A simple self-organizing tool for text.
initial prototype of audio lock feature for longer recordings and of diarization (meeting aka multispeaker transcription). Unfortunately not sure how to solve the problem of ios/pwa falling asleep!!! https://bugs.webkit.org/show_bug.cgi?id=254545
title
Token Count 48/10000. AI functionality will not work for text longer than 3200 tokens.
To adjust behavior of changelog, edit Prompt Settings
Crazy speed improvement on speech to text. Switched speech to text transcription api to Groq Whisper-3-large. It falls back to OpenAI api (whisper 2) which should make everything a little more reliable with that redundancy. I tried whisper-3-large-turbo, and while faster, doesn't seem quite as accurate. Also added voice activity detection. Basically it should prevent the random hallucination or jibberish if you submit empty audio. VAD is shockingly tricky to get right. Not absolutely sure this is right. But testing live!
Token Count 117/10000. AI functionality will not work for text longer than 3200 tokens.
regression fix from yesterday, affected new accounts for a few hours. small changes to ai/edit feature. added spinning indicator. Switched ai/edit feature to Gemini Flash model. It's just faster and seems on par with 3.5 haiku. Small bug fix in that feature too where html entities would sometimes get throw in.
Token Count 67/10000. AI functionality will not work for text longer than 3200 tokens.
fixed help drawer -- it didn't scroll on desktop and sometimes it was needed. some backend adjustments and refactoring to embeddings. Don't expect any visible changes from this. some very subtle improvements to search voice ai/edit feature uses claude 3.5 haiku -- much improved!
Token Count 59/10000. AI functionality will not work for text longer than 3200 tokens.
prompt settings button, clean up -- consistently use svg.
Token Count 12/10000. AI functionality will not work for text longer than 3200 tokens.
added mouse over hovers to most all the links lol. after 2 years.
Token Count 17/10000. AI functionality will not work for text longer than 3200 tokens.
added underscore style markdown parsing for bold and italic
Token Count 9/10000. AI functionality will not work for text longer than 3200 tokens.
improved the fetching code for csrf. Basically send the request sooner, so there is much less chance of a csrf error.
Token Count 26/10000. AI functionality will not work for text longer than 3200 tokens.
Adjusted amount of context llm gets for natural language dates prompt. Should be an improvement in accuracy. fixed regression, prompt settings were mistakenly hidden in a quest for optimizing loading speed. :|
Token Count 38/10000. AI functionality will not work for text longer than 3200 tokens.
some caching bugs -- too aggressive caching. Right click on entity to change type slightly more reliable, but not quite 100%.
Token Count 25/10000. AI functionality will not work for text longer than 3200 tokens.
past and future sections removed from mobile screens. I never used it. More likely to use calendar to change days. And slight adjustment on past/future layout (nothing notable, just hoping it fixes occasional layout bug).
Token Count 43/10000. AI functionality will not work for text longer than 3200 tokens.
more prefetching on mouseovers and click on mouse down. FASTER woo also fixed a bug where the page would sometimes scroll with the quick toggle button on a line.
Token Count 35/10000. AI functionality will not work for text longer than 3200 tokens.
fixed a rendering bug on iOS when spaces would push to the next line. seriously this one was starting to drive me insane. I hope it's all fixed lol. I will never abandon the <textarea>!
Token Count 42/10000. AI functionality will not work for text longer than 3200 tokens.
persistent prompt pages now work -- that is the block for today is copied from the previous day it was edited, the same way it does on the home page. persistent prompts also no longer show up on any future day pages. That doesn't make sense.
Token Count 51/10000. AI functionality will not work for text longer than 3200 tokens.
added ability to "add to home" for any prompt page. Each prompt page now has it's own manifest.json that allow for this.
Token Count 28/10000. AI functionality will not work for text longer than 3200 tokens.
If you press and hold the little button to the left of the line, it'll do the same as ctrl-shift-return, ie strike through by default. Great for mobile.
Minimum viable offline support. Edits are stored in local storage and cleared once synced. Also added a very basic service worker that caches static files. Appears to load faster for those who ‘add to home’ and use on mobile.
Token Count 46/10000. AI functionality will not work for text longer than 3200 tokens.
error fixed on similar block feature for empty blocks. Inconsequential, but feels good to make errors in the logs go away.
removed any dependencies on gpt 3.5 duplicate backlinks where the context is identical are filtered to only show one -- on the home page at least.
Token Count 33/10000. AI functionality will not work for text longer than 3200 tokens.
added title text to block settings button polished the copy button a little more, added quick animation on click and cleaned up the code a little.
Token Count 30/10000. AI functionality will not work for text longer than 3200 tokens.
minimum viable copy button added. need improvement, but seems to work. moved save indicator and made it fade out
Token Count 22/10000. AI functionality will not work for text longer than 3200 tokens.
stripe/subscription sync errors fixed subscribe banner added back to free accounts. it went missing from a template upgrade regression a while back. django 5 to 5.1 upgrade
Token Count 37/10000. AI functionality will not work for text longer than 3200 tokens.
So stoked! There's been a nagging rendering error when a name or company was tagged within a url. Basically random occasions would cause crazy overlapping text during editing. Swapped anchor tag for span during edit mode. Cross our fingers, no more weirdness. It's interesting, chrome seems to treat anchor slightly different. Safari seems to do it better.
Token Count 72/10000. AI functionality will not work for text longer than 3200 tokens.
slight adjustment and improvement to date tagging prompt.
Token Count 10/10000. AI functionality will not work for text longer than 3200 tokens.
made some changes to how manifest.json is served -- now fully loaded into memory and served static, hopefully as efficiently as possible. I think it was causing a db hit and contributing to crashing during hacker news traffic.
csrf error fixed when on prompt page and trying to adjust block title or block settings. super big rewrite and expansion of help/docs page. Added to menu button on computer view as well, even though it's redundant with bottom left link.
Token Count 47/10000. AI functionality will not work for text longer than 3200 tokens.
some huge fixes on roam import. More robust and hoping urls correctly load now after the import.
Token Count 19/10000. AI functionality will not work for text longer than 3200 tokens.
login with google in one click -- instead of it previously going to another page to then click again. Nice quality of life improvement.
bug fix for accounts with a username that started or ended with an underscore significant fixes with roam research import tool. Handles conflicts and duplicates much better. additional templates moved to jinja -- faster, but not much of a noticeable change.
small layout adjustments. Better alignment of user name and audio input button. small fix with caching. it would take a hard refresh for a block to disappear after you delete it. Now it properly clears the cache and it goes away. small type error in frontend fixed. don't think it was causing any issues.
Token Count 62/10000. AI functionality will not work for text longer than 3200 tokens.
removed unlinked blocks from datatype pages. it's not needed and saves a db query.
Token Count 18/10000. AI functionality will not work for text longer than 3200 tokens.
beta of roam research json import feature added to menu
tiny bugfix when archive is empty, error at endpoint for new accounts.
Token Count 16/10000. AI functionality will not work for text longer than 3200 tokens.
fixed regression where 'today' could be tagged as a natural language dates since the recent update in date parsing. In general, backlinks should not be created to the day of the note.
Front end bug fix, where sometimes audio buttons would be hidden on mobile after you press record.
Token Count 20/10000. AI functionality will not work for text longer than 3200 tokens.
bug fix -- prompts would be missing older blocks due to template mistake. bug fix -- doesn't wig out (scroll weirdly) trying to make a selection on mobile.
Token Count 34/10000. AI functionality will not work for text longer than 3200 tokens.
fixed a couple javascript errors on landing page. switched person and company entity recognition to gpt4o-mini. search/ask is smarter! :) some lines of code deleted that were causing ai attributes to not work, ie recognizing phone numbers on existing people wasn't reliable. Still needs work and testing. slight adjustment to automatic date filtering in search/ask as it was sometimes falsely finding a date
Token Count 81/10000. AI functionality will not work for text longer than 3200 tokens.
date handling has been gutted. And largely turned over to claude 3.5 Sonnet. Seems good so far. Still some optimizing to do, but not slower and seemingly much more reliable than the rule based methods. Previously it was a combo of chatgpt 3.5 and rule based methods. But it would fail a good number of tests and was a patchwork of if statements. And got quite slow. The new method looks for any date entities on the server, and if any are found, claude is called to intelligently decide the dates. let me know if it fails you! keizo@grugnotes.com
Token Count 132/10000. AI functionality will not work for text longer than 3200 tokens.
currently experiencing openai api issues/rate limits. May break ai entity identification and search. fixed The core ai functionality has been gutted. Date recognition is now entirely ruled based with some help from small natural language libraries to determine past or future dates. many tests are good need more bad with holidays llm/chatgpt still responsible for tagging people and companies. could use additional testing still a lot of room for basic speed improvements fixed funky scroll on mouse click bug
Token Count 107/10000. AI functionality will not work for text longer than 3200 tokens.
templating issue fixed if you had a mention on your home page grr. weird bug on persistent blocks going blank -- just refresh and it comes back, but annoying. will investigate tonight. fixed a server side error (I think this was it) update it is not! but i understand the problem a little more caused by polling an unsaved persistent block... gotta love sync problems fixed (I think) css adjustment for the buttons to the left of the lines. better on mobile, same on desktop.
Token Count 110/10000. AI functionality will not work for text longer than 3200 tokens.
Some new front end code that helps with more natural scrolling and keeping the text within view -- both on computer and in ios. Typo fix on template.
Token Count 32/10000. AI functionality will not work for text longer than 3200 tokens.
Finally switched to newer embedding model 'text-embedding-3-large' for search functionality. Seemingly better and faster search results already, but still needs tuning. fixed ai breakage on new accounts caused by this ~12 hrs later New templating backend deployed. No visible changes, but slight speed improvement, especially for more complex or long pages.
small bug fix in find/create prompt search. It was broken if the prompt was set to 'generate_today' but not show on this day... if that makes sense. Also now, when a block is already existing on the day, it correctly sets focus to that block. small bug fix -- html properly escaped on archived blocks (anything older displayed as plain text for rendering speed)
Token Count 77/10000. AI functionality will not work for text longer than 3200 tokens.
Search and similar prompts features fixed from the Pinecone vector database issues.
Token Count 15/10000. AI functionality will not work for text longer than 3200 tokens.
Vector database service Pinecone is down as their service has gone through some breaking changes. Will take 1-2 days to update. Sorry! This means search is failing and similar prompts. :(
Token Count 39/10000. AI functionality will not work for text longer than 3200 tokens.
on a prompt page, blocks were listed first, then backlinks. Now they are listed mixed together in order of original block date. Works, but still needs ui and speed optimizations.
fixed a caching bug. if you delete a block on the main home page, the cache now correctly clears. For the past few weeks, it would appear to no be deleted until a full refresh or something else changed.
Token Count 44/10000. AI functionality will not work for text longer than 3200 tokens.
fixed the crazy bug from yesterday where new line or lines added at the start of an existing note would not save. Weirdest thing ever. Browser would seem to remove new lines unless the html started with a new line. Basically my template needed to be <textarea> text</textarea> instead of: <textarea>text</textarea> crazy right?
Token Count 71/10000. AI functionality will not work for text longer than 3200 tokens.
new model and prompt deployed for ai/edit voice editing feature. Uses full context of the note -- it's a lot better, but I'm sure it's not perfect. Also found a crazy bug where a new line added to the start of an existing note doesn't save. Like wut -- need investigation asap.
Token Count 65/10000. AI functionality will not work for text longer than 3200 tokens.
Updated copy on landing page. Small adjustment on revision history so the text is selectable.
brotli added back to landing page
Token Count 8/10000. AI functionality will not work for text longer than 3200 tokens.
bug fix with similar prompts feature that would cause them to never load -- I think related to django upgrade some weeks back.
Token Count 24/10000. AI functionality will not work for text longer than 3200 tokens.
More major issues fixed for usernames with capital letters in it. Future, Past, Archive may not have been loading and search issues as well. Grug take long time! But work now. Some backend updates. Switched PyMYSQL to mysqlclient. Not sure if it makes a speed difference, but I'd like to think it's an improvement. Also laid groundwork for websockets if needed, though note used for anything yet.
Token Count 88/10000. AI functionality will not work for text longer than 3200 tokens.
Ooof, fixed a csrf error on audio recording -- partially broken since april 7th.
Token Count 21/10000. AI functionality will not work for text longer than 3200 tokens.
fixed a few endpoints that were no longer getting compressed due to yesterdays upgrades.
first deploy migrating from Django 3.2 to 5! and gunicorn to uvicorn server! Welcome to modern web dev Grug. We have server sent events -- it means slightly better device sync. You can try type in the same note on two different devices. This was a massive deploy. Hopefully nothing fundamentally broken, but Grug watch closely. 😅 Door open for many more improvements. 🤗
Token Count 85/10000. AI functionality will not work for text longer than 3200 tokens.
fixed drag and drop blocks that were broken last week from revision history update...
More aggressive caching on home, usually clearing cache on write. Shooting for sub 100ms server response. Actually, there were like 4-6 deploys today with various bugfixes of the caching.
A bunch more orm/sql query optimizations. Less queries on load. And a couple indexes added. And importantly pretty significant improvement on save function. SPEED! yay. Some adjustments to html to improve load speed.
Token Count 41/10000. AI functionality will not work for text longer than 3200 tokens.
A few small and subtle query optimizations. Very small speed improvement.
Token Count 13/10000. AI functionality will not work for text longer than 3200 tokens.
Minor adjustments to caching so stale data is avoided. Better handling of pasted text and auto adjusting the textarea height.
Token Count 23/10000. AI functionality will not work for text longer than 3200 tokens.
Speed update! Better preloading and some initial client side caching. Little snappier responses. 😍 wondering what I broke 😅🤓
minimum implementation of edit 'revision history' for each block deployed. Needs work and needs diff formating still. Not functional on mobile yet, but soon!
Token Count 31/10000. AI functionality will not work for text longer than 3200 tokens.
Small bug fix and reliability improvement to search/ask. Alteration and hopefully improve to how known entities are relied on vs chatgpt entity recognition. I'm sparse on details here, but changes deployed to production! :)
A bunch of backend work on how backlinks are saved. Backlinks now have a creation date that will persist through saves and minor changes. It's not much of a big deal right now, but I'm hoping it can provide some additional context in the future, to help identify stale tasks for example. Backlinks are copied to new days on persistent blocks. Persistent blocks remove lines that are strikethroughed out the next day. That is, if the line is surrounded by ~~, it gets deleted. Will be adding this as a user setting soon. Small front end rendering fix.
Token Count 122/10000. AI functionality will not work for text longer than 3200 tokens.
oh man, fixed a bad bug. Tags from hashtags and brackets were not properly creating backlinks for a while. Shaved 6 queries off the home screen load. Probably not a noticeable speed difference, but it brings joy to my heart.
Token Count 50/10000. AI functionality will not work for text longer than 3200 tokens.
Encoding issues kinda fixed with latest version of chrome. Everything was rendering as symbols. Now seems ok.
Made the headers sticky on the datatype pages.
such a dumb bug to last this long. Capital letters in usernames no longer break urls.
right clicking on the quick toggle button does the equivalent of ctrl-shift-return -- the default being markdown strike through around the line. Already found a cursor positioning bug, will fix later this week lol.
Sorry! there was a major bug since mid january that made natural language dates no longer link -- or actually they were linked, but it wasn't visible on that day. It should be fixed now.
Right clicking on a link brings up a context menu that allows changing the datatype. Minimum viable features! Most useful if AI gets it wrong. Also allows creating autotags. Needs to be in view mode, it doesn't make sense in edit mode. Unlinked mentions or backlinks are show at the bottom of prompt pages. WIP. There are still some edge cases and bugs related to these features!
Token Count 91/10000. AI functionality will not work for text longer than 3200 tokens.
Added Inter and Roboto as fonts.
one line bug fix to prevent possible creation of two unique blocks within the same prompt and date. Which should be only possible if you set a title. In this case, the path was created with a timestamp which shouldn't be possible.
small bug fix where ai tags could occur within existing manual links or urls
Token Count 14/10000. AI functionality will not work for text longer than 3200 tokens.
fixed a diff match patch error that caused some sync errors around emoji.
First deploy of quick toggle ui feature that adds the ctrl-return shortcut as a clickable feature on desktop and on mobile.
drag handles moved to top of blocks
Token Count 7/10000. AI functionality will not work for text longer than 3200 tokens.
Fixed some formatting issues from dark design update, probably a dozen or so little tweaks. Fixed some issues on date views where 'persistent blocks' wouldn't display.
Darker, but cleaner design deployed. Smaller text on mobile.
fixed a bug. If two browsers or devices were open. And the block was brand new, ie never saved, typing in one would not sync to the other with out a refresh. Now it should.
Some tests written, and non-visible improvements/bugfixes to sync. Chasing one last bug where you would lose a few words on save. Grug saw maybe 3x a month. Grug think we got it! But needs battle testing. Slight alteration to speech to text ai/edit prompt. Handles some situations a little more consistently. UnboundLocalError on search bug fix. Small font change to make date and prompt filtering more obvious during search.
Token Count 94/10000. AI functionality will not work for text longer than 3200 tokens.
small ui updates, replaced some emoji with svg started work on save history ui, incomplete
small bug fix on prompt settings form where the textarea formatting was bad
implemented 'generate on days'
Token Count 6/10000. AI functionality will not work for text longer than 3200 tokens.
Changed favicons & app icons to new logo. Draft privacy and terms are online. Made 👉, ✅ default as autotags on new accounts.
Some optimizations to javascript and stopped loading the archive at bottom of the page on mobile only. It was causing performance issues. added semantically similar blocks on individual block pages. minimum viable feature. not sure how useful yet.
some small formatting adjustments with new logo fixed on window resize bug where the textarea would not correctly size fixed some type error bugs in search fixed formatting on password reset page
landing page update and logo change!
First deploy with autotags implemented.
Fixed bug introduced on oct 22 where speech to search and speech to find broke. :|
Added links to the day headings under "past" and "future". Changed the permalink style from an anchor emoji to / Mon xx. It's a little weird, but I think I like it better than the emoji. Maybe I'll consider a lone #, we used to do that for permalinks in the old web. Blocks are unique by the url now. The improvement here is that there can be more than one block in the same prompt on the same day -- if one is given a 'title'. Basically this makes it function like a wiki much more effectively. More work to be done. It's now possible to create a prompt with only an emoji or with emoji's in it. It will convert to a text string that works in the url. However, it was mainly a bug fix and it only works in the backend. More work to be done on the front end to make it a functional feature. #TODO
Token Count 187/10000. AI functionality will not work for text longer than 3200 tokens.
Another improvement on block ordering -- new blocks created are always appended in whatever column the prompt last had or default to column 3. The vertical row ordering is unique to each day. Column is universal or at the prompt level. Fixed funky ios bug where links would need to be touched twice before they would go... iOS devices no longer tres to focus on loading -- since they keyboard can't come out because that's the way iOS works. But at least now, links and stuff on Daily Notes or wherever work on loading. bug fix -- block pages would break if the prompt didn't exist yet.
Token Count 121/10000. AI functionality will not work for text longer than 3200 tokens.
found another sync bug! But also may have fixed it today. Added another check to prevent duplicate requests. Optimistic this helps a great deal. increase the clickable area by 5px around AI generated tag/links. Nice ui improvement!
improved audio record button response speed after you get microphone permission from the user. The trick was removing noice cancelation and auto gain things from MediaRecorder set up. Whisper speech to text is so good, don't think it matters there will be no on device noise reduction.
Token Count 56/10000. AI functionality will not work for text longer than 3200 tokens.
fixed some accessibility things, and increase contrast for a lot of the ui
some refactoring work on sync. Reduced extra sync requests by slight bit. And now server responds with correct hash when a block doesn't exist. There is/was a bug here where sometimes server would overwrite user that happens to me 1-2x a month. Would lose a few words perhaps from seconds ago. This might fix -- but yet to confirm. :|
Token Count 75/10000. AI functionality will not work for text longer than 3200 tokens.
few hours focusing on speed -- major one is deferring all javascript. Much improved loading speed. Small improvements and error fixes.
fixed a bug where past & future were not formatting correctly on load
fixed bug where search/ask would break when extra spaces were present
first deploy of ai/edit via audio feature. Experimental... but cool! bug fix: adding a prompt to automatic speech recognition from the prompt's settings caused an error. bug fix: legacy code on settings page caused an error when changing automatic speech recognition settings
improved positioning of past and future sections at 2 column width
small error bug fix where the entity recognition wouldn't work right away, it would take a refresh or two, on new accounts.
a new user created a username with a space, and it broke the account. Fixed the validation bug.
fixed a formatting issue where column 2 (daily notes usually) would overlap today's mentions
it shouldn't matter much in daily use, but refactored and improved caching of embeddings -- basically more efficient :) very low chance, but also made sure no possibility of duplicates in "similar prompts" on prompt pages.
removed all the prompt settings from the settings page. There is no real need since prompts are drag and drop sortable now. increase contrast on block and prompt settings. Removed a click by direct linking to prompt settings from block settings. Not great, but an improvement.
Token Count 53/10000. AI functionality will not work for text longer than 3200 tokens.
Improved ordering of blocks when it transitions to 2 col and 1 column from 3.
Better word wrapping, and fixed a rendering error with long words. We no longer break-words. Just wrap on overflow. Little bit of javascript refactoring. Fixed the padding/height being too short issue when the page is first loaded.
little javascript refactor, fixed a bug that was calling ai endpoint twice!!!
Finally implemented drag and drop moving of blocks. This changes the column and ordering at the 'prompt' level so the view will be the same on any day.
Did some refactoring of some llm prompts and test code to make converting singular/plural prompt names more robust. Mostly not noticeable, but feels good to get done!
some ui fixes when there is a pop-over style thing, ie search. Fades out properly and no more pointer affecting things in the background issues.
Some small rendering error bugs fixed when there's punctuation around natural language dates. Also fixed rendering error where inline style wasn't removed correctly on focus out. Surfaced as overlapping text. Slight ui improvements on speech to text. On desktop, trigger to get microphone access requires 100 ms mouse over, hopefully fewer accidental triggers. On mobile, got initialization response a little faster -- ie nicer to use.
Token Count 80/10000. AI functionality will not work for text longer than 3200 tokens.
small ui changes -- home button added at bottom left on mobile. Help button moved to menu. wider table widths on prompt pages for attributes
bunch of small bug fixes w/css and ui. Moved the signup link to be at bottom. Fixed pull to refresh -- as it was doing it anywhere on the page. Adjusted css, so textareas don't interrupt scrolling Can now have prompt level keywords for speech to text.
Token Count 57/10000. AI functionality will not work for text longer than 3200 tokens.
deployed mvp of speech to text. This took a while, and did quite a bit of experimentation.
Cursor placement with multiuser editing is getting pretty good. Patches should get applied and the cursor or selection does the right thing.
Small update to search prompts to consider todays
Added a web manifest, so "add to home" runs as a progressive web app -- meaning the url bar is dropped and it loads from cache more instantly. This is possible now that there is sync functionality. HOWEVER, there is no offline support yet -- but the path is closer. Some small ui improvements and ui bug fixes with that, more to come.
more work on sync. A few bug fixes so that things should converge between all clients.
More work on sync -- made a pretty significant change. Let's call it *semi realtime sync*. It's not google docs level collaborative, but updates do happen and things mostly converge. Using differential sync. For Grug purposes, it does the job -- and creates a path towards multiuser notebooks and tracking changes over time. still an mvp feature still need to match cursor position when updates happen some odd things happen if actually trying to edit exactly at the same time, but this is very much not typical use case.
Token Count 109/10000. AI functionality will not work for text longer than 3200 tokens.
improved sync. some changes to optimistic locking. Should see far less false errors
changed the css technique on underlines (uses border now) for ai links -- this was a major source of rendering errors. improved front end -- fixed some rendering errors on resize and refactored code to be more efficient
Token Count 45/10000. AI functionality will not work for text longer than 3200 tokens.
fixed a front end error that came up from hidden characters
Token Count 11/10000. AI functionality will not work for text longer than 3200 tokens.
fix some breakages from open ai updates change to optimistic locking. No longer relies strictly on the last modified for the locking, but an integer. This should fix the occasional out of sync error that would occur when saves would happen back to back and htmx hadn't return the server last modified time. The save count is updated on the front end, so it should stay in sync and only go out of sync if another client updates it.
Token Count 90/10000. AI functionality will not work for text longer than 3200 tokens.
On prompt pages, the data fields will update after ai is called. So the page feels live. :)
search will now redirect to the 'date' view if you only type in a date. Things like aug 5, tomorrow, monday, a year from now, etc should all go direct to that page. fixed bug, find/create will add block to the date of the datepage it's currently on, instead of always today
ctrl-shift return keyboard shortcut for wrapping a line with ~~ or other characters. First version. Needs work to apply to selections.
ui improvements, better menu and datatype link formatting for both desktop and mobile. Started using alpine js... made subscriptions page visible in menu added ctrl-k short cut to move cursor to search and then find/create prompt and back to default focus if it a third time bug fix on find/create prompt where search results wouldn't disappear after hitting enter.
Token Count 70/10000. AI functionality will not work for text longer than 3200 tokens.
Implemented a simple warning when block length is over 3000 tokens. When getting primary entities, text will be truncated after 3200 tokens. Previously was not handled at all. #WIP
Updated the intro text on first login.
Fixed some more issues related to persistent prompts. When an empty persistent prompt was created, the main page would crash without an existing block. Fixed auto-focus on settings page. When creating a prompt from a data type page, the data type is set with more "confidence" so it will be recognized.
Token Count 60/10000. AI functionality will not work for text longer than 3200 tokens.
Fixed a bug or two related issues with "persistent" prompts. It was a significant problem with the Scratch Pad default!!! Deleting all notes would result in save failure. Fixed. Also removed some old behavior where persistent blocks would get copied to tomorrow. Now it should always copy from the past to today.
Token Count 64/10000. AI functionality will not work for text longer than 3200 tokens.
some small improvements on mobile search formatting. Better, not great yet.
better handling of llm mistakes and manual overrides of entities bunch of database optimizations htmx preload! faster.
search fix where natural language dates were not selecting local timezone.
rewrote landing page with updated copy bug fix on login where settings and sign out links would not show due to timezone issue
made search on prompt pages filter to that prompt only
search/ask grug... mvp feature deployed. This one took a while. Chatgpt based only when you ask a question. All the rest of the time, it presents semantic and keywords search results. When there is one clear best result, it'll be presented up top.
Token Count 58/10000. AI functionality will not work for text longer than 3200 tokens.
some corrections to natural language dates. fixed things like this past wednesday. before it was putting that as next week.
small front end bug fix where tags were still highlighted within a longer word. "Action" within extraction for example.
backend changes with ai prompts to use json instead of custom formatting. aiming to be a little more robust on random output from llm.
Token Count 27/10000. AI functionality will not work for text longer than 3200 tokens.
css improvements for mobile datatypes at bottom of screen fomatting fixes on block view bug fix where some blocks weren't show in archive. specifically where the prompt had setting generate in past checked.
fixed tiny front end bug where prompts got replaced with prompt capitalizations. So lower case company, might get capitalized and cause a rendering error.
pretty major deploy! major backend changes chatgpt api, makes costs manageable! and a lot faster! known entities are tagged from database! this major, helps ai perform better as well quite a few tweaks and improvements on the front end with tag highlighting less filter conflicts, as text is tokenized so we can manage the chaos better no double tagging -- longer tags go first a lot of refactoring
Token Count 92/10000. AI functionality will not work for text longer than 3200 tokens.
broke the date display in yesterdays deploy. fixed. on mobile -- made it so the space key tabs in when it's white space before the cursor. seems to work! best feature ever!
removed auto login/signup form, replaced with a simpler login form. Should fix any password manager issues, and prevent accidental account creation.
partial rewrite of filters/rendering front end. Fixes many rendering bugs when tags would interfere with each other. Text is tokenized before tags are highlighted to prevent html from getting jammed up.
Date:
Go to the day