It only has 272 pages, but there is a big scandal right now about France's most prestigous literary award remobing a critically aclaimed(!) bestseller(!!) novel because it likely was "almost entirely written by AI"

https://www.theguardian.com/books/2026/sep/25/thelyson-oreli...

Comments URL: https://news.ycombinator.com/item?id=49907971

Points: 1

# Comments: 0

1. Sad that he died from cancer

2. Noticed he compared primary energy and felt stupid for missing that

> This would be an ambitious but achievable cadence for Starship, particularly if the tanker Starships didn’t have to be reusable, and could be made without a heat shield or control surfaces. Just how much time SpaceX has to reach this cadence is an interesting question, since right now NASA and SpaceX are locked in a game of chicken around who can commit to the least realistic timeline. But it probably has to get in gear by early 2027.

This is good evaluation. A launch every week in 2027 is ambitious, but not impossible.

Starlink didn't get any subsidies. There were reports in summer about them potentially getting 600 Mio (btw the broadband program is 40 billion heavy) and I can't find sources that SpaceX got any program founding yet.

——————————————————————————

Context: I have 30 years of experience with software dev, 20 years with game dev tools, 10 years with Unity. I own a studio that develops simulators and training applications for industry. "Serious games" as they call it in Europe.

For years I scoffed at AI coding. I would periodically try it, only to find that it was more hassle then it was worth. The hand holding and bug fixing was more work than doing it myself. This all changed about 4-5 months ago, and about a month ago we all started using Unity CLI.

Here are my insights in no particular order:

1. Our dev speed has ~5x almost overnight

2. Quality has not gone down because we're all experienced devs and we're careful how we use AI and we don't let it make decisions regarding project structure or design patterns. However, I'm seeing less and less glaring mistakes made by the AI.

3.We're still reviewing generated code but I suspect not for long, the code is better than what most devs I know can write, at 20x the speed. The temptation to just push and move on is huge and irresistible.

4.There is no joy or sense of accomplishment. No pride in making something clever or quickly, and all progress is associated with the AI and not with you.

5.The market is dead. Nobody has money to spend. We're still working but leads have dropped off a cliff.

6.There is no going back. If we stop using AI we'll be out of business in a month.

7.There is no space for junior devs. I honestly don't know how to incorporate a junior into a team anymore (which is something I used to do for decades). Every time we tried they just become a meat proxy for AI while learning nothing, and getting in the way.

8.Everything regarding managing a team and a project has changed, and nobody knows how to do it anymore. I lost the ability to correctly estimate work required for a task, for example.

9.Everyone hates this. Most of devs my age are planning early retirement and are just waiting to be laid off.

10.People that use AI for coding don't learn anything. To understand code you have to write it, and nobody is writing it. Maybe understanding and reading code will become obsolete soon? I don't know.

11.Everyone I asked feel they are becoming dumber and losing their focus. I know I am.

I hope this is a pendulum and it will swing back at some point, because right now it feels like a software apocalypse.

Comments URL: https://news.ycombinator.com/item?id=49818027

Points: 3

# Comments: 1

Edit: The bot also maphacks

Why though a human? Mathematical proofs are very ivory-towery, but if OpenAI would solve a subkind of Cancer, without mortal humans understanding, cancer is still be healed.

True, but the driver is a stranger to me.

Herd animals like cattle/horses, are highly suspicious of, and stressed by, strangers. And imagine how uneasy two chimps could react when meeting for the first time.

Hard disagree. It was a great phone. The only disadvantage was battery life, if you were a heavy phone user you needed to charge it to get through the day, but as a phone itself (phoning/messaging people) it was delightful!

Look at the clip here of Steve scrolling through contacts like it is butter and the awe of the audience: On other phones large contact lists were cumbersome.

https://www.reddit.com/r/apple/comments/9kahkr/11_years_ago_...

Than visual voicemail! On other phones you called into voicemail and had to hear sequentially through all. With At&t Apple had the unique feature that one can scroll selectively through voice mails.

Of course the second iPhone 3G with the wjooshing sounding light saber app and the app were a beer is poured out made it cultural viral. And then Apple noticed withe the 4/4S that a good camera in your pocket was THE must have killer feature (especially for the women and newborn parent demographics). But the first model was a great tool for just phoning people.

From Jacob:

> A common response is “if they truly believe this, why are they still building it?” At OpenAI, many have not deeply internalized the civilizational stakes. At Anthropic, the stakes are well-understood, but they are locked in a race to get there first - they believe no one else will act responsibly, so they must do it themselves, despite the risk.