movedx01

> We don't have a formal process for this. Nobody on the team keeps a complete mental model of Claude Code in their head, and we don't think anyone needs to.

Nobody on the team keeps the mental model of Claude Code as it is today in their head, so nobody on the team is able to reason and decide about Claude Code in the future, is that right? So no long term architecture strategy can exist as no current architecture understanding exists. While it seemingly does work for a system which is a TUI, would the same be true for a complex distributed system today?

The one that Claude Agent SDK uses?

Kind of reminds me of this more recent paper: https://arxiv.org/html/2602.02459v1 Different use case and implementation, but a similar idea. In this case applied to sharing last state(not the whole KV cache) from big brain model running in the cloud with a smaller/dumber model running on-device in a robot, in a latancy-aware way.

Buying a license for a stock photo is paying someone who has put the effort.

Well, okay, I am not sure how much effort goes into creating your typical stock photo, probably not a lot, just still more than 0 effort it takes for the AI to generate it.

And yes, I see difference between an automated system flooding the web with AI generated "news" in disguise vs a niche blogger using AI to iterate on an image with hand crafted prompts. Labels are not perfect, just better than nothing.

Probably not critical, just helpful to be able to understand where the source is willing to cut corners. Helps me understand if the given content source values are aligned with mine without risking wasting time to ingest slop just to come to the same conclusion.

The same way I look at food labels to support local produce and those who don't try to trick me into thinking I am consuming something it's really not.

I personally wouldn't care for AI usage in icons, I don't put a lot of attention to them. Someone else might.

Adoption absolutely did happen, I am not questioning that. What I am questioning is whether it really is the revolution the people selling it want us to believe it is.

Just to disclose: I use those every day, I have two Claude Max 20 subscription myself. I am still in doubt how much more productive professionally it made me. I am having a ton of fun in exploring stuff I never would have otherwise though.

I define software quality in my daily life by this: how often I am delighted by the piece of software I use. Those moment are rare and far between, and it's not getting any better.

Slapping an explicit "I did not put effort into this" label on slop content is not censorship, its quite opposite, it lets people filter out the noise. No human can hope to be able to do this on their own at the scale GPUs can pump out tokens.

Authentic voices are today being drowned in waves upon waves of AI slop spam. This is not quite censorship but the end effect is similar - human voice cannot be heard. Just this time not because someone stopped the human from talking, but because they as shouting 1000x louder instead, at pennies on the dollar it costs to create something truly valuable.

The lullaby for the Gen AI era exists, but its for CEOs and it is being played in management meetings, it's main theme is about maximizing EBITDA.

The defensive mechanisms kick in because even though more code is generated than ever, we are not observing an equivalent rise in software quality or usefulness, some would perhaps argue it's even opposite.

If gen ai for code was really what it is being sold as it would all be obvious to everyone, we would be seeing better software all around us everywhere and posts such as the one here would just be laughed off, delusional, but they are not.

The code explosion did happen, the value of software this code makes - not yet. Not to say it won't, its just not here right now, and it never happening is still a possible outcome.

Yes, they basically pioneered lootboxes, they shaped and scaled microtransaction economy around randomized outcome purchases under disguise of gaming and then slapped a marketplace on top of it(to take even further cut %% nonetheless).

> I can't even picture gaben with a wispy moustache to twist evilly.

Add a 500m gigayacht to the picture, maybe it will make it easier. Or a fleet.

What ethics do you see being superior in the company known for exposing underages to gambling? The anyone elses must be really bad guys. Yes I like my deck and I respect their contributions to gaming on linux, but Valve is no saint.

> "addictive design of the algorithms"

Any self improving loop where the user is not in control, thats it.

If I subscribe to A and get more of A - thats fine.

If the algorithm detects that I spend 0.5 second longer on average looking at content with feature A and so decides to show me more of A - thats bad. At most it might be allowed to ask me if I want to subscribe to more of things with explicitly defined feature A, but even that assumes we are fine with collection of behavioural data like this in the first place and so it is a stretch already.

Transparency and control is what makes the difference here in my opinion.

Why not restrict the addictive design of the algorithms instead? No need to blanket ban social media access if the social media cannot optimize to steal every last inch of their attention. Anything on the feed becomes opt-in only and no engagement data coming from the user or from the outside can be used to optimize it, thats it. Control is back in the hands of the content consumer, parental restrictions become trivial, no black box algorithm deciding what bubbles up and what gets buried deep down.

More likely implying they are not being compensated fairly.

From what I've seen trying to play around with Claude Tag, it uses shared credentials. You set it up with Github org access, add it to public channel, and all random people in that channel can now ask it to do stuff with code. It's opposite of what Cursor does - each Slack member needing to connect their own Github account. It's a security nightmare basically.

nice, cranker

Nice! I had a similar idea and a prototype based on Temporal. Wondering, what are you using under the hood to runs the workflows?

> So why are you looking at this code?

Because I am getting the call to fix it when it breaks. I don't have to fix assembly by hand because compilers are deterministic and I have maybe encountered a single real compiler bug in my whole career. Compilers have earned my trust. LLMs are eroding that trust more and more every day I work with them. I encounter LLM-created problems in basically every single diff they surface for me, just over the months the diffs are getting bigger and harder to review and uncover the problems.

LLMs are not an abstraction(not even a bad one) because by design what they are doing is disambiguation. Compilers are not doing that, what you put IN the compiler has to be unambiguous in the first place.

Disambiguation is not a functionality of an abstraction layer. A good abstraction layer is the one I don't have to understand and can trust, if I have to understand its inner workings to use it it ceases to be an abstraction. Except with LLMs you can't even do that, they are a black box you can have no hope of understanding.

And it is not to say LLMs and agentic coding tools are not useful, they are absolutely very useful. They are just not an abstraction layer.

If someone is trying to bend the rules of my passively managed index fund to their will, are they trying to actively manage my passively managed index ETF ?

AI studio added it recently, Vertex not.

> coming soon

The developers are literally on the bleeding edge here, it might be the most developed of the AI use cases right now. The most advanced tooling for LLMs revolves around SWE work, there are multiple prolific benchmarks that the labs are actively targeting in this area, and new ones are being built, whole product categories being spawned, software companies bleeding money for tokens.

It's the other professions that are to follow once the training data is in place to go reach for their livelihoods. SWEs got the early taste of what is coming. And the blender news is exactly that.

Average is only a tombstone of someone having failed to do better. And settling for average means pulling down.

When it comes to bs dashboard where "average is all you need", maybe the "better than average" result would be asking yourself if it's even worth doing in the first place?

Probably the same way other models learned to surpass human ability while being bootstrapped from human-level data - using reinforcement learning.

The question is, do we have good enough feedback loops for that, and if not, are we going to find them? I would bet they will be found for a lot of use cases.

I am vibe-porting an old game, Knights & Merchants(actually its Delphi rewrite - KAM Remake) to WASM. It's going well, I even have multiplayer working at this point, will release it publicly at some point.

Learned more about WASM, OPFS, JSPI and other exotic browser stuff more than ever, also learned more about pascal than I ever wanted to, but it's been immensely fun.

Not having a code review process is archaic engineering practice at this point(at any point in history, really), be it for human written or AI written code.

Perhaps the problem is that you RL on one patch a time, failing to capture the overarching long term theme, an architecture change being introduced gradually over many months, that exists in the maintainer’s mental model but not really explicitly in diffs.

While at the same other companies have built entire business lines around fixing shit code(probably with more of the same though).

It doesn't matter, neither of those scenarios makes the effort impressive in this case. The vibe coded thing might even be useful - that does not make it impressive though. Effort does.

Orphaned or as Peter Naur wrote in 1985(https://pages.cs.wisc.edu/~remzi/Naur.pdf), dead programs :)

Autolands absolutely do exist.

You know what is an insult? Supermarket on my street putting on display sloppy ads with ramen bowl that has 3 different thickness chopsticks and cartoon characters with scrambled faces. Now that is an insult, because there was a human being doing that job, and I am sure there was a great "productivity boost" related to that change.

I am a heavy AI user myself, and sure as hell I am not putting my foot in that place again.