HackerLangs
TopNewTrendsCommentsPastAskShowJobs

wwind123

51 karmajoined vor 29 Tagen

comments

wwind123
·vor 2 Minuten·discuss
In every company I've worked at (admittedly all with >1000 employees), there is always some text in the offer or onboarding documents that clearly state that you should not bring any previous employer's trade secret to this company.

I wonder whether OpenAI's offer letter or onboarding document also says such a thing.
wwind123
·vor 22 Stunden·discuss
Ha, finally found time to get it working. Yeah it's more hassle than Claude Code since this needs a separate daemon server, but not very bad.

1. Install another copy of codex in a special dir on the Linux machine:

  $ curl -fsSL https://chatgpt.com/codex/install.sh | sh
2. Run codex remote-control from that special dir to start and pair the daemon:

  $ ~/.codex/packages/standalone/current/codex remote-control start

  $ ~/.codex/packages/standalone/current/codex remote-control pair
3. On the phone, open ChatGPT app, Choose Remote, then pair it with the code printed above.

4. Voila! The codex sessions running on the Linux machine now show up on the phone!
wwind123
·gestern·discuss
Hmm, I don't have a desktop computer. I prefer my laptop be used for other purposes, and can sleep when not in use, instead of running a coding agent 24x7. That's why I prefer running coding agents in the cloud.
wwind123
·gestern·discuss
Hmm, thanks. Didn't know about this. But looks like a bunch of hassle to set it up?
wwind123
·gestern·discuss
I've been using Claude Code, Codex, Gemini (now Antigravity) at the same time for half year now, ever since I dipped my toe into agentic coding. I'd say in general Claude Code and Codex are equally powerful, Gemini is lagging behind.

One thing I appreciate with Codex is, OpenAI nowadays sometimes just gives you quota resets you can bank, so when you use up weekly quota before the week ends, you could just reset the quota, to continue using Codex. I've been much less anxious about Codex quota because of this perk. I just used one reset in the bank yesterday, and still have 3 resets left. Whereas with Claude, when you've used 95% quota 3 days before the week ends, you'd be much more anxious.

On the other hand, Claude Code's /remote-control mechanism is extremely helpful when I am running it in the cloud and wants to monitor it or control it on my phone. Codex currently doesn't support this kind of usage. Codex only allows you to use your phone to connect to a session on your desktop, not in the cloud.
wwind123
·vorgestern·discuss
On one hand, I understand that some old code is hard to delete because it's hard to detangle a lot of the legacy dependency. On the other hand, too much useless old code existing in the code base by itself could become a big maintenance burden for both humans and AI. In some cases at some point it might become more economical to just invest a bunch of resource to detangle the dependencies to be able to remove the old code.
wwind123
·vorgestern·discuss
Half year ago I tried to use Codex, Claude and Gemini build the same scripts to automate various things on my machine. Claude was the clear winner back then, making the most reasonable assumptions, presenting results in the easiest-to-read format, writing runnable script with minimum dependency. Half year later I think Codex and Claude models have both advanced a lot, but Gemini is still lackluster. Gemini could catch problems when reviewing Claude/Codex's design plans and code, but it's hard to make Gemini make complex plans or implement complex code by itself.
wwind123
·vorgestern·discuss
I think LLM-driven agentic flow is useful in some cases, but in many other cases, deterministic code would be indeed much safer and more reliable. In the ideal world, people can build a proof-of-concept with LLM agentic flow quickly, and if it seems to work like expected, then they should use LLM to convert that agentic flow to deterministic code!
wwind123
·vor 5 Tagen·discuss
Famine could be caused by drought or flood or other numerous things. When the country can't produce enough food, its people would need to rely on food from outside.
wwind123
·vor 5 Tagen·discuss
It's about how to benefit the entire human species, or at least to reduce human suffering across the board. If there is famine in North Korea, then the surplus food from the world flowing into there won't be an issue right?
wwind123
·vor 5 Tagen·discuss
I agree UN sounds like a good organization to help distribute the wealth created by AI to the world. But this idea won't be considered by the current U.S. administration. In that case what other countries can do is probably to tax the AI companies at rates higher than regular companies.
wwind123
·vor 5 Tagen·discuss
That's a great question. Some form of union has already started in some companies, as far as I know. But not many employees have joined those unions. Probably because most employees have high income and don't really feel like they need collective bargaining power, compared to other low-income laborers.
wwind123
·vor 6 Tagen·discuss
I can feel for both camps.

Some of my published work is pirated heavily. That's not my main income source, so I just shrug and let it go. If anything, I'm probably happy that people are reading my work. Especially if it's people that can't afford it, I'm glad they enjoy my work -- those books got pretty high reader ratings, and it seems to me many readers are actually reading the pirated version.

But I do have friends that depend on this income source, and fighting piracy has become a part of their day job. It's not a fun thing to do, they'd rather spend time working on their next story, but they still have to do this everyday. I feel for them.
wwind123
·vor 7 Tagen·discuss
I make Claude, Codex and Gemini review each other's design plan and implementation. Each always found a lot of things the others missed...until Fable 5 came out. Whatever plan or code Fable 5 comes up with, now it's very hard for Codex and Gemini to find any serious hole in it.
wwind123
·vor 7 Tagen·discuss
For some of the things I buy, I prefer just doing online, because it's often not easy to figure out where one particular thing is in the store. But when I have time, I do enjoy browsing in the store and discovering new things to buy that I never thought of before.

Home delivery in the U.S. is expensive because the labor cost is expensive, and because population is generally more spread out geographically. Cities in China and India have home delivery with much lower cost. But with the advance of robot technology, maybe not too far in future home delivery in U.S. could have lower cost too.
wwind123
·vor 7 Tagen·discuss
If a notification is dismissed on iphone, there's indeed no central UI to see it again on the phone. That's a sad state of iphone. Many people have asked, but Apple just doesn't care enough to do it. Now I hope this kind of high-profile security incidents could nudge Apple towards taking action.
wwind123
·vor 8 Tagen·discuss
I used to hate phones without the headphone jacket too, even though my headphone lines always needed some detangling out of my pocket when I needed them. But then I tried a pair of Bluetooth earbuds (two earbuds connected with a plastic band to hang on your neck), and actually fell in love. No need to detangle lines, and when I don't listen to things I could just take down the earbuds but leave the plastic band on my neck. Not easy to lose, compared to the completely wireless earbuds. Batteries are in one or both ends of the plastic band, so one charge could last a long time. The only downside is it takes up more space than both wired headphones and wireless earbuds when you put it in a bag, because the plastic band is not that flexible. But that's a cost I am willing to pay.
wwind123
·vor 9 Tagen·discuss
In my experience, for more mechanical refactoring work (like splitting a big source code file into multiple smaller ones), GPT 5.5 runs way faster than any of the Claude models. But for other tasks that require deeper reasoning, it's not that clear who is the winner.
wwind123
·vor 9 Tagen·discuss
Who knows. Maybe Mythos 5 already found a hole in SHA256, so this won't be too hard. :)
wwind123
·vor 9 Tagen·discuss
This kind of approach would generally still need human guidance, otherwise these models might get stuck in weird niche corners of the problem space that would not be relevant to any real world project.