> The first that will be replaced are going to be those that are using AI mindlessly, because at that point, what are you besides a very expensive human LLM interface?
I think this archetype has a good chance of surviving. Not because of merit, but because they will be the only ones able and willing to work on projects taken over by AI slop.
I'm very much aligned with everything else you said.
Only tangentially related, but does anyone know if it is possible to ‘paste’ images to an agent harness running inside a docker container?
My current workaround is to paste it inside the working directory on the host machine, then @ reference it, but would be nice to streamline that workflow.
> Working directory persists across commands. Set CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR=1 to reset to the project directory after each command.
It reduces one problem - getting lost - but it trades it off for more complex commands on average since it has to specify the full path and/or `cd &&` most of the time.
Update: I gave it a try and it does exactly what I hoped. However one (minor) annoyance I immediately realized was that with `hex` enabled I will get this warning whenever I close the terminal window:
> The terminal still has a running process. If you close the terminal the process will be killed.
Hopefully there is a workaround for this (I'm using then Ghostty emulator).
Sony WH1000XM5 headphones are my daily driver, mainly Zoom calls and music. I'm generally pretty happy with them, but one big gripe I have is when I'm on a call and briefly take off my headphones to e.g. chat with someone in the room, there is like a 90% chance they stop working and I have to reconnect them.
It happens so often I even wrote a script to switch to the MacBook internal speakers then back to the headphones.
I've used wired headphones before (and the Sony even has a wired option), but I didn't like how the cord was constantly getting the the way of my arms.
edit: Another big gripe is with the Bluetooth codec itself, and how the quality changes depending on if the mic is active.
I use the Raycast + Whisper Dictation. I don't think there is anything novel about it, but it integrates nicely into my workflow.
My main gripe is when the recording window loses focus, I haven't found a way to bring it back and continue the recorded session. So occasionally I have to start from scratch, which is particularly annoying if it happens during a long-winded brain dump.
This reminded me of this passage from Anxiety Is the Dizziness of Freedom by Ted Chiang:
> None of us are saints, but we can all try to be better. Each time you do something generous, you're shaping yourself into someone who's more likely to be generous next time, and that matters.
User Defined Functions (UDFs) are another option to consolidate the logic in one place.
> Using Functions on Indexed Columns
In other words, the query is not sargable [0]
> Overusing DISTINCT to “Fix” Duplicates
Orthogonal to author's point about dealing with fanout from joins, I'm a fan of using something like this for 'de-duping' records that aren't exact matches in order to conform the output to the table grain:
ROW_NUMBER() OVER (PARTITION BY <grain> ORDER BY <deterministic sort>) = 1
Some database engines have QUALIFY [1], which lends itself to a fairly clean query.
I have an iPhone SE 2nd Generation. After a recent repair I was forced to upgrade to iOS 26.
My biggest gripe is the buggy keyboard. It shrinks a bit horizontally every time I open it. When using a mobile browser (I tested on a few), website footers and similar elements will get stuck above where the top of the keyboard would normally be, as if there was an invisible keyboard.
These tweaks to minimize the glass effect go a long way, such that I'm not as put off by the overall design as I was in its stock configuration.
I was hoping for more of the author’s own perspective over those ninety years. Instead, it read more like a stitching project of other people's ideas. In particular the barrage of quote fragments disrupted the flow and made it harder for me to engage with the main point of each section.
I think this archetype has a good chance of surviving. Not because of merit, but because they will be the only ones able and willing to work on projects taken over by AI slop.
I'm very much aligned with everything else you said.