AI agents are becoming your biggest API consumers, and they can’t always DM other teams. If you want to be productive with AI, if you want your codebase to be a place where agents can actually work, you need to think of your codebase as an application that the agent is interacting with.
So what you’re saying is: mis-type everything! 👉😉👉
What an exciting time to be building software! With AI, we’re able to achieve production outages with unprecedented frequency!
“Oh Sandra, you dumb bitch.”
The pattern of demoing stuff like this and then responding to the glaring issues and failures with, “but just wait until the next model bro, eventually this will work bro, just need a larger context window, maybe some recursive prompting, we’re basically already there bro,” is so embarrassing. If I claimed to have written this myself and presented it at a tech conference (or hell, even turned it in as an assignment in a CS course), I’d be laughed out of the room when it failed to compile hello world. The fact that people see this and get excited is so bizarre.
If it can’t compile hello world, can you even imagine all the easily exploitable security issues, the unhandled edge cases, the major performance issues, etc. that are buried in that dumpster fire of source code. That this is what passes for software “engineering” now is so sad. Too bad they don’t start using this compiler at Anthropic.
I can’t wait to see how RFK Jr. manages to turn this one around! /s
I’m not so sure the “open source” part is working either when you think about how AI tools were trained.
It’s really sad, because the accessibility of developing software and collaborative nature of the open source community is a big part of what drew me to software engineering as a career, and it’s always been one of the first things I mention about why I love it. But, of course, these fucking evil companies found a way to take every individual part of something good and twist it into something awful.
It’s stuff like this that leaves me completely hopeless that the AI industry will ever see the crash that it 100% deserves.
The most frustrating is when someone asks me for help because they’re stuck then hits me with a barrage of “chatgpt said xxx” complete nonsense while I’m trying to assess the situation
That is the absolute worst. I’ve even gotten “Because Claude said so” in response to code review comments asking why they made a certain design decision.
they let off the gas
Man, I’m so jealous. My company is too large for me to have any sway, and they just added AI tool adoption as one of the key performance indicators on our performance reviews. 😔
I am staunchly anti-AI, but the company I am working for unfortunately pushes AI tool adoption extremely aggressively. A lot of the things in the post are similar to sentiments I have. Specifically the sections around vibe coding offloading the burden of work to the reviewer and how to mitigate that by pushing back against those sorts of PRs.
I agree with you, though, that the post ignores the simplest solution of just not using AI tools. It may be the case that the author doesn’t have the ability to enforce that, but it should still definitely be listed as the first and most logical solution.
I’m at the point where I’m seriously considering creating a blocklist of certain engineers at work that spam out vibe coded trash PRs and informing my manager that I will not do code reviews for anyone on the list.
Mainly just piano. I like playing chords with my left hand and the melody with my right hand. I’m not great at keeping steady rhythm. If I or anyone else starts singing along, I immediately lose focus. I mostly just play for myself for stress relief.
I’m trying to learn guitar, but it’s slow going for the time being.
There’s some deep irony in the fact that his whole post-Phantom-Menance character arc was “too angry to die” and how Disney is too greedy to let him die. They’ve brought him back so many times. I realize this is before his final death on Tatooine, but still crazy how determined they are to revisit these already over-explored characters rather than take a chance on something new and exciting (like an Old Republic era TV show).
Duolingo isn’t just teaching vocabulary — it’s teaching real communication.
Wow, nice, even the article’s written by AI! /s
Come to think of it, why would I even bother learning a new language in the first place? I’ll just have my AI talk to my friend’s AI, and that way I won’t have to think or interact with another human at all!
That’s fair, although this paragraph buried at the bottom of the post felt more like a disclaimer than anything. Yes, I’m white, and I have never wondered if I should join the Black Panthers and I have no issue with the fact that it’s not a space for me. I clicked on the post because I was interested in hearing a well-articulated explanation of why it is important to that organization to be, for lack of a better word, discriminatory in it’s membership as well as what people who find the concept of armed protest appealing can do instead. And instead of getting either of those things, 90% of the article was “lol, white people and their lattes, am I right?”
The 300 dudes in a field:
I’m not sure why this is even being upvoted. The entire blog post is just using stereotypes to lambast any white person who has ever participated in a protest related to racial injustice. It almost feels like the goal is to deliberately alienate potential support and sow division.
The title makes it clear that the blog post is about white people, but nowhere in the entire post does the author even bother to try and describe how white people can show support or unity with groups like the New Black Panther Party. It feels pretty bad to structure the entire discourse around the idea that all white people are virtue signaling and not even entertain the idea that some might actually want to help.
Pretty sure we’ve had evidence of this since at least 1982. What the tools are for, on the other hand, is a subject of ongoing debate.
Upgrade it to Cat6a.
Unfortunately, the person who deliberately prompted AI to write this blog post and publish it is getting exactly what they want. Attention. And all of the gullible people acting like this is somehow an example of “dangerous levels of AI intelligence” or whatever bullshit are playing right into it.