This is precisely what happens in the Apple TV series “For All Mankind” an I think it’s a pretty realistic take on how future lunar and Martian settlements would work (either everyone cooperates or everyone is cooked)
Yeah, I can’t recommend gpt-5.3-codex enough, it’s great! I’ve been using it with the new macOS app and I’m impressed. I’ve always been a Claude Code guy and I find myself using codex more and more. Opus is still much nicer explaining issues and walking me through implementations but codex is faster (even with xhigh effort) and gets the job done 95% of the time.
I was spending unholy amounts of money and tokens (subsidized cloud credits tho) forcing Opus for everything but I’m very happy with this new setup. I’ve also experimented with OpenCode and their Zen subscription to test Kimi K2.5 an similar models and they also seem like a very good alternative for some tasks.
What I cannot stand tho is using sonnet directly (it’s fine as a subagent), I’ve found it to be hard to control and doesn’t follow detailed instructions.
Out of curiosity, what’s your flow? Do you have codex write plans to markdown files? Just chat? What languages or frameworks do you use?
I’m an avid cursor user (with opus), and have been trying alternatives recently. Codex has been an immense letdown. I think I was too spoiled by cursor’s UX and internal planning prompt.
It’s incredibly slow, produces terribly verbose and over-complicated code (unless I use high or xhigh, which are even slower), and missed a lot of details. Python/django and react frontend.
For the first time I felt like I could relate to those people who say it doesn’t make them faster,” because they have to keep fixing the agent’s shot, never felt that with opus 4.5 and 4.6 and cursor
Codex cli is a very performant cli though, better than any other cli code assistant I've used.
I mean does it matter what code it's producing? If it renders and functions just use it. I think it's better to take the L on verbose code and optimizing the really ugly bits by hand in a few minutes than be kneecapped every 5 hour by limits and constant pleas to shift to Sonnet.
This is pretty cool! I'm not sure how you'd make a business out of it, but I can definitely see myself using it to justify some decisions on my day to day stuff.
I'm also a sucker for serif fonts so points for that.
Yeah, I only just yesterday got it to the point where people can create their own arguments. I was just using it to check my own assumptions on why I have such a complicated "end-of-month finances" list of things to do. :) But I also like the idea of using it for political arguments or even fun stuff like mystery-solving.
Speaking of politics, I've always thought it would be fun to see the different assumptions made by two "sides". My expectation is that both sides gradually accumulate more and more extreme, and often more and more ridiculous, assumptions to distinguish their side from the other.
Eventually, everyone's downstream beliefs are resting on extreme assumptions that nobody actually believes! Which makes moderate well-reasoned arguments from "the other side" much more threatening than extreme positions that can be passed off as lunacy, naivete, or evil.
Yeah... so far, I have found that trying to fully justify a political conclusion has a way of moderating the conclusion. But it's still possible to arrive at very different well-reasoned conclusions just from different axiomatic personal values.
I wanted to add more value to this comment about monetisation - regardless if that's doable or not, it's an extremely cool project!!
What if you could sell the data for each argument? That might be valuable to LLM labs, because then you can essentially guarantee that every single argument you provide is human checked, and you could accumulate a large DB of those. Of course you'll never be able to capture every single argument possible, but it's rather a mechanism that would allow incremental improvement with time. But codifying logic and natural language is a very nice idea.
Hosted OpenClaw, one click and you get a full agent with configurable skills, channels and the whole thing, all running in its own sandbox.
I love OpenClaw but setting it up is a pain: VPS, Docker, API keys in plaintext, security patches... So I’ve spent the last couple weeks building a hosted version that handles all of that. Each user gets their own isolated environment on Cloudflare Workers.
Still doing some testing with friends before opening signups but planning to launch properly this week.
Would love feedback on the landing page in the meantime!
Yeah, it’s pretty much ready, I’m just squashing a few last bugs. Launching this week, trying to move fast for exactly that reason.
Good call on the examples, I’ll add some that show off browser automation and more complex workflows.
Memory at launch is what’s baked into OpenClaw, but I’m planning to upgrade it to vectors + a continuously updated doc shortly after (similar to what Claude Web does)
If you want early access I’d be happy to get you set up personally, just shoot me an email at ramon <at> agentmode.co
You wouldn’t even believe the stuff I’ve heard in “startup” and “innovation” spaces about regulation and stuff like government grants.
I usually hear the “we [europe] have some of the brightest minds, we can do anything” and sure, granted, but that’s not the issue and it has never been. Why would those bright minds want to build something in a place that’s so obviously against the very same idea of free competition? Of course they don’t, those who can just flee and those who can’t usually end up building some useless grant-ware in an endless cycle. That’s not to say that we don’t have great startups and entrepreneurs, we do, but I find myself fighting every day against a system that’s built for the state to decide what, when and how citizens must innovate (and live).
That’s crazy cheap, I pay close to 400€ (!!!) monthly for Tirzepatide (GLP-1) and close to 50€ for Lisdexamfetamine (ADHD) in Spain. Truth be told, the ADHD meds are covered by the Social Security health insurance or I’d be paying double that, but I don’t think GLP-1s will ever be covered here.
I keep working on Rigel.sh as a side project (a next-gen remote desktop solution with no latency and online-first for teams and hobbyists) but I wanted to write a Redis-compatible cache but using JS instead of Lua for scripting so I’m also working on that.
It doesn’t seem to be very good, but don’t worry, just keep prompting Claude and I’m sure you’ll get it sorted out.
Jokes aside, it’s cool but it’s not useful if it’s the first time I visit and I see I have 10+ past visits from all around the world… obviously this is not reliable and I wouldn’t use it for anything, much less anything serious.
Why actually try to understand a problem space? Far easier to prompt a turd into existence, polish it up with a cliché marketing page, and collect public validation from your fellow “hackers”
Thanks for checking it out! We’ve identified the root cause of the inaccurate visit counts you saw and have now fixed the issue — the accuracy of DevicePrint should be much better now. If you have any remaining odd results, let us know!
“Hey Claude, users are noticing my product is fundamentally broken. Please shuffle some code, increase the confidence label to 99.6%, and spam the HN thread claiming I identified the root cause of a bug. Frame it as a small edge case. Do not under any circumstances empirically validate the supposed fix.”
Snark aside, I still see 9 previous visits from various countries, down from 900+ previously. It does correctly identify me as being in incognito mode, but if I switch to a normal tab I see a completely different set of previous visits.
reply