hartleybrody
Joined 15 years ago
Karma
2,491
Submissions
245
Member since
Aug 9
Recent submissions
Comment · 2 months ago
This is probably the skill you remembered: https://github.com/AminBlg/SimpleEnglish
I have been using it for a few weeks, and it significantly improves the quality of the docstrings and code comments, as well as the readability of spec docs.
I have also added a few key bullet points to my AGENTS.md and have found the results to be very effective and generating plans and code that looks like something I would have written:
-----------
## planning, design and spec docs
- the highest design goal is simplicity -- in our systems and our mental model -- even if if means edge cases are unaddressed and could potentially fail
- please practice "ya ain't gunna need it" (YAGNI) do not add unnecessary guardrails
- do not plan to add caching, many layers of unnecessary abstraction or other premature optimizations
- look for places where adding or clarifying an invariant would simplify the code or the overall system
please specifically try to avoid:
- redundant calculations or duplicated work
- duplicated conditionals or state-machine logic
- storing state that can be derived from other state, which could drift and become out of sync over time
- leaky abstractions across layers of the application
- multi-line comments explaining a variable name or a single statement. well chosen names and design should makes these unnecessary, as the code is self-documentingComment · 2 months ago
This has not been my experience at all. I have been using this skill[0] for several weeks and when I ask it to rewrite existing AI slop docstrings to use this convention they are nearly always 10-20% smaller, plus easier to read and mostly free from the traditional "tells" of AI writing.
Comment · 3 months ago
11 years ago, I had the idea that I should be able to take any article on an arbitrary website and listen to it as a narration in my chosen podcast player. At the time, text-to-speech (TTS) services were very robotic and it was difficult to listen to anything longer than 10 seconds. But now that TTS is much better, long form narrations are actually quite pleasant to listen to, so I gave it another go.
There's a browser extension that reads the content of the article on the page (only when you activate it, using least privilege browser APIs for content scripts) and then narrates the article for you. You get a custom podcast RSS URL that works in (almost) any podcast player, and then you can take articles with you to catch up while driving, walking the dog, etc. All the typical podcast audio controls you're used to like speed settings, skipping, and no new apps to download or learn.
It has genuinely been a big benefit and allowed me to keep up with articles I'd never normally have time to read, plus it allows me to reduce my screen time. My wife also uses and loves it. There have been some interesting bugs in the narration like originally pronouncing "24/7" as "twenty-four sevenths" but I am working through different strategies to get more accurate narration from arbitrary long-form text.
With apologies for the ".AI" domain, it was a bit of an impulse buy: https://earcast.ai/
Comment · 11 months ago
Boston. Was looking into becoming a medic when living there many years ago, and learned that Boston EMS has their own dedicated training and certification, with more limited protocols for EMTs since there are so many world-class hospitals within a few minutes drive from any point in the city. EMS has less to do but load-and-go.
Comment · 1 year ago
Is IntelliJ generating source code that gets committed to your codebase?
Seems completely different. See also, this discussion:
Comment · 2 years ago
>that you're sorry and to truly empathize with the people they're firing
Serious question: what should have been said on this call to do that? There was a lot of "I'm sorry you feel that way" seeming to come from the HR representative, but it seemed to miss the mark.
Comment · 3 years ago
I used to work in a hospital and one thing that was already tough was when doctors would copy massive (multiple page) notes that were mostly boilerplate, probably stored as some template in the EHR. After seeing the same note a few times, you started to learn which page to scroll to in order to view the relevant section for the patient. I would hope this system only generates clinically-relevant text for that patient, usually only 2-3 paragraphs for a standard consultation.
Comment · 3 years ago
Wow, lots of haters in this thread. Having doctors spend less time with clerical/administrative work needed to record conversations will free up more time to focus on patients. I assume the generated note text can be easily modified by the doc if necessary, but saves them the bulk of having to type things up and remember everything that was discussed.
Comment · 4 years ago
This is an excellent point. While their main value prop seems to be "servers closer to your users" you could also just use them as a drop-in replacement for something like heroku and just use one region to simplify the mental model, pricing and orchestration.
Comment · 4 years ago
OP here, thanks for making that distinction more clear. I had listed them all as new tech that I am starting to use, but you're correct that I wouldn't intend to use them all _together_.
The HTMX and alpine libs were intended to be sprinkled onto existing web apps (my usual python/flask stack), whereas Phoenix would be for building all new projects.
https://hnbadges.netlify.app/?user=hartleybrody