Riny
My feedback
11 results found
-
96 votes
An error occurred while saving the comment Riny
supported this idea
·
An error occurred while saving the comment Riny
commented
Context is a real disaster and a Lumo 2.0 regression. Messages of “context length exceeded” appear even on 10% of token capacity.
An error occurred while saving the comment Riny
commented
Lumo 2.0 has been advertised to handle larger chats and files. However, the token capacity is still the same old one as before, namely 128K (~ 90.000 words, 10MB). Nothing changed in that. So there is no such improvement. Even worse: Lumo’s thinking (memory) consumes loads of tokens, regardless of the mode, so that new function decrease overall capacity. Large files accepted in previous versions are rejected in 2.0. A downgrade. And despite an extensive Support ticket over months these issues are not solved at all. In short, I don’t get what I’ve paid for.
-
4 votes
An error occurred while saving the comment Riny
commented
I found out that "Optimize memories" in the Memory settings tab, can significantly reduce the impact of memory on the chat context usage. With memory "on" the application automatically adds memory items across chats. In my case ~4100 items, containing ~89K words, which hit the chat ceiling instantly. Using the optimize function decreased that to 116 items and ~2500 words. This created over 90% chat space. However, I advised Support to lift the token capacity to a minimum of 500K.
An error occurred while saving the comment Riny
commented
On fixing, Proton may consider to increase the context space significantly. Compared to many other AI’s, Lumo has little tokens (128K). For intensive tasks, including uploaded large files, a minimum of ~500K tokens would make the workflow much smoother.
Riny
shared this idea
·
-
1,047 votesRiny
supported this idea
·
-
371 votes
An error occurred while saving the comment Riny
commented
I’m using the Brave browser extension which creates a desktop shortcut. Works fine. Though a real desktop app would do better likely.
Riny
supported this idea
·
-
411 votesRiny
supported this idea
·
An error occurred while saving the comment Riny
commented
After contact with Proton Support these are the currently supported file types within Lumo.
pdf
doc, docx, odt
rtf
xls, xlsx, csv
ppt, pptx
txt
log
md, markdown
html, htm
latex, tex
rst
css
js, mjs, jsx, ts, tsx, json
xml, yaml, yml, toml
ini, cfg, conf, properties, env
py, java, cpp, c, h, hpp, cs, php, rb, go, rs, swift, kt, scala, clj, hs, ml, r, sql
sh, bash, zsh, fish
ps1, bat, cmd
dockerfile, makefile, cmake, gradle, maven, sbt, cargo
lock, gitignoreThese are all text based files. Proton could not provide a time frame to implement more file types in the future, depending on customers reports.
-
1,333 votes
An error occurred while saving the comment Riny
commented
In the Windows desktop app there is a search option available, but in the iOS app for iPhone and iPad it’s not.
An error occurred while saving the comment Riny
commented
I need to keep an overview on certain similar events. Now I need to scroll thru my agenda to find them one by one. This is extremely time consuming.
Riny
shared this idea
·
-
257 votesRiny
supported this idea
·
-
386 votesRiny
supported this idea
·
-
497 votesRiny
supported this idea
·
-
6 votes
An error occurred while saving the comment Riny
commented
After contact with Proton Support these are the currently supported file types within Lumo.
pdf
doc, docx, odt
rtf
xls, xlsx, csv
ppt, pptx
txt
log
md, markdown
html, htm
latex, tex
rst
css
js, mjs, jsx, ts, tsx, json
xml, yaml, yml, toml
ini, cfg, conf, properties, env
py, java, cpp, c, h, hpp, cs, php, rb, go, rs, swift, kt, scala, clj, hs, ml, r, sql
sh, bash, zsh, fish
ps1, bat, cmd
dockerfile, makefile, cmake, gradle, maven, sbt, cargo
lock, gitignoreThese are all text based files. Proton could not provide a time frame to implement more file types in the future, depending on customers reports.
Riny
shared this idea
·
-
676 votesRiny
supported this idea
·
I found out that "Optimize memories" in the Memory settings tab, can significantly reduce the impact of memory on the chat context usage. With memory "on" the application automatically adds memory items across chats. In my case ~4100 items, containing ~89K words, which hit the chat ceiling instantly. Using the optimize function decreased that to 116 items and ~2500 words. This created over 90% chat space. However, I advised Support to lift the token capacity to a minimum of 500K.