I use chrome primarily when something appears broken in Firefox and i want to test if it’s a ff browser issue. Turns out it’s pretty much never a ff browser issue. Cmd+q
I’ve definitely experienced step jumps down in quality on an almost daily basis. I usually used xhigh. The experience of relying on codex’s outstandingly thorough coding earlier in the year has evaporated for me. I’m seeing incredibly stupid implementations intermittently, and have simply switched to Claude until openai takes the issue seriously. As far as i could tell they haven’t taken it seriously for the several months I’ve been personally seeing it.
I've switched 3 months ago to Codex because Claude got incredibly stupid. 6 months ago vice versa. It doesn't matter if you use Codex or Claude. Both will fuck with you at some point. Though Codex probably less.
How do you mean OpenAI lets you use your own harness? I'm under the impression that a custom harness requires the OpenAI SDK, which requires api tokens rather than plus/pro accounts.
"A little secret. About 5% of our production traffic is on the Pi harness, about another 5% is on OpenCode. Reminder you can use your ChatGPT account in a flourishing set of other tools.
We’ll continue to make Codex awesome, but you have options."
Not just harnesses, you can even use the subscription in CI/CD. That, plus the fact that web chat does not count toward the same limits, is why I think the Codex personal plan is easily 10x the value of Claude Code.
I'm never going back to claude from codex, including for the reasons you mentioned, but it must be said that web chat inference on ChatGPT is magic incantation, and I'm almost certain they're not serving the same models there as in Codex.
Claude web definitely feels like it's the same models behind as in API, with much less extra behavior/layers that make it behave differently.
You must've missed the OpenAI's response to Anthropic forcing everyone to their own harness if they want subscription pricing: official endorsement of custom harnesses like opencode and pi even when used with Codex subscription.
I think they even partnered with opencode or something like that (don't remember).
OpenAI's harness is fully open source[1], and (AFAIK) doesn't come with any kind of signed-build request integrity verification like Claude does. And by that logic, if you're allowed to use their API with a fork of Codex that you yourself compiled, there's nothing stopping you from making some other harness act like such a fork.
And although Codex Desktop is not open source (AFAIK), it does expose CDP and appserver which allowed me to build a Greasemonkey-like plugin system on top of it. It's surprisingly powerful, you can add transcript annotations, programmatically control the side panels, integrate a native-looking account switcher, and so on.
Yup! MIT licensed, do whatever you want, you can also just use it directly with nodejs installed through `npx clankerbend` [0]. The screenshot on the github repo links you to a YouTube demo.
Warning: I use this daily myself for work, but beyond me arguing with it to get the CDP architecture, this was completely vibe-coded. I mostly use vim mode (jump to line, jump to prev/next user message) and the account switcher.
I have noticed this degradation of 5.5 reliability to what, in my experience, I consider Claude-level of reliability since early June.
My journey dealing with this has been transitioning from 5.5 high to 5.5 xhigh to 5.4 high.
5.4 high has been perfectly reliable for me for the last 3 weeks, and I am happy there.
Occasionally, I run some tasks on 5.5 xhigh to check if it has gone back to being 100% perfectly reliable, but, at this point, I am assuming they are just counting on releasing 5.6 rather than dealing with this reliability issue.
I'm on the same journey but I bought a 3090 and put qwen 3.6 27b on it. It covers some things with better reliability. Obviously it doesn't have the breadth of a large model. If that's even a selling point for large models for coding?
i don't ever believe these issues are technical. They're business decisions to downgrade performance because to fix it means $$$$ and you arn't paying them enough.
Contabo, an even cheaper alternative to Hetz, raised prices this month as well by 30-35% as well. Just noting it here because i couldn’t any info elsewhere.
Contabo is still notably cheaper than it was 2 years ago. I just shut down a 2 year old VPS and made a new one because it was ~20% cheaper than it was two years ago, and I also get more CPU and more RAM
Interesting, but still very good pricing compared to the enormous increases we now see at Hetzner (plus the increase before that one). I'm wondering if they have more hardware on stock and/or better means of hardware supply.
I have a few more or less idle VMs running at different providers, and keeping an eye on the european VPS market it seems that many struggled, while contabo is relatively stable. E.g. ovh at times limited the buying process to 1 instance (now it is at 5, not sure what was the default before) and also available locations were limited at one point a few weeks back.
I wonder how aws handles this in bedrock. Do they use Anthropics classifiers? Or their own? Or none? Would their data policing be different in bedrock than their other services?
> Jordan is suspiciously lurching to the extremely high energy end of the light spectrum when we know that the low energy end (comparable to infrasound) doesn’t have negative impacts on us if we can’t detect its presence.
Masley spouts the falsifiable propaganda that any photon (light/emf) below ionizing radiation energy can only cause “heat” and can have no other possible harm effects.
Many science-minded people (though more accurately in this case, billiard-world materialists) have become quite militant defenders of this idea (ostensibly fighting off the hoardes of tinfoil hatters and quantum aquarians sensitive to 5g).
This point is very plausible military industrial propaganda. There were numerous studies with evidence (starting from the 60s) such as - non ionizing radiation (eg hv powerlines) might cause lots of cancer, and it’s weaponized (sub-thermal) usage can microwave the brains of enemy spies. THOSE studies have come out in declassified and leaked docs.
Now we have several plausible and serious theories of mechanism for low-f light disrupting biology that lean into quantum biology. While the iceberg of quantum biology understanding is still in its early decades, the mounting downstream evidence of health and medical issues are established public knowledge.
I’m helping a client move data from dozens of spreadsheet to an aggregate one. The elegantish solution is to use Python, each run takes about 5s and 1 cal of energy. If i hadn’t helped her write the script, she as a non techie could have started with something like this tool, and it’ll take 90s and use 200 cal of energy. The numbers are fudged a bit, but still, how can this be profitable, or ethical? To say nothing of the spontaneous hallucination that sneaks in from time to time, especially when the model gets silently lobotomized.
Or she could have done it manually, and spent orders of magnitude more time and energy.
The scarce resource preventing more people from the ideal solution of using a script in your scenario is you. Most people can’t write a script, so their options are slow and “expensive” manual process, or the 100x as efficient AI. The 1000x as efficient script isn’t an option (well, until the model is good enough to know it should obviously just write the script too).
And time to value is another dimension. In your case finding the right person, scheduling the project, you implementing and delivering at best is a week if not more. With AI they get it in seconds. I may have fudged the numbers but the scale relative gains likely will be same.
I don't think Cook gets enough credit for this [0] - Book: Apple in China. (Author Interview [1])
It's an undisputed damning account of how Cook was used by China to train millions of Chinese electronics manufacturers, managers, and engineers. The US took the most advanced industrial electronics manufacturing tech, and handed the expertise on a silver platter it to a long term strategic enemy.
Frankly, he shouldn't legally have even been able to do this. But that he was, he ought to be crowned one of China's greatest champions of this century.
When people discuss this subject, I wonder what they think the counterfactual world would have looked like. Do people think China could have been kept backwards forever? I notice nobody goes around accusing Maurice Chang of doing this. Or W Edwards Deming.
According to the book, Apple had a special team to prevent divorces among the engineers sent to Asia. That's how long they were over there training.
An argument can be made that Apple nearly singlehandedly advanced China's consumer electronics manufacturing by 20 years, and hastened the decline of U.S. manufacturing while doing it.
China doesn't allow key AI engineers and scientists to go overseas. They literally have exit bans and confiscated passports. The west could have ordered companies like Apple to stop sending engineers, banned companies like Boeing and Rolls Royce from building factories in China, and retained massive wealth, expertise, and national strategic advantage, but allowed it to be pissed away for quarterly profits.
Boeing is a US company. RR is, last time I looked, a UK company. "The West" isn't a coherent political unit.
Besides, this is the exact opposite of the FDI strategy of past decades. How far should the ban on overseas FDI go? Ban on investing in South America? Full capital controls? As you mention, passport confiscation (!) for key nationals? I don't think any of this would have worked for "the west" at any point past about 1970, or even post-WW2.
Airplane and jet engine manufacturing are literally defense industries.
Corporations operate at the discretion of the local government. Corporate charters could be revoked or threatened to be revoked to preserve national interests.
I'm not saying that I agree with or recommend the mechanisms that China uses. I'm saying that the West actually does have alternative mechanisms if it wanted to try.
As it stands, we are now under a ticking clock before China creates competitive, commercial and military airplane industry and begins to massively undercut Airbus and Boeing, and it was our own companies that wound the clock.
> Do people think China could have been kept backwards forever?
its what the vice prez literally said in a speech; you can look it up on youtube...
fwiw, i have no idea if people that say such things are sincere but sending 100's of billions of dollars investment to china doesn't sound like they expected them to take it and turn around into their biggest competitors otherwise they would never have done it imo... but i'm not a billionaire so what do i know ^^y
I think it's more the taking (or at least not growing) skills, jobs, know-how from the US and giving to China, irrespective of if they would have developed on their own in any case. It's not about keeping China down, etc. People like to compare this with Japan in the 1980s, but Japan was indisputably an ally of the US, whereas China has never been.
No, but it's kind of pathetic that the elites in America hallowed out our manufacturing capabilities and condemning tens of millions to abject poverty so their shares can be worth slightly more as a sign of societal sickness.
I think you're overstating your point a bit; I'm not convinced that the tens of millions are that much worse off than their counterparts in poorer parts of China. Was there ever a massive assembly plant for iPhones in the US?
(also, everyone in this subthread seems to be arguing that the US should be at least in part a planned economy with state-directed industry?)
Go visit something called "the rustbelt" (not a term of endearment) and get back to me.
One thing you can always count on about HN are extremely out of touched tech workers that ignore poverty in their country that they helped propagate because "fuck you, I've got mine."
Hopefully it doesn't come back to bite you in the next decade.
There's an element of revisionism to this perspective. It used to be thought that integration with the global economy would gradually bring more alignment with Western values as well.
The ideas was that a rising middle class would demand more say in running the country. That elites would need to become accountable to the people, ideally via democracy. That geopolitical competition would be positive sum.
That idea was minorly present during Clinton and Bush, by the time Obama was in office I think it was clear that was never going to happen. The book covers the period from 2016 on, so long after that neocon dream.
The idea lingered for longer than that. China under Hu Jintao wasn’t exactly friendly to the west, but it was Xi who really set China on its present course to build a multi-polar world, make real noise about reunification with Taiwan, etc.
This new direction didn’t become clear to both sides of the aisle in the US until a year or two into Xi’s tenure. If someone else other than Xi had been chosen, we would likely have a very different China today.
> he shouldn't legally have even been able to do this
What law do you want to write to make it so that knowledge can't be transferred to other countries?
In the mid 20th century, the Green Revolution, partly led by Norman Borlaug, fed billions, and was a huge transfer of knowledge to other countries, and hugely beneficial for all of humanity. (The critiques, well they exist but they are refinements, not critiques that would justify not doing the Green Revolution).
In the case of Apple in China, this was not a one-sided transaction, both sides benefited massively.
Now I do think we should be encouraging the US to compete more, which was what the Biden administration was really good at getting going. But mere ban of commerce, and not providing the industrial policy for US industry to catch up China's excellence, leave us in a world where we are all poorer, both the US and China.
The world is not a zero-sum place, capitalism and technological change are in fact quite positive sum, and when we act like everything is zero-sum we are all worse off.
> What law do you want to write to make it so that knowledge can't be transferred to other countries?
Actually, this is fairly standard via export control laws. When a certain technology is deemed critical, it can be put under export control. When I worked in the semiconductor space, some of the advanced tech we had was subject to these laws. Countries came under different tiers - we could freely discuss the tech with most European countries, but had to be a lot more careful with China and Russia. We couldn't/wouldn't hire Chinese/Russian nationals unless they already had a green card (the legal process was too challenging).
Of course, not saying electronics manufacturing should have been in that bucket. But there is plenty of precedence.
Thanks, that seems like a reasonable way to do it, if it were to be done, though the types of manufacturing would have to be very specific.
We could perhaps outsource mass precision manufacturing of aluminum iphone and macbook cases to Germany, or try to build up the industry over time in the US that would enable such manufacturing. But such multi-year delays that are kinda-sorta in the interest of a nation but not at all in the immediate interest of a private company and US consumers, imposed by politicians that have not bothered to dive deep into the issue but are instead responding to half-informed populist revolt, seem like a dangerous path.
If something like that were to be done, a carrot approach is far more likely to yield better outcomes than the stick approach of export controls, IMHO.
The book's thesis is frankly unwarranted Apple glazing. Asian Tigers trained PRC decades before Apple. Muh designed in California and manufactured in China was always Cupertino hands Chinese factory specs and Chinese engineers and workers building it into reality. US manufacturing already in the shits by then, the idea that Apple substantively "elevated" PRC manufacturing is huffing copium. PRC process engineering was always the hardest part of the equation that somehow gets credited to US. PRC manufacturing made Apple, not the other way around.
The reality is PRC already had magnitude more high end manufacturing talent by the time Apple entered PRC already and they're the ones that made Apple scribbles at scale possible. The stories of PRC manufacturers having stupendously fast line turn arounds, making changes in hours should disabuse the notion they needed learning, when they already knew how to execute at scale. Apple's derisked manufacturing in other countries still can't do this, PRC was doing this on day one - see overnight turnaround to retool iPhone line from plastic to glass screen 20 years ago. Apple went to PRC because PRC already had competently trained manufacturing workforce, and only one that can operate at speed + scale. Apple buying a few 1000 CNC machines doesn't tip the balance remotely in Apple's favour - if sector moved towards CNC and tighter tolerances, PRC industry would have simply followed, Apple $$$ is nice, but PRC doesn't need Apple $$$ - capex is not a bottleneck for their system. And Apple would have never push enough goods and make $$$ without PRC.
Cute. That is the commenter’s whole point about monopolies. Google is on record making their product worse to squeeze revenue. We’ve been living in the enshitification economy.
Sure, until their "smart filters" start considering GCP-hosted websites as pre-verified and small self-hosted websites as malicious. You know, like they have been doing with email?
Chrome is big enough that a website owner can't afford a false positive on their malware list, just like they can't afford to have all their email end up in spam for all Gmail users.
Due to their near-monopoly Google also has no incentive to avoid adding false positives to their blocklist - provided they don't accidentally block high-profile targets. And if a CxO is screaming over your shoulder that your website has been blocked, arguments about "false positives" aren't very compelling: they'll just demand you move off the "shitty basement provider" and switch to "proper hosting, like the Google Cloud"...
> We’ve been living in the enshitification economy.
that whiny bullshit about somebody elses website? you dont have to rely on a website or app. either you need their monopoly because you cant do it yourself, or you have options.... in both cases the whining is not needed
reply