It doesn’t really come as a surprise to me that these companies are struggling to reliably fix issues with software which relies on a central component which is nondeterministic.
I've noticed a lack of product cohesion in general and it does make me wonder if it's a result of dogfooding AI.
For example, chat, cowork and code have no overlap - projects created in one of the modes are not available in another and can't be shared.
As another example, using Claude with one of their hosted environments has a nice integration with GitHub on the desktop, but some of it also requires 'gh' to be installed and authenticated, and you don't have that available without configuring a workaround and sharing a PAT. It doesn't use the GH connector for everything. Switch to remote-control (ideal on Windows/WSL) or local and that deep integration is gone and you're back to prompting the model to commit and push and the UI isn't integrated the same.
Cowork will absolutely blow through your quota for one task but chat and code will give you much more breathing room.
Projects in Code are based on repos whereas in Chat and Cowork they are stateful entities. You can't attach a repo to a cowork project or attach external knowledge to a code project (and maybe you want that because creating a design doc or doing research isn't a programming task or whatever)
Use Claude Code on the CLI and you can't provide inline comments on a plan. There is a technical limitation there I suppose.
The desktop app is very nice and evolving but it's not a single coherent offering even within the same mode of operation. And I think that's something that is easy to do if you're getting AI to build shit in a silo.
Even a distributed or silo'd org chart has some affinity across the hierarchy in order to keep things in overall alignment. You wouldn't expect to use a product suite that is, holistically, not fully compatible with its own ecosystem, even down to not having a single concept of a project. Or requiring a CLI tool in an ephemeral environment that you cannot easily configure.
That's clearly a trade-off that Anthropic have accepted but it makes for a disappointing UX. Which is a shame because Claude Desktop could easily become a hands-off IDE if it nailed things down better.
And the multiple concepts of subscriptions for products, and the idea of MCPs/connectors that arent shared between the different modalities, and the idea of api key vs subscription, and two different inbound websites (claude.ai and claude.com)...
Agreed. I use the Claude desktop app almost every day, and have used Code and Cowork since their respective launch dates, and even I still have a really hard time grokking what each is for. It becomes even more confusing when you enable the (Anthropic-provided) filesystem extension for Chat mode. Anthropic really needs to streamline this.
YES! I thought it was just me being a bit scattered. But uploading an important file to a project only to have it not there because....<garbled answer from Claude> is distracting to say the least. I don't know what I've enabled offhand but I hate having to stop and try to work out why Claude can't reference a file uploaded to the project in a chat within that project. I think they should pause on all the wild aspirations and devote some time to fundamentals.
Add to that that notion mcp works for the chat but not code. now my workflow has docs I comment with others in notion, while the actual work and source of truth is in GitHub.
Need to fall back to codex to keep things in sync, but that's a great opportunity to also make sure I can compare how things run - and it catches a lot of issues with Claude Code and is great at fixing small/medium issues.
Absolutely its dogfooding AI and vibing huge features on the house of cards. Its a fucking mess, and the product design is simultaneously confusing and infuriating. But the product is useful and Im more productive with it than without it now.
Well, the fun part is that the algorithms themselves are deterministic. They are just so afraid of model distillation that they force some randomness on top (and now hide thinking). Arguably for coding, you'd probably want temperature=0, and any variation would be dependent on token input alone.
Meh. Temp 0 means throwing away huge swathes of the information painstakingly acquired through training for minimal benefit, if any. Nondeterminism is a red-herring, the model is still going to be an inscrutable black box with mostly unknowable nonlinear transition boundaries w.r.t. inputs, even if you make it perfectly repeatable. It doesn't protect you from tiny changes in inputs having large changes in outputs _with no explanation as to why_. And in the process you've made the model significantly stupider.
As for distillation... sampling from the temp 1 distribution makes it easier.
Bringing up computational determinism in the early days of AI was absolutely career-limiting. But now, even if the model itself is deterministic for batch size 1, load balancing for MOE routing can make things non-deterministic any larger batch size. Good luck with that guys!
Location: London/UK
Remote: Yes
Willing to relocate: No
Technologies: Experienced Generalist / Go / TypeScript / AWS
Résumé/CV: https://dri.me/C0BM3ArVTLwKv7zVOtAwY1k3tOZGkw
Eml: luke at lukebarton co uk
Product engineer. Coming out of some time off. Open to principal/staff/well-compensated roles. I do my best work in fluid, fuzzy, real-world problem spaces, where things need to be figured out, where creativity and adaptability are valuable traits. System design. XP/DDD. Coaching & Mentoring. Available immediately.
The play was to use AI as an opportunity to quietly insert adverts into a platform full of paying users.
The moment your company starts playing a pauper and enshitificating the products I already pay for, is the moment I stop giving you any money at all. Try it. I’m not paying you money so you can try to make more money from me. Either add value and convince me to pay more, or fuck off.
I don’t mind looking stupid. It’s actually an important part of my identity - I lay my humanity bare. I am of flesh after all.
I’m starting to suspect that it’s making it more difficult for me to land a job though. I don’t know. There’s something about it. It’s almost as if businesses aren’t hiring human beings, but I can’t quite put my finger on it.
This is a distinctly Zed solution - trying to move the agent experience into the editor, rather than just giving the agent an interface with which to control and read from the editor.
Not only do the most popular editors have little-to-no incentive to implement it (they’re more interested in pushing their own first-class implementations, rather than integrating those of others), it’s much more work to integrate the evolving agent experience into the IDE than it would be to provide IDE integration points for the agents themselves.
So, I think this project would have been much more successful if it had been more focussed on keeping the agent and IDE experiences separated but united by the protocol, instead of trying to deeply marry them. But that’s not in line with Zed’s vision and monetization strategy.
It won’t be long before the big players start to release their own cloud-based editors. They’ll be cloud-based because the moat is wider, and they’ll try to move coding to the cloud in the way that Google Workspaces moved docs to the cloud. Probably with huge token discounts to capture people. If you squint, you can already see this starting to happen with Claude Desktop, which runs its agent loop on the cloud (you can tell because skills appear to need to be uploaded).
Notably, Microsoft, with VSCode and GitHub have a web-based editor advantage in this space, but no models.
It's not just Zed, Emacs has has a thriving ACP implementation in agent-shell[0], and allows for some very cool integrations[1]. There are a fair number of other clients[2] as well.
The second half of this is spot on. The now is making IDEs that can integrate with agents, not the other way around. Soon the Claude and Codex will do that for us on their hosts and the argument is it will save sending the context up.
Me being a non-US reader, it’s honestly a bit frustrating to see how often people from the US forget that a large portion of HN readers are from other countries and don’t share the same context for posts like this. It ends up assuming US context as universal.
And don’t get me wrong. I agree that corruption is horrible. I live in a country where corruption was and still is rampant. Political discussions related more closely to, let’s say, AI companies such as OpenAI or Anthropic when it comes to the Pentagon do spark interest, since they are somewhat more directly connected to decisions we can make as tech professionals in other countries, whether for moral, ethical, or practical reasons. That is not really the case for posts like these, however. To your point, I would love to see the tech/hacker community come up with ideas about solving corruption, even if it’s just philosophical discussion.
If my point still doesn’t make sense, imagine seeing posts about corruption cases from any other non-US country being posted on HN. What would you think about those?
When i browse sites based in other countries, i don't complain when there's a lot of talk specific to that country. I didn't know what Eurovision was until last week, but now LMNC is representing the UK. A lot of talk about how it should be boycotted because of Israel. How a bunch of people i never heard of are corrupt. i'm just there to cheer on LMNC, but i get why it's being overshadowed by the current politics.
I don't think the answer to that is to discourage posting US-centric stories about serious political issues. I think the answer is to encourage people from other countries to post theirs, too.
We need more understanding of each other and of each other's situations, not less. The more we tech people bury our heads in the sand about politics—every country's politics—the more likely we are to create more situations like the one we're in today.
In November 2015, solicitor Myles Jackman said that performing a sexual act with a dead animal would not be illegal under the Sexual Offences Act 2003. He stated that possessing a photograph of such an act would be illegal under the Criminal Justice and Immigration Act 2008 if it was produced for pornographic purposes, but not if the purpose was "satire, political commentary or simple grossness".
What? So putting your willy in a pig on camera is totally fine while you do it ironically?
Why and how would any reasonable human being decide what the purpouse of a photograph of sex with animals is?
Have furries been overstepping the law the whole time?
The other day I saw a guy on the train looking at pictures he was actively receiving of a topless woman. He was clearly enjoying it, in his own little world, so I leaned over and said “don’t get scammed buddy”.
His anger brewed for a few minutes and he decided he wanted to fight me, so he menacingly stood up. I remained seated and told him to sit down. He ended up grabbing me by the throat, while no-one around did a thing to stop him.
It’s made me think twice about interacting with random people, tits or no tits. But I doubt I’ll learn anything from it and continue with reckless abandon, because life is mundane otherwise.
Losing your temper when a serious boundary has been crossed is natural and expected. It had a positive outcome in that it stopped your bad behaviour immediately.
> He ended up grabbing me by the throat, while no-one around did a thing to stop him.
The bystander effect is real, but you should also take this opportunity for self-reflection, because in this case, you were the person behaving badly who instigated the situation.
Serious boundary? He put tits in front of my eyes. Am I supposed to remember to keep my eyes pinned to the floor when out in public? What a terrible way you must live.
I’m afraid to say, that if you want a boundary, go home. Otherwise, accept that you’re in public, and people can and will speak to you.
Also, you’ve just justified being violent in response to someone making sounds with their mouth. I bet you’re a calm person to be around, when everyone does what you want.
I just want to reply, a few days after the fact: What you describe would be illegal in my country. Save for me insulting your basic human dignity, i.e. if I were to call you subhuman or something like that (which I'm not, this is an example), what you're describing would be assault and you'd be arrested.
You’ve suggested they live in a bubble, yet your comments suggest that you expect no-one to “invade” your blissful little privacy bubble, and believe it’s okay to strike out and be physically violent to others if they do.
> Go out into the world and behave like the GP. Your apparent mental model of society will collapse quickly.
The problem you’ve got is that I will win. If you permit escalating mouth words to physical violence, I’ll have stabbed you in the face for your mouth words before you’ve gotten very far. Subduing your propensity for physical escalation is in your favour.
This is quite entertaining and I'm glad there are people like you, but you didn't even think it would be inappropriate to comment on a naked picture that someone receives in a private conversation? I don't even think you were supposed to look at his phone.
Yeah, you see, I don’t think you’ve quite understood the art of talking to anyone. It doesn’t happen by staring at the floor and minding your own business. Quite the opposite, mostly.
Despite illusions and every misguided attempt, when in public, you’re not actually in an impenetrable little bubble. And when your bubble bursts, you can laugh, or get angry. I recommend choosing laughter because it’s easier on the eyes.
> Yeah, you see, I don’t think you’ve quite understood the art of talking to anyone
Have you? You're dripping with condescension for everyone who's replied to you so far, in addition to the guy in your anecdote. You've asked one person to "fuck off" when they were polite. Do you think closewith or pingou have enjoyed their interaction with you?
Or is your art of talking to people just meant to amuse you and ignore the feelings of others?
By the way, there is a social convention that we refrain from commenting on what's on people's phones even though we can see it. It's considered an invasion of privacy if we do.
> You've asked one person to "fuck off" when they were polite.
Someone doesn't understand an example when they see one.
> You're dripping with condescension for everyone who's replied to you so far,
Yes
> Or is your art of talking to people just meant to amuse you and ignore the feelings of others?
Every one of you has failed to see what's wrong with expecting people to act the way _you_ want when in public, and been compelled to tell me how _you_ think I should act to make _you_ happy. I can act the way I want, just like the gorilla on the train can act how he wants, and hark: this is the world. One can laugh at it, or one can get angry. I am laughing. You are, what? Being moved by symbols appearing on a screen, which evoked emotions attached to your lack of control over the way _I_ behave, which makes you feel afraid because I could "invade your privacy" -- what does that even mean? Like seriously, what does that matter what my eyes see? Why am I responsible for averting my eyes from shit you're presenting in public? Why should I not pass comment? Did I hurt your feelings? Because you forgot you're in public and didn't keep your shit private enough? Or did you hurt your own feelings through your own unrealistic expectations and your own failure to keep private what you just bandied around in public?
Because I can explain why you shouldn't turn into an ape and physically attack someone. Because physical violence leads to injuries which cannot be undone.
I am so sorry that I saw your phone in public, and that your feelings were so hurt by what my eyes saw - as a failure to stare firmly at the ground. And I'm sorry that my mouth vibrated some air particles that tickled your eardrum in a way that revealed a truth that made you feel uncomfortable. Beat me, I deserve everything you have for me.
What a troubled world you're trying to enforce.
> By the way, there is a social convention that we refrain from commenting on what's on people's phones even though we can see it.
There's a social convention that you don't go around displaying tits on screens that other people might see. So what? Did I turn into an ape and start fighting him? No.
>It's considered an invasion of privacy if we do.
"Invasion"? I barely moved a muscle. On this basis, his pornography invaded my consciousness. Did I turn into an ape and start fighting him? No.
Forgive me for speaking to all of you, for a brief moment, from a place of condescension, but y'all have a fragile expectation of privacy in public, if y'all are gonna turn into gorillas the moment you become aware of your own failure to conceal what you wish you kept private. Privacy is not in harmony with the properties of the physical world when in close proximity to other human beings - and it's not anyone's job to turn their eyes off, or keep their mouth shut, for your pleasure, just as the sky has no job ensuring the weather is in keeping with your desires. You can either fight or allow the world around you. I'm suggesting to you, that you allow it. The world rains on me all the time, and I play with every drop. If you're fighting, you're choosing to fight, and it's not a good look. If you're being "invaded", you're choosing to have something to defend.
I'm declining your invitation to close my eyes, and I'm letting you know my door is open, so come on in, but please, if you wouldn't mind - take your shoes off.
You've written a lot of words to avoid saying a simple thing - you wanted to mess with someone to entertain yourself and it backfired. That's the whole story. The philosophy is window dressing.
> Yeah, you see, I don’t think you’ve quite understood the art of talking to anyone.
Well, mastering the art of talking to anyone involves being able to initiate a conversation with people of many cultures, in many mental states, in many circumstances.
A master of talking to anyone won't begin with a condescending and invasive comment, as they will recognise that beginning a conversation disrespectfully is unlikely to be received warmly.
I would say mastering the art of talking to anyone includes having a good mental model of what the other person thinks or how they would react.
It can be delightful to be surprised, but if you are surprised all the time then I would say something may be wrong in the way you see the world.
Nowhere did I say that people should mind their own business at all time. You cannot imagine a situation where you shouldn't talk to a person? You feel entitled to look at their phone? Is there no social boundary you respect? You are free to not respect them, but you can't hardly be surprised to experience pushback.
Again, I like that people like you exist, I hope I don't come as too aggressive.
I was not interested in his phone until my eyes were drawn to the image of some great big jubbly boobies staring back at me.
I’m sure you’ve encountered the phenomenon of noticing something unusual within your line of sight.
If you’re going to engage with such content in public with such disregard that others’ gaze may be drawn to it, then you deserve to receive whatever wisdom or drivel may spill from those onlookers lips.
And you’re right, there is nothing stopping anyone from talking to me. I accept their intrusion into my space as a peril of being in public. If you climb through my window to speak to me, that is a different matter.
But they made their own bed with that one.
reply