fibonachos

I’ve been using diagrams a lot lately. My team currently owns a wide surface area, so there is a lot of mental context churn as we bounce between parts of the system. HTML diagrams, or artifacts in the Claude desktop client, are super for helpful for bootstrapping/refreshing my mental model when starting a new project.

Apply TV + two HomePod Mini’s is precisely my setup. I wanted a TV in my living room without it dominating the space. The only practical location was over the fireplace, so I went with a “frame” TV.

It’s not a home theater by any stretch, but perfectly adequate for every day viewing.

It’s worked for me with multiple strays, one of whom is no longer a stray. The other one who hangs around is still quite feral, but he has grown less skittish over time.

In my late 20s and early 30s I would frequently join my coworkers outside while they took a smoke break. I would generally try to stay at the periphery or upwind when possible. Over time, I found myself having inexplicable cravings for a cigarette despite never having smoked one. Presumably this was due second hand exposure. (Acknowledging it would have been smarter to simply stay indoors.)

That eventually faded after our careers took us in different directions, and landing remote roles or at places with fewer or no smokers.

I can’t imagine how difficult it must be to quit. Props to anyone who makes the attempt, successfully or otherwise.

My newest cat started as a stray. Cautious around humans, but not feral. He was hanging around a lot, so of course I started giving him food because I’m a sucker that way. He disappeared for a couple months, then showed up injured from a fight one day, so we took him to the hospital and ended up keeping him in the garage for a few days to recover. We also did the usual due diligence to locate an owner.

The rest, of course, is history. Now he’s a big 20lb goober of a cat who is positively enamored with my wife. The feeling is mutual.

This feels like a good place for tighter integration between editors and agents. The editor could notify the agent of user authored changes.

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.