wwind123

I think it's just a common practice to do it this way in the industry. May not mean these companies are intentionally hiding something at this point of time.

A side note: the article starts with "If England has Shakespeare, Spain has Cervantes, Italy has Dante, and Russia has Pushkin, then who do we have?" but does not mention China: usually Li Bai (李白) and Du Fu (杜甫) from Tang Dynasty (1300 years ago) are regarded the best poets in the history of China. Li Bai is nicknamed Immortal of Poetry (诗仙), while Du Fu is nicknamed the Saint of Poetry (诗圣). Most scholars like Du Fu better because his poems' use of all the connotative overtones, but most regular people like Li Bai better because his poems are easier to understand.

A typical suggestion is to make the agent create or update a .md file once in a while, so the agent would remember the new important things that have shown up since the last update. The problem is, how would the agent know which things are really important. If it knows that well, then /compact should work well too...

Why not try a real database like Postgres? It's not as light-weight, but when operations get complicated, real databases are much easier to work with. I had a website that started with SQLLite, but when it got complicated enough, I spent two days to migrate the whole thing to Postgres. With current LLM coding agents, it's not that hard.

Also...allow people to work from home more. During the Covid pandemic, most white-collar employees work from home, and the commute and the traffic is usually not a big problem. But now more and more companies ask employees to go back to office, and traffic jam is becoming a headache again.

Yeah, some work from Google has had an outsize impact on the entire industry. Won't be surprising if they eventually get a nod from the Turing Award. Including the main authors of the Transformer work for driving the LLM revolution, and Jeff Dean and Sanjay Ghemawat for driving the big data movement.

I still remember back in 2005 when I just joined a company, a coworker was quipping Google is not a real elite company, because it doesn't even have a Turing Award winner. I showed him the news that Vint Cerf joined Google recently.

To be honest, I'm more worried about another side of the problem.

LLM's are good at learning from whatever humans have posted online. But with the agentic workflows getting more popular, more and more problems those AI agents figure out are not posted online, and the next time another agent running into the same problems they would have to figure it out from the scratch again. It'd be nice if there's a mechanism these agents would share the lessons they learn with each other, which could save a lot of trials and errors and wasted tokens. Humans share knowledge online. AI agents should be able to do so too. The moltbook thing from half year ago could have this potential, but too bad it's flooded by spams.

Of course, to make this AI knowledge sharing truly work, there may need to be a peer-review mechanism to ensure the knowledge being shared is truthful, reliable, non-trivial etc. That can probably be all worked out if somebody (or AI agent) really put effort into it.

I think a main worry is that, this AI wave is quite different from past technological revolutions in that, this wave is happening so fast, the speed that humans learn new skills and master new jobs would lag more and more behind the speed that machines replace humans in those jobs. Without societal or legal constraints, capital chasing the max efficiency and profit would just replace humans with machines whenever machine cost comes down below humans.

A few years ago I listened to a seminar where a few real professional doctors discussed the hospital scenes in movies or TV shows. They mentioned that those dramatic and chaotic operation room scenes where the doctor yells commands with a loud voice look so fake to them. In a real operation room, everyone (including the doctor and the nurses) is highly trained, works in tandem calmly and efficiently -- there's never a need to raise voice.

In every company I've worked at (all with >1000 employees), there is always some text in the offer or onboarding documents clearly stating that you should not bring any previous employer's trade secret or intellectual property to this company.

I wonder whether Open AI's offer letter or onboarding document also says such a thing.

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

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

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

4. Voila! The codex sessions running on the Linux machine now show up on the phone!

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.

Hmm, thanks. Didn't know about this. But looks like a bunch of hassle to set it up?

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.

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.

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.

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!

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.

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?

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.

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.

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.

I kind of understand your frustration about the ad-hoc nature of the Inflation theory. When I was younger I believed the truth must be simple and beautiful - if a theory is complex and ugly then it's not the real truth. But as I get older, now I think the universe is what it is. Things may or may not have a simple or elegant explanation. Theories exist to explain things and make predictions. As long they serve both purposes well, then they are the working theories.

It's not a brand new project, but a project I've been working on and off for the last half year. I was trying to add a major feature which required some big refactoring of the current structure of the code. With the previous models I'd expect many rounds of reviews and debates between the AI agents. But with Fable 5, there's basically no debate, Codex and Gemini basically approved immediately. :)

With modern cryptography techniques, Apple could certainly do it if they cared enough. I guess the potential benefit doesn't justify the potential effort and cost related to the change, from Apple management point of view.

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.

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.

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.

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.