HN user
What’s interesting is that it maps well to how my brain actually works. My chain of thought is very non-linear. Maybe even a little chaotic, going off on tangents before returning to the main thread as it were. This has always made written and verbal communication a bit of a challenge, but the AI seems to parse my unedited stream-of-consciousness without issue.
I’ve started learning into the various AI-isms in my prompts. Most recently, em dashes to chain related information in a single sentence.
“Something something main point — but also pay attention to this related thing — finish main point.”
Anecdotally, it seems to produce more consistent results when I “speak its language”.
On the output side, I’ve become much more aggressive about trimming and editing any prose it produces that I intend on sharing. Both for my own benefit to improve comprehension, but also because dumping the raw, verbose output on my colleagues feels lazy and disrespectful of their time.
I had a similar situation where someone had their email client configured with my address in the reply-to header. We shared a first initial, last name, and isp… also happened to be my email address. His email was firsnamelastname, or something similar. I emailed the guy several times explaining how to fix it, and that I was getting a lot of his business correspondence. Never heard from him.
Then one day I get a Chase Zelle email saying that someone was sending me money. Something like $500. Logged into the Chase app and sure enough, could have taken it with the click of a button.
I contacted the sender to explain the situation and recommended they call the intended recipient for a correct email address.
Couldn’t image just taking it knowing it wasn’t intended for me.
The insurance requirement isn’t uncommon where I am (California). Though I would avoid whatever plan they are pushing. I got mine through my existing insurance provider and it worked out to ~$15 per month IIRC.
Same here. Little side projects and convenience tooling for $day_job that otherwise wouldn’t have gotten built for lack of time. Doesn’t need to be perfect, beautiful code for an audience of one. It just needs to work.
Perhaps solution was the wrong word for me to use here. It was intended to encompass the implementation details (abstractions, architecture, observability, etc)… All the decisions the engineers would normally make during planning and execution. Once I have that nailed down, the act of writing the code is largely mechanical.
That’s the source of my “easy” framing. It has always had the lower cognitive load in my experience. Now that I can offload the mechanical part to AI, I spend more time on the hard parts.
I still read plenty of code along the way, maybe less of it now because it’s easier to surface which parts of the code I need to read.
Responding to my own comment to add that I think this moment favors the curious and passionate. None of what I wrote above is a complaint. I’m having more fun now than I have in a long time.
My personal experience: writing code has always been the easy part. AI does most of that now.
Understanding the problem and the existing system well enough to design the right solution, even with AI assistance, is a higher cognitive load. I’m doing a lot more of that lately.
I’m more productive, but also more tired. This may be due in part to the breadth of what my team owns, which makes my day a bit more context-switchy than other teams.
As others in this thread have noted, the situation is still evolving. However, I worry less each day about being replaced by AI. There has always been more work than available bandwidth in my experience.
What seems clear to me is that expectations around velocity and throughput will increase (are increasing). AI use will be required to meet those expectations. Learning to use this new tool effectively will be essential for career progression (and preservation).
Overnight oats have been my go to lunch and pre workout meal for a couple years now.
75g 0% Greek Yogurt, 75g Almond Milk, 10g Maple Syrup, 8g ISOpure unflavored protein powder, 8g PBfit powdered peanut butter, Salt to taste. Whisk everything else together in one bowl. Pour over 85g of old fashioned oats and stir.
511 calories, 79g carbs, 30g protein, 9g fat. Easy to tune the recipe to macro targets.
Cholesterol numbers are great.
One specific example that comes to mind is developer tooling in the form of bash scripts. Sure, I can write it myself, but I do this so infrequently that there is a cost for the context switch and ramp up. This, and similar dev ex things that have been languishing in the “one day” pile because there is always the next feature to build. I can now spend 10 minutes here and there to ship incremental QoL improvements alongside my core work.
I’m still a couple decades off from “senior”, but I have already reached a point where most day to day driving feels like a chore. If/When Waymo finally arrives in my smallish Bay Area city I can see myself using it a quite a bit. Hopefully self-driving cars are ubiquitous by the time I reach “shouldn’t be driving” age.
re: your last bullet.
This has been very effective in my experience. “See class foo for example implementation “
I should clarify. I do very little greenfield development, even outside of work. So my understanding of vibe coding being good for this use case is largely rooted in the relayed experience of others.
Multiline autocomplete is still the biggest productivity boost for me. This works well in a familiar codebase with reasonably consistent patterns.
After that it’s the “ask” capability when I need to get oriented in unfamiliar and/or poorly documented code. I can often use the autocomplete pretty effectively once I understand the patterns and naming conventions.
Similarly, agents are good for a first pass triage and plan when troubleshooting tricky bugs.
Still haven’t had a good candidate for going full vibe code. Maybe that’s because I don’t do a lot of greenfield coding outside of work, which seems to be where it shines.
Just my experience. It’s new set of tools in the toolbox, but not always the right one for a given task.
This has been saving me a lot of time as well in a decade old code base. I can paste a stack trace and provide additional relevant context, then ask the LLM to do a first pass debug.
From that I usually get a list of file+lines to manually review, along with some initial leads to chase.
Another use case is when fixing performance issues. I can feature flag my fix and ask the model to confirm the new code path will produce the same result for a given set of inputs. We also have test coverage for this kind of thing, but the LLM can do a once-over and point out some flaws before I ever run those tests.
I haven’t gotten to the point where it writes much code for me beyond the auto-complete, which has been a modest boost in efficiency.
free heat that we couldn’t control
I understand the appeal of free. It’s the idea of someone else controlling it that gives me anxiety.
The multi-line autocomplete feels like the right middle ground (for me) when working in an existing code base with well established patterns. Adding new functionality is mostly a matter of scaffolding, commenting as I go, typing the first few characters of a code block and tabbing my way through the bulk of the code.
Same here. My interest in the Sci-Fi genre started with an HN comment recommending Blindsight, by Peter Watts.
Several comments and sci-fi series later, and I’m currently reading about spacefaring sentient spiders.
That little grill got me through many years of apartment living where I couldn’t have a propane grill.
This is basically where I’m at. It’s mostly become a utility.
There was (mockingbird?) near my home in the 90s who did a solid imitation of the multi- tone aftermarket car alarm that was common around that time. I recall being annoyed by it at the time since it often happened in the early morning hours. I kind of miss it now (or I’m just a little nostalgic for the sound of the time period).
My wife’s 2015 Honda has a similar setup for the climate controls. One morning the windshield fogged up after a few minutes of driving when the cabin was warming up on a cold day. Not being my daily driver, I had to look low on the dash to find the defogger button, while driving in the rain. Nothing bad happened, but I remember feeling a little helpless in the moment. That nothing went wrong was really just pure luck.
He lets them all go to voice mail, so nothing about his behavior encourages them to keep calling. Yet they keep coming
My pet theory is that scammers are harvesting voice samples from voicemail greeting for the purpose of training a voice impersonation AI.
I now use the default greeting.
It took longer than I would like to admit to realize it was time to leave WoW for good. A few increasingly long breaks, followed by brief periods of trying to “fall back in love” with it.
It wasn’t so much that I got burned out on the game. It just didn’t fit into my life the way it once had, but not for lack of time. A person’s relationship with a video game can be weirdly complex.
I have tried a few times to taper off Venlafaxine with no success. Looking back I think the problem was twofold: I tried to do it too quickly (1-2 months), and expected things to somehow be different despite having made no other changes (lifestyle, job, etc).
This time is different. I'm now in a job that I find rewarding, started resistance training 4 days a week 2.5 years ago, changed my diet (mostly to support my fitness goals). I'm also taking it slow, halving the dose and taking several months to adjust to the new normal, whatever that looks and feels like.
It's a marathon, not a sprint. (True for both the fitness and mental health goals).
I filled out a contact form some months ago asking how I, as an individual, can purchase an individual subscription. After some back and forth they coul only offer to connect me with their sales team. No thanks.
Provide a low friction subscribe and unsubscribe flow, and I will gladly pay for your product, Reuters.
Broken coffee machine? That’s a SEV0. Declare an incident.
Someone recently joined my team (mid size SaaS) from a FAANG, and the couple times I asked about their time at said FAANG they quickly steered the conversation elsewhere. I took the hint.
I get the sense that they would mostly rather forget the experience.
I’m in my late forties and sprained my back/hip pretty badly right at the start of COVID. A year later I was having trouble descending stairs and starting to develop knee pain on the same side of my body. So I began a fairly rigorous resistance training program about two years ago with hopes of regaining full mobility. The results have been fantastic. I still have a bit of pain from in both the knee and back, but it’s not disruptive. Most importantly, I have normal mobility and the injured areas have stabilized. With any luck it will continue to improve so long as I stick with it. That’s in addition to all the other benefits that come with being in better physical shape.
I have read this sentiment elsewhere and I’m genuinely curious about what it is that the imports try to change. I’m a California native and have lived here most of my life. Any time I have thoughts of moving somewhere else, it’s usually because I’m drawn to the culture. So the idea of moving somewhere only to try turning it into the place I moved from just seems odd to me.
I know people move for other reasons, CoL being the most obvious one in this context. Even then I would expect people to choose a place where they would more easily assimilate rather than trying to change the existing culture.
Lastly, California is far from being a monoculture. Even in the famously liberal areas, there is still a great diversity of culture and ideology in my experience. Drive two hours in any direction from those areas and you may as well be in rural anywhere USA. I feel like the California hate is rooted in stereotypes that don’t apply to a majority of the population here.