Hacker Newsnew | past | comments | ask | show | jobs | submit | laborcontract's commentslogin

It's already out.

Can you explain how to use it? I’ve tried asking it to do “create 3 files using multiple sub agents” and other similar wording. It never works.

Is it in the main Codex build? There doesn’t seem to be an experiment for it.

https://github.com/openai/codex/issues/2604


Codex Monitor seems like an Antigravity Agent Manager clone. It came out after, too.

Bunch of the features u listed were already in the codex extension too. False outrage it its finest.


I have both Codex Monitor and this new Codex app open side by side right now; aside from the theme, I struggle to tell them apart. Antigravity's Agent Manager is obviously different, but these two are twins.

I have a very hard time getting worked up over this. There are a ton of entrants in this category, they all generally look the same. Cribbing features seems par for the course.

Antigravity is a white labeled $2B pork of Windsurf, so it really starts there, but maybe someone knows what windsurf derived from to keep the chain going?

cursor?

from what I can tell, the people behind windsurf were at it first

oh, codeium? that was them?

Maybe github copilot then


was langchain before copilot?

Obviously horrendous but why isn’t this person monitoring his site?

Also, why do people use vercel nowadays? I’m sure there are reasons, but I moved over to railway (you can insert alternative provider here) and I no long f* around trying to fix page load time due to cold starts, I have predictable pricing, and my sites on railway are fast so much faster. Plus, if cost is a factor, railway offers serverless. It’s not as shiny as vercel, but nextjs works perfectly on it.

It astounds me that vercel has positioned themselves as a sanctuary city for normies and yet, the city is littered with landmines and booby traps.


Don’t underestimate the amount of people who don’t care how their companies money is spent.

counterpoint:

- The readme is two lines and has six words, one of which is a typo.

- Claude would never commit a node_modules folder unless coerced.

It’s disrespectful to casually call things AI-generated. I wish people would do it less unless they have 1) proof and 2) a meaningful reason for it.


I was in the market looking for some fun iOS games, things that I could play casually, pick up in a moment, load quickly, and not be burdened by the ridiculousness of modern gameplay and incentive mechanics. To my surprise, it was very hard. I couldn’t find anything. This is exactly what I’m looking for.

Apple has had some good chips, but is not a high priority for game developers. If you are on ARM, than the emulation performance hit will heavily limit what kind of games are playable.

https://github.com/86Box/86Box/releases

https://github.com/Moonif/MacBox/releases

Note, Steam will also natively run on many Apple ARM systems now, but again the compatibility of game titles will be sparse. Have fun =3


Google AI overviews are often bad, yes, but why is youtube as a source necessarily a bad thing? Are these researchers doctors? A close relative is a practicing surgeon and a professor in his field. He watches youtube videos of surgeries practically every day. Doctors from every field well understand that YT is a great way to share their work and discuss w/ others.

Before we get too worked up about the results, just look at the source. It's a SERP ranking aggregator (not linking to them to give them free marketing) that's analyzing only the domains, not the credibility of the content itself.

This report is a nothingburger.


> A close relative is a practicing surgeon and a professor in his field. He watches youtube videos of surgeries practically every day.

A professor in the field can probably go "ok this video is bullshit" a couple minutes in if it's wrong. They can identify a bad surgeon, a dangerous technique, or an edge case that may not be covered.

You and I cannot. Basically, the same problem the general public has with phishing, but even more devastating potential consequences.


The same can be said for average "medical sites" the Google search gives you anyway.

It's a lot easier for me to assess the Mayo Clinic's website being legitimate than an individual YouTuber's channel.

I don't think anyone is talking about "medical sites" but rather medical sites. Indeed "medical sites" are no better than unvetted youtube videos created by "experts".

That said, if (hypothetically) gemini were citing only videos posted by professional physicians or perhaps videos uploaded to the channel of a medical school that would be fine. The present situation is similar to an LLM generating lots of citations to vixra.


Your comment doesn't address my point. The same criticism applies to any medium.

The point is you can't say "an expert finds x useful in their field y" and expect it to always mean "any random idiot will find x useful in field y".

Imagine going onto youtube and finding a video of yourself being operated on lol

This applies to both physical and digital goods. I've tried to think hard about how to keep my digital life in order in a way that my kids will be understand to make some sense of. I'm not there yet but I am mindful of it.

Trying to explain the sentimental value of your belongings to others is like trying to explain a dream.


I'm not a hoarder, but my dad is.

I have a couple of items from my dead grandparents, and it's a connection.

It's a tangible connection that feels more real than something intangible like memories.

As for my dad though, I have no idea. He recognizes that it's a problem, but can't stop. It's stuff like plastic ship models, or stuff he wants to buy on eBay - postcards from defunct airlines that he used to fly on.


That makes sense, but don't you think hoarding muddies the signal? Do you know what of your father's you'd want to keep of his hoarded goods?

There is nothing that he has hoarded that I want to keep. I have told him that.

I have told him that he has so much stuff, that it would be impossible for me to recognize the $1,000 model boxes from the worthless model boxes, and that when he dies, I'm just going to have to wholesale the lot for probably a penny on the dollar.

I told him him that the people who will pay money for plastic model kits are the same age as him, and if they all die around the same time or before him, there will be no one to buy the model kits.


I've had the same discussion with my parents. They wanted me to go through their home and mark down everything I want. I don't want any of it and frankly dealing with a full house of stuff after they die is something I dread. I wouldn't even know where to start. Are there companies you can hire that will take care of everything?

Australian here. I paid a garbage removal company to basically empty a house. Their qebsite called it "estate cleanup". It took a whole day for a team with crowbars to smash up every piece of furniture and load it in a truck and take it.

People take this offensively and insist someone must have wanted an old chest of drawers or something if only put it on facebook marketplace and work with interested parties and assist with them obtaining it - but those people dont realise how much they are asking of someone who is dealing with loss.


Yes, they’re called clean out companies. They’ll swoop in and put everything in a dumpster. You can engage an auction house-+cleanout company if you think they have anything worth selling.

The only people who want to pick through a hoard to find the "good stuff" is other hoarders and flippers.

Also, 90% of the time that the act of hoarding ruins the objects hoarded so everything becomes trash anyways.


> 90% of the time that the act of hording ruins the objects horded.

I can also attest to this.


> don't you think hoarding muddies the signal?

Yes, which I am thankful now that I only have a couple of items and haven't had to make the choice of what to keep or not.


Thank you for sharing.

If you're remotely interested in this type of stuff then scan papers arxiv[0] and you'll start to see patterns emerge. This article is awful from a readability standpoint and from an "does this author give me the impression they know what they're talking about" impression.

But scrap that, it's better just thinking about agent patterns from scratch. It's a green field and, unless you consider yourself profoundly uncreative, the process of thinking through agent coordination is going to yield much greater benefit than eating ideas about patterns through a tube.

0: https://arxiv.org/search/?query=agent+architecture&searchtyp...


As someone who has found skills useful, seeing skills like this[0] raises the same question about (a subset of) skills as did MCP: why not just have the agent run ‘tool --help’?

https://skills.sh/ubie-inc/agent-skills/codex


The point is for the agent to have an index of available skills so that it can decide autonomously if it needs to load one.

https://zzbbyy.substack.com/p/what-are-skills

In my experience it doesn’t work too well with codex, but I expect llm providers to train them on that use case and improve the situation soon.


Not all flags will be relevant, you can trim down and contextualise the instructions for your specific project.

I totally agree with you. Running a cheapo mac mini with full permissions with fully tracked code and no other files of importance is so liberating. Pair that with tailscale, and being able to ssh/screen control at any time, as well as access my dev deployments remotely. :chefs kiss:


why a mac mini rather than a cloud vps


I use a new Ryzen based mini PC instead of Mac mini, but the reasoning is the same. For the amount of compute/memory it pays for itself in less than a year, and the lower latency for ssh/dev servers is nice too.

One less company to give your code to.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: