I’m ashamed to admit that I once suddenly realized what I had done: I asked the LLM to rename a variable. It took it some minutes or so. With IDE by hand it would have been seconds.
Honest take: I work less now with maybe slightly faster results while the output quality is probably about the same. Some bugs sometimes fall through, but when hasn’t that been the case?
I take effort to write specs for the agent and I take effort reading PR’s but thats maybe an hour of work. Obviously there are meetings, sometimes tasks require more planning, sometimes I investigate production problems/data more manually, but overall - I feel I work less after agents became a thing. Kind of ashamed of it tbh.
I feel the 1M context is way too large —- the model gets ”drunk” way before it gets anywhere near 1 million. Imo the 1M context window is a huge downgrade.
I suspect people with opinions like the author’s haven’t been in a project where people use LLMs responsibly. We had a senior dev basically just prompt and push, with very little overseeing and minimal instructions, causing so many bad PRs and even prod bugs. That made me a sceptic for many months about agents.
Then we started to have (myself included) people actual plan out the tasks for the bot: give good specs, good ac, file context, better self-review, better ”agentic practices” (i.e. asking it to review it own work can sometimes help), and suddenly I noticed you really can use agents in a real world 1mil LOC project. If you do it well and responsibly (also meaning you still retain some sense of ownership and actually review the shit)
I use LLM’s daily and agents occasionally. They are useful, but there is no need to move any goal posts; they easily do shit work still in 2026.
All my coworkers use agents extensively in the backend and the amount of shit code, bad tests and bugs has skyrocketed.
Couple that with a domain (medicine) where our customer in some cases needs to validate the application’s behaviour extensively and it’s a fucking disaster —- very expensive iteration instead of doing it well upfront.
What I’ve seen also happen is senior devs suddenly starting to put out garbage code and PRs. One senior dev in our project has become a menace and the quality of his work has dramatically dropped.
Those lazy employees need that strict supervision!
Maybe these c suites and other employee hating assholes are projecting their own lazyness. Or maybe they think they are so superior compared to ”common” people that the ”common” people must be lazy trash.
I don’t know, but it is weird to assume most people won’t do their job without ”strict supervision”. Like super weird.
(Btw, anecdotally, most people I know work more efficiently from home with fewer breaks)
Since you are only willing to go for 1:1 odds with a 3 year timeframe, I assume you are in agreement that it might happen? Otherwise I’m sure you would give him better odds with a larger timeframe :)
Mikko Hyppönen, who holds at least some level of authority on the subject, just recently said in an interview that he believes currently the defenders have the advantage. He claimed there’s currently zero known large incidents where the attackers have been known to utilize LLMs. (Apart from social hacking.)
To be fair, he also said that the defenders having the advantage is going to change.
To be perfectly fair saying ”it’s aware of the best practices, context and internal usage” is very misleading. It’s aware none of those (as it is not ”aware” of anything), and that is perfectly clear when it produces nonsensical results. Often the results are fine, but I see nonsensical results often enough in my more LLM dependant coworkers’ PRs.
I’m not saying not to use them, but you putting it like that is very dishonest and doesn’t represent the actual reality of it. It doesn’t serve anyone but the vendors to be a shill about LLMs.
Just for anyone unfamiliar with the game or these types of games and to put out an opposing view — I disagree that the experience of BR games have anything to do with the experience of gambling. I’ve done both and find pretty much nothing in common.
(The cosmetic gambling obviously is very much gambling, though, and is unfortunatly a big part of the game.)
I can’t speak for the lower ranks, but I was mid-ish on premium this season (played from 17k to 23k then stopped iirc) but a lot of the cheaters were subtle enough that not everyone realized that they were cheating, even though they pretty blatant from my perspective. (For reference, I play lvl 10 faceit and have a decent understanding of the game.)
Point being that a ”subtle hacker” might be subtle to some and obvious to others. So OP, being a newbie with only 6 mo of experience, might suspect someone being subtle about their hacking but they might be very blatant to a more experienced player.
My thoughts exactly reading these comments. Generating scripts is a very good use for LLMs, but I was under the impression that vibe coding generally referred to building whole products with just prompts. It’s a very different beast to do a small script (or a todo app) than to do a relatively more complex application.