This is a classic early internet style snarky comment you used to find all over forums

This is basically just telling people to learn to code

Which IMO they should anyway if they are doing advanced automation

No coding is required. You can literally ask your agent to install and configure it. It is only 2 small binaries and no external dependencies. It cannot be any easier than that.

I would never use it on my MacBook or any machine but I understand why technical people would want to experiment with something dangerous like that. It’s novel, exciting, and might inspire some real practical products in the future (not just highly experimental alpha software).

Google has always done no warning bans

YouTube is also full of huge content creators, people who make Google tons of money, that complain about the Byzantine and opaque rules they have to dance around to maintain their livelihood and fan base

Google fears their giant userbases so they act with zero regard for communication and transparency because of the small chance it’d help the abusers

That’s called protecting a monopoly not protectionism

It’s an extremely strong incentive to not use Gemini for anything serious

You must not work in the SaaS business if you think that

Not sure if this is sarcasm, but I'll respond as if it isn't. Having worked my entire career to date in the SaaS business, it is well known in some verticals that a large portion of revenue comes from companies that literally do not know they have purchased your product. And when you have a large customer like that, people are very careful to walk quietly and not do anything to notify them. I've seen it happen quite a few times.

Most of these AI coding articles seem to be about greenfield development.

That said, if you're on a serious team writing professional software there is still tons of value in always telling AI to plan first, unless it's a small quick task. This post just takes it a few steps further and formalizes it.

I find Cursor works much more reliably using plan mode, reviewing/revising output in markdown, then pressing build. Which isn't a ton of overhead but often leads to lots of context switching as it definitely adds more time.

> When people go out of their way to avoid common sense they should be punished.

Sounds like it was mostly just people reacting to government incentives. Subsidized markets acting irrational.

Politicians are conduits. Someone wanted this to happen.

But yea, subsidies. I've been on many a call where "there's govt funding available if we shape this like x" is one of the major selling points.

Politics has a habit of being very insular once elections are finished.

There will always be a strong belief in artificially changing market behaviour by simply throwing money at it and hoping it sticks. When the money dries up the public tends to go back to "what's practical and affordable?".

> There will always be a strong belief in artificially changing market behaviour by simply throwing money at it and hoping it sticks.

Well, it can be made to work, you know. Late (in the XX century) industrialization stories are like that: competitive (dis)advantages make any such attempts simply unprofittable for any businessman (or even a group of them), but if the government keeps skewing the market for decades... The Japanese car manufacturing has been heavily subsidized for most of the XX century, even after their several disastrous attempts to enter the US market. But it all worked out in the end.

I'm guessing the first question will be "How are we going to keep the UI consistent?". The hard part is never the code writing it's carefully releasing fast changing features from product people. Their chat UX is the core product which is replicated on the internet and other devices. That's almost always React or [JS framework] these days.

Migrating the system would be the easier part in that regard, but they'll still need a JS UI unless they develop multiple teams to spearhead various native GUIs (which is always an option).

Almost every AI chat framework/SDK I've seen is some React or JS stuff. Or even agent stuff like llamaindex.ts. I have a feeling AI is going to reinforce React more than ever.

Why does the ui need to be consistent? If its for documentation I then an llm should be able to write those instructions.

Yep, I understand why let's release this one feature everywhere is a great lure and I do get annoyed when desktop vs mobile spotify gets features later or never. However, a phone is not a desktop capability wise and what we usually get is the power of the phone on a desktop, aka the lowest common denominator of capabilities.

This fetish we as an industry have to hide platform specifics makes us blind to the platform specific capabilities. Some software would be better off if it leaned into the differences instead of fighting them.