I'm not sure if you got it, that inhumanely != inhumanly. Where inhumanely is without consideration for the human race, whereas the other is non-human-like.
The LLM itself doesn't, but agents can research, compare, add to their memory, and use that to narrow the results down to a probabilistically higher set of outputs; I have used an LLM for my own MRI results and it was nearly spot-on, verified by a subsequent visit to a specialist. YMMV as they say. But I do believe we are entering the era where LLMs are considering past interactions and long context windows to inform it of personal preferences and history in order to output more accurate results.
Technically it is a a possible infinite sentence, as it can mean both "terrible" and "bottom", hence the sentence would be "terrible terrible terrible terrible bottom", which is colloquially valid.
Except when it does... CodeRabbit will review my PRs sometimes complaining about code written by Copilot or Augment. They should just fight it off between themselves.
I've been using Augment lately in dbt, PHP, and Typescript codebases, and it has been producing production-level code, it has been creating (and running!) tests automatically, and always goes through multiple levels of review before merge.
Posts like these will always be influenced by the author's experience with specific tools, in addition to what languages they use (as I can imagine lesser-used languages/frameworks will have less training material, thus lower quality output), as well as the choice of LLM that powers it behind the scenes.
I think it is a 'your mileage may vary' situation.
I had the same issue described in the article... how do you choose a community?
It was the first question I had when looking into Mastodon, and a few minutes in I closed the tabs.
I don't want to choose a community, I want a single place/domain I rely on, I don't care if the backend is decentralised, I want the entry as a new user to be as low as possible, I need to understand the product in a few sentences.
They lost me as a potential user, I wonder how many more they lost. That entry barrier (just as with UX / registration forms) has to be as low as possible.
Indeed, as long as we can export data I wouldn't mind too much. Worst case you can write your own tool to represent the data in a visual format you desire. I think the columnar structure of Notion (which collapses on mobile) is quite neat.
The only thing I'm scared of is I've started writing a book (in Notion), and it would be a shame if something happens to it due to unrecoverable data loss...
Absolutely love Notion for the aspects mentioned in the article; I love how I can cluster everything together (work, life, etc.)
From short term planning (templates for my week which I copy every Sunday to start a fresh week - these templates are a 7 day todo list (in columns) with a link to my main calendar, project 'kanban' boards, and a linked "general todo" list for things that don't fit in the week and keep dragging on)
After being addicted to scheduling everything in a calendar (for about 5-6 years), and having to drag items I didn't complete to the next day every single day, working with templates (and linked lists / embedded sections) in Notion is really a game changer. I've tried many other to-do tools (like Wunderlist which I loved before it came Microsoft To-Do, which I still gave a chance but had too many bugs).
Notion is just a game changer plain and simple, I hope they never break it, this is the only tool I have come to love and trust to keep my entire life in.
This is nostalgic, I spent countless hours in MPT as a kid. I moved on to sequencers around 10 years ago, but I remember trackers fondly, making music felt a bit like coding.
The intersection between Geoguessr and making music; I started a series called Making music on Geoguessr a few years ago, and since then have become quite passionate about the game and learning geography.
I recently started a website that combines StreetView scenes with part of it generated by DALL-E - thisstreetviewdoesnotexist.com - also forced myself to learn a little Svelte for that… React had been my previous go-to when dabbling in front-end.
Warning: It can get wild, lower volume... Tried out a bunch of samples and by slightly tweaking some parameters you can end up in overdriven white-noise hell depending on the "brain" + samples.