too big to deliver simple solutions? youre making way too much sense and this would die in committee or be replaced when someone new needs to justify themselves by launching a new product to supplant an existing one.
The labyrinth of ways to interact with the temporal path between pages is a cluster. History, bookmark, tab, window,, tab groups.
There are many different reasons to have a tab, bookmark, or history entry. They dont all mean the same thing. Even something as simple as comparison shopping could have a completely different workflow of sorting and bucketing the results, including marking items as leading candidate, candidate, no, no but. Contextualizing why I am leaving something open vs closing it is information ONLY stored in my head, that would be useful to have stored elsewhere.
Think about when you use the back button vs the close tab button. What does the difference between those two concepts mean to you? When do you choose to open a new tab vs click? There is much to be explored and innovated. People have tried radical redesigns, havent seen anything stick , yet.
If you expect the browser to help you manage your various workflows beyond generic containers (tabs, tab groups), then you become tied into the browser's way of doing things. Are you sure you want that?
I'm not saying your hopes are bad, exactly. I'm interested in what such workflows might look like. Maybe there _is_ a good UX for a web shopping assistant. I have an inkling you could cobble something interesting together quite fast with an agentic browser and a note-taking webapp. But I do worry that such a app will become yet another way for its owner to surveil their users in some of the more accurate and intimate areas of their lives. Careful what you wish for, I reckon.
In the meantime, what's so hard about curating a Notepad/Notes/Obsidian/Org mode file, or Trello/Notion board to help you manage your projects?
shopping assistant was a specific example, but in the process of research, brainstorming, etc theres a bunch of different ways id like to see visualization and record of how i got somewhere, what was discarded, summary of what was retained, whats coming next, options for branching.
the web is a document structure, but browsing it doesnt need to be linear.
We had that ability in Firefox, through XUL. Then it was removed. Tree Style Tab addon doesn't work properly to this day because of this.
We had that ability in Chrome, through Chrome Apps. You could make a browser app, load pages in webviews, with the whole browser frame customizable. Then it was removed.
We had an ability to make a new innovative browser, until Google infested all the standartization committees, and increased complexity of standards on a daily basis for well over a decade. Now they monetize their effort on making Chrome by removing adblockers and enforcing their own ads, knowing full well that even keeping a fork that supports manifest v2 is infeasible for a free open-source project.
There is no way forward with the web we have right now. No innovation will happen anymore.
I am by no means an expert art historian but I'm not sure I 100% follow the logic of their conclusion.
"pentimenti, or correction marks, a common indication that “a painting is not a copy, but an original work created with artistic freedom.”"
How often are they analyzing copies made by 12 year old. Is a 12 year old more likely to have made errors or drifted from the source during the process of the copy? Could the corrections be attempts to bring the painting closer to its source, because it wasnt close enough?
If you're copying from another painting, you don't paint a figure and then decide to move it a centimeter to the left. But original paintings often have such changes.
Can I ask, did you pull all this from subtitles and scripts?
Quite frankly, the corpus of film criticism might be a better source. Analysis of context, interpretation, intent, result, success, failure, contention might be more useful to shape a story than the literal story itself. It's asking too much of current gen LLMs to be able to synthesize motif at a higher abstraction. In my experience they get stuck on specific examples and crudely stitching pastiche together, instead of working in the blank empty space between thoughts and ideas.
I also am unsure that "describe your opening scene" is the best place to start. I may have a story that has a tangible beginning, middle, end, and want to fix certain elements along the way. "This must happen to start act 3" so the story coherently steers correctly towards goals.
but google did erode trust in their product, and the american government went after them, so they "made it more obvious" which still really didnt change that most people dont care if something is sponsored and just look at the first result.
it's something that continually needs to be reenforced again and again. somebody will be made example of.
you dont know what you dont know. walking into hockey for the first time, you may think you should be looking for the puck.
but really, what you want to look for is how the players are moving. it's sort of a "which one is different from all the others." one person will clearly be moving in a completely unique way, as the others chase them or vie to get open or get in somebodys way. to acomplish this identification, youre looking at their legs, shoulders, hands, feet, and heads.
The same applies to context vs a database. If a reasoning model makes a decision about something, it should be put off to the side and stored as a value/variable/entry somewhere. Instead of using pages and pages of context, it makes sense for some tasks to "press" decisions that become more permanent to the conversation. You can somewhat accomplish that with notebooklm, by turning results into notes into sources, but notebooklm is insular and doesnt have the research and imaging features of gemini.
And also, in writing, writing from top to bottom has its disadvantages. It makes sense to emulate human writing process and have passes, as you flesh out, and conversely summarize writing.
Current LLMs can brute force these things through emulation/observation/mimicry but they arent as good as doing it the right way. Not only would I like to see "skills" but also "processes" where you create a well defined order that tasks are accomplished in sequence. Repeatable templates. This would essentially include variables in the templates, set for replacement.
> Not only would I like to see "skills" but also "processes" where you create a well defined order that tasks are accomplished in sequence. Repeatable templates. This would essentially include variables in the templates, set for replacement.
You can do this with Gemini commands and extensions.
The template would more define the output, and I imagine it more recursively.
Say we are building a piece of journalism. First pass, do these things, second pass build more coherent topic sentences, third pass build an introduction.
Right now, the way that models write from top to bottom, the introduction paragraph seems to inform the body, and then the body is just a stretched out version of the intro. Whereas how it should work is the body is written and then condensed into topic sentences and introductions.
I find myself having to baby models, "we are going to do this, lets do the first one. ok now lets do the second one, ok now the third one. you forgot the instructions, lets revise with the parameters you were given initially. now lets put it all together."
I'm babbling, I just think these interfaces need a better way to define "lets write paragraph 4 first, followed by blah blah" to better structure the order in which they tackle tasks.
reply