Location: San Francisco, CA
Remote: Yes, onsite preferred
Willing to relocate: Yes, tech city preferred
Technologies: JavaScript, TypeScript, React, Express, MongoDB, NodeJS, HTML, CSS, Deno, Svelte, Swift, SwiftUI, Figma, Ansible, Docker, Git, Python
Résumé/CV: https://home.jrmann.com/resume
Email: jordan.r.mann.25 [at] dartmouth [dot] edu
I graduate from Dartmouth College in June, and I'm excited to apply my majors in Computer-Science + Human-Centered Design and Studio Art in the industry. I have a passion for re-imagining digital services as more usable, accessible, scalable, and beautiful products. My internships at Kard Financial and Appian Corporation focused on full-stack engineering, and I'm open to branching out! Let's chat - https://talkwith.jordanmann.com
So they have a operable spaceship, they know what radiation is because they talk about cosmic radiation and shielding, but they don't have any way to measure radiation or awareness of what exposure looks like or even an inkling that it could exist on a planet, even after visiting several defunct technological civilisations. It's a fun story, but it goes to show the lengths you have to go to to contrive a story where there's a possibility of harm to even a couple of people.
If nothing else they appear to have microelectronics (e.g. video playback and displays). Manufacture of that requires knowledge of radiation because you need to keep the encapsulation material low-activity. Plus the general ideas behind semiconductors and microlithography are based on physics very close to the physics of ionising radiation (e.g. photoelectric effect) and you probably use D/EUV, X-rays and ion/electron beams somewhere in the process too.
Single bit errors = radiation. If the voltage log is fine, there's nothing else that could impact that many chips at once. These characters are morons.
The entropy arrow definition would have worked here.
iTerm2 actually has a pretty well-designed tmux integration[0].
Overview from the guide:
When you run "tmux -CC", a new tmux session is created. An iTerm2 window opens and it acts like a normal iTerm2 window. The difference is that when iTerm2 quits or the ssh session is lost, tmux keeps running. You can return to the host you were ssh'ed into and run "tmux -CC attach" and the iTerm2 windows will reopen in the same state they were in before.
It works with multiple panes, windows, etc. Worth trying out!
I'm too lazy to move things out of ~/Downloads, so I've just started using the folder as my default working directory and struggle to clean it out every quarter or so.
/tmp (or probably ~/Library/Caches/TemporaryItems for my account only) being cleaned out on every reboot would force me to be more intentional.
I collapse the crufty locations down onto my desktop. It doesn't really stop me from treating it that way, but it means there's only one place to clean up, and creeping icon sprawl eventually forces me to deal with it semi-regularly (instead of letting it slide until it's time to wipe the device...):
I find ChatGPT most helpful as a "what's that called" tool. A lot of my queries are finding/confirming the right idiom when writing something, or getting a specific name out of a vague description (JavaScript concepts, shell commands, CSS selectors).
Search engines with SEO are so reliant on keywords that it often feels like I'm suggesting answers rather than asking questions - it's so refreshing to be able to just ask again.
Yea, this is great. I used it alot for this. When you kind of know what you wanna do but you dont know the technical term.
Like if you dont know it is called sharding but you know you wanna store stuff on several databases.
Me:
I have a postgresql database but it has too much data in it. I wanna split the data in several databases. What is that called?
GTP: Splitting a database into multiple smaller databases is known as database sharding. Sharding is a technique used to horizontally partition large databases across multiple servers or instances in order to distribute the workload and improve performance. Each shard is typically hosted on a separate physical or virtual machine and stores a subset of the total data, allowing for more efficient queries and faster data retrieval.
It's replaced Google for the "what's that called" tool.
Google used to be good at that task, but it's sucked for the last four years or so. Whenever they gave up on search and leaned into sludge content plus ads.
GPT is better than Google for something like, 'how do I implement nested blog post comments in Flask'
And much worse than Google for, "site:miguelgrinberg.com nested comments"
Unfortunately I don't know the equivalent of Miguel for everything I need to know, so on average I suppose GPT is better. However it also means that you may never discover the Miguel of your domain!
I hope it's going to remain that way, but the realistic cynic in me tells me that using ChatGPT to discover stuff is going to increasingly suck more now that people are going to try to target ChatGPT for SEO.
