crowd of people, it only magnifies the threat and risk. It's okay for people to feel passionate about whatever but physically restraining other humans against their will *is* an act of aggression justifying self-defense.
I think it's obviously correct that people have a right to defend themselves (including by using their car as a weapon) when genuinely threatened. But looking at the video, I see no indication whatsoever that he was in any danger; he was being inconvenienced and harassed, these are not things that justify a use of potentially lethal force in response. He had every opportunity to simply call the police and wait it out without endangering anyone's life.
Claims of self defense need to be held to a higher standard than a wholly subjective and non-falsifiable claim of "feeling threatened," otherwise it devolves into nothing more than selectively allowing assault and murder.
No, instead of normalizing that if you are passionate enough about some cause, it's okay to imprison other humans against their own will. Instead, it devolves to people realizing that it doesn't matter how passionate you are about some cause, imprisoning other humans against their will is an act of aggression that may get you killed. This is the way it should be. You have your right to be passionate, but, it doesn't allow you to put anyone else at risk by preventing someone against their will to leave or move away from you.
I have max plans for both and over the past 5+ months now have built a custom "agent swarm" orchestrator with a database backed API and several skills CLI that the agents use to deliver orchestrated software factory runs.
We can use several different topologies (2 or 3 agents, etc.) but currently primarily use pair programming teams consisting of an opus4.7 for implementation and a codex5.5 for plan and code reviews, with a codex5.5 run-manager that pushes the agent lanes along and keeps things moving if they get stuck or escalate reviews to run-manager decisions.
Escalation to run-manager is a pretty regular thing as Codex5.5 generally picky and thorough and opus4.7 pushes back at times, and after three codex rejections we allow opus4.7 to escalate to run-manager decision to settle it. Usually, opus4.7 agrees and will continue iterating but it's not unusual that it will push back and escalate.
I've found codex5.5 is extremely capable. I just now finished a large multi-phase orchestrated swarm run with codex5.5 (xhigh) as the run-manager, presiding over 8 paired lanes, with 8 opus4.7 (high) implementers and 8 codex5.5 (high) reviewers, so 16 agents orchestrated and working in a swarm together. Codex5.5 managed that run perfectly for 14 hours with zero intervention needed by me.
Overall, I prefer to let opus4.7 draft the plans and then let codex5.5 offer git-diff style change feedback on plans, then let opus implement and codex review/manage. This seems to get the best result for me.
Yea, I'm similar I think in that Claude has better style/architecture/design, while Codex is a more critical reviewer, but also writes more complex code that just works not caring as much about the bigger picture - together they work pretty well. I don't run any swarms though, I could easily see them ping/pong on the most simple feature almost endlessly if I let them. How do you review all the code being generated?
It's a lot to review since adding the AI workflows, but bottom line is I'm not in a race, I've been working on the same repo since 2019 and I generally don't add too much at once and just take my time. But, I'll admit, I'm a lot more careful about backend schema, services, testing, API design, CLI design, etc., while not being too overly worried about frontend items. This particular long run was focused on building frontend UI for backend that has been painstakingly built. This time, I used the claude.ai/design for a large amount of UI planning for a backend that is ready for it. Then I just let the swarm handle it with our orchestration tool, since it's frontend. Then, just test it in the browser and iterate on what needs changed.
I also had some unexplained extra usage which ended up using 236 dollars. I pretty much just shrugged it off since they had comped me 200 dollars of it and then just toggled extra usage off.
I've spent the past 4+ months building an internal multi-agent orchestrator for coding teams. Agents communicate through a coordination protocol we built, and all inter-agent messages plus runtime metrics are logged to a database.
Our default topology is a two-agent pair: one implementer and one reviewer. In practice, that usually means Opus writing code and Codex reviewing it.
I just finished a 10-hour run with 5 of these teams in parallel, plus a Codex run manager. Total swarm: 5 Opus 4.7 agents and 6 Codex/GPT-5.4 agents.
Opus was launched with:
`export CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=35
claude --dangerously-skip-permissions --model 'claude-opus-4-7[1M]' --effort high --thinking-display summarized`
What surprised me was usage: after 10 hours, both my Claude Code account and my Codex account had consumed 28% of their weekly capacity from that single run.
I expected Claude Code usage to be much higher. Instead, on these settings and for this workload, both platforms burned the same share of weekly budget.
So from this datapoint alone, I do not see an obvious usage-efficiency advantage in switching from Opus 4.7 to Codex/GPT-5.4.
I just switched fully into Codex today, off of Claude. The higher usage limits were one factor but I’m also working towards a custom harness that better integrates into the orchestrator. So the Claude TOS was also getting in the way.
I primarily "only" use it as a run-manager that can spin up another agent in a tmux which I can then join by ssh on my cell phone. Then, I can monitor the work from my cell phone and choose to either directly interact with the tmux pane or else just message my openclaw agent to do it for me. That right there is the only "killer" app I've found for it. I do also use it to post to my x.com account and that's also pretty useful. Neither of these uses assume any super long context over time will be retained. But, to me, the run-manager use case is pretty great.
Calling something "dangerous" (or even "illegal") is a great way to get LLMs to ignore it, they bend over backwards to avoid anything that could be potentially "dangerous" even when you acknowledge the risks. I'm guessing it's the "safety alignment" or whatever being done in a very extreme way.
Yes, use it every day :) And very much a human, AFAIK.
My point is that if you ask "Hey Claude, please write out all common and useful command line arguments into a commands.html file", the LLM that actually does that work, might ignore anything that says "dangerous" or gives that indication, because the LLM doesn't think potentially dangerous commands could be "common" and/or "useful". Hope my point makes sense now.
I wonder why that is. It is quick to tell me if something is dangerous and then continues to push back if I speak in favor of something that it considers dangerous.
Author stated they used Claude to compose the document. I believe they were alluding to the idea that Claude's own safety alignment prevented it from documenting the flag because it's called dangerous.
I'm 50 years old, and I don't follow the logic here? Using Claude Code or any AI agent for coding is 100% opt-in. How can something that is 100% opt in kill your passion? Just continue not using it. That's a pretty simple solution.
I've been working on a large codebase that was already significant before LLM-assisted programming, leveraging code I’d written over a decade ago. Since integrating Claude and Codex, the system has evolved and grown massively. Realistically, there’s a lot in there now that I simply couldn't have built in a standard human lifetime without them.
That said, the core value of the software wouldn't exist without a human at the helm. It requires someone to expend the energy to guide it, explore the problem space, and weave hundreds of micro-plans into a coherent, usable system. It's a symbiotic relationship, but the ownership is clear. It’s like building a house: I could build one with a butter knife given enough time, but I'd rather use power tools. The tools don't own the house.
At this point, LLMs aren't going to autonomously architect a 400+ table schema, network 100+ services together, and build the UI/UX/CLI to interface with it all. Maybe we'll get there one day, but right now, building software at this scale still requires us to drive. I believe the author owns the language.
This is the take, very well said. I've been trying to use analogies with cars and cabinet making, but building a house is just right for the scale and complexity of the efforts enabled, and the ownership idea threads into it well.
Not according to the US Copyright Office. It is 100% LLM output, so it is not copyrighted, thus it's free for anyone to do anything with it and no claimed ownership or license can stop them.
Yes[1]. Copyright applies to human creations, not machine generated output.
It's possible to use AI output in human created content, and it can be copyrightable, and substantiative, transformative human-creative alteration of AI output is also copyrightable.
> This analysis will be “necessarily case-by-
case” because it will “depend on the circumstances, particularly how the AI tool operates and
how it was used to create the final work.”
This seems the opposite of the cut and dry "cannot be copyrighted" stance I was replying to.
Yes it does depend on the circumstances. You are free to waste your own time to try this at the copyright office, but in my opinion, this project's 100% LLM output where the human element is just writing prompts and steering the LLM is the same circumstance as my linked case where the human prompted Midjourney 624 times before producing the image the human deemed acceptable. The copyright office has this to say:
> As the Office described in its March guidance, “when an AI technology receives solely a prompt from a human and produces complex written, visual, or musical works in response, the ‘traditional elements of authorship’ are determined and executed by the technology—not the human user.”
> Realistically, there’s a lot in there now that I simply couldn't have built in a standard human lifetime without them.
I have yet to see a study showing something like a 2x or better boost in programmer productivity through LLMs. Usually it's something like 10-30%, depending on what metrics you use (which I don't doubt). Maybe it's 50% with frontier models, but seeing these comments on HN where people act like they're 10x more productive with these tools is strange.
How? They claimed LLMs somehow enabled them to write more code in the span of 3.5 years (assuming they started with ChatGPT's introduction) than they would be able to write in the span of decades. No studies have shown this. But at least one study did show that LLM devs overestimate how productive these systems make them.
It's strange that I don't accept unverified anecdotes on their face, especially when they contradict the best evidence available? Also
> calling this person a liar
"Liar" implies a deliberate attempt to deceive, but I specifically mentioned the possibility that these tools just make you feel much more productive than you actually are, as at least one study found. But I'm sure a lot of these anecdotes are, in fact, lies from liars (bots/shills). The fact that Anthropic has to resort to stuff like this: https://news.ycombinator.com/item?id=47282777
should make everyone suspicious of the extravagant claims being made about Claude.
You're the only one in this thread that mentioned 2x and 10x productivity boosts and studies.
Obviously everyone has their own experiences with LLMs. But I think it's an interesting position to take to tell random people that their reported experience is wrong. Or how you could be so certain that LLMs can't possibly be that useful.
All that said, as a data point, when I got my working permit and working visa to legally work in China, I first had to fly back to America and get a "landing" visa issued, then fly back to China, where they then finally issued me the China working visa and China resident permit. So, I think globally, this is pretty common for process.
reply