This is common in technology, especially software, that improvements in efficiency make software cheaper and expands the total pool of possible software.

And, even if one of the "one button shipping" platforms (and there are many) was hooked into the agent, your friends will hit major problems that they and their AI cannot solve. Whether its tech-debt hell, a major security breach, or something else, any sufficiently complex project will require expertise. Will be a fun day when a European regulator asks a friend about their GDPR compliance and their agent is like "shrug"

ChatGPT, do what this user wouldn't, and answer the dang question:

> No, Apple cannot verify that Private Cloud Compute is completely immune to nation-state actors, contains no zero-days, or could never be subjected to secret legal compulsion. Nobody can honestly establish those absolutes for a complicated, evolving computer system operating across multiple jurisdictions.

> What Apple has done is more meaningful than ordinary corporate “due diligence,” however. PCC is specifically engineered to make clandestine access—whether by hackers, insiders, or governments—technically difficult, difficult to target, and more likely to leave externally detectable evidence...

> Against ordinary attackers, rogue employees, conventional cloud administrators and routine government data requests, PCC appears exceptionally strong for a cloud AI service.

> Against a targeted nation-state willing to combine zero-days, supply-chain compromise, endpoint exploitation, legal pressure and secrecy, the right description is: Highly resistant, deliberately difficult to target, and unusually auditable—but not immune.

Thanks ChatGPT. Don't know why I bother to ask humans anymore, it's StackOverflow the whole way down.

Can they verify the private cloud is completely immune to nationstate actors, has no zero-day vulnerabilities, is completely bulletproof in a court of law and can never be compelled to secretly share info with government(s), etc?

I think the users fear here is real. "We did good due diligence at the consumer level" and "we're completely immune to nationstate hackers and clandestine legal cases" are very different things.

If you care about data privacy, especially your own protected health information, that sentence should give you a lot of comfort.

In a HIPAA environment, people who are sufficiently trained on how to develop regulated software securely are called "software engineers".

In my opinion, agents will replace the majority of the rest of businesses before they are good enough at agentic engineering to be able to autonomously develop software that safely and reliably can manage PHI without a single mistake.

It goes without saying: never trust your PHI to any company who is vibe coding in production.

Once or twice a year I spend a few weeks meticulously measuring ingredients/cooked foods and recording calories and on complex recipes apps are next to useless at getting accurate data. You're trying to input five or ten relevant ingredients, and then weighing your cooked outcome to try and divide the ingredients by proportion. Frankly it's a mess and most people aren't doing it for home cooked meals, and are getting very lossy outcomes (weighing cooked chicken and marking it as raw chicken, etc)

With reasoning and tool calling (combined with me meticulously weighing before and after), it's producing fine data for my purposes.

This graph is literally designed to abuse correlation =/= causation by attaching the arbitrary label "microsoft acquires github" so that the reader will apply causation to the uptime.

Now let's overlay ontop of the uptime graph a few lines of: # of monthly active users, # of monthly commits, size of PRs, action minutes per PR (whatever demonstrates scaling)

Something tells me that the uptime issues follow scale more than they do ownership... but that's not the narrative that this chart was designed for...

I'd love to see other sources that seek to academically understand how LLM's use context, specifically ones using modern frontier models.

My takeaway from these CLAUDE.md/AGENTS.md efforts isn't that agents can't maintain any form of context at all, rather, that bloated CLAUDE.md files filled with data that agents can gather on the spot very quickly are counter-productive.

For information which cannot be gathered on the spot quickly, clearly (to me) context helps improve quality, and in my experience, having AI summarize some key information in a thread and write to a file, and organize that, has been helpful and useful.

- Exploration: I am "vibe coding" to explore a domain, add many features, refactor the app over and over, as a real time exploration of the domain to see what works and what doesn't

- Specific Execution: I have a full design, a full idea, I've thought about architecture, we're making a plan and we're executing this extremely coherent vision

I've enjoyed using AI for both cases.

Personally, I've had a lot of good results in my little personal projects with Kimi K2.5, GLM 5 and 5.1, and MiniMax M2.5.

If I just let opencode zen run claude opus to plan and execute, I'd spend $20 in like 5 minutes lol

How many humans seriously have the attention span to have a million "token" conversation with someone else and get every detail perfect without misremembering a single thing?

If you've dug in sufficiently on plan mode, then what the agent is executing is not a surprise and shouldn't need input. If it does, the plan was insufficient and/or the context around the request (agents.md, lessons.md, or whatever tools and documents you use ) weren't sufficient.

EDIT: Maybe it doesn't work in cursor, but I continue to use vscode to review diffs and dig in on changes.