Supermaven
@SupermavenAI
Followers
4,012
Following
19
Media
17
Statuses
218
Explore trending content on Musk Viewer
FREENBECKY AT 9ENT
• 1166011 Tweets
HAPPY ANNIVERSARY BTS
• 358643 Tweets
Namorados
• 342524 Tweets
Congreso
• 285456 Tweets
Ley Bases
• 264011 Tweets
Ciotti
• 214647 Tweets
Jerry West
• 145600 Tweets
$COOKIE
• 91744 Tweets
Elon Musk
• 86559 Tweets
The Logo
• 84744 Tweets
DIVINE PERFECTION SUNG HANBIN
• 83784 Tweets
Happy 11th
• 79265 Tweets
Reconquête
• 71574 Tweets
Zemmour
• 69286 Tweets
Sky TV
• 61006 Tweets
Rohit
• 60247 Tweets
#INDvsUSA
• 58427 Tweets
Kohli
• 57586 Tweets
Polis
• 53223 Tweets
Jamundí
• 50390 Tweets
Mancuso
• 38215 Tweets
Adventure Time
• 36865 Tweets
Powell
• 34399 Tweets
Tagesschau
• 27863 Tweets
Regular Show
• 20574 Tweets
Super 8
• 18328 Tweets
Bullrich
• 14442 Tweets
Trabajo Infantil
• 12756 Tweets
Dube
• 12619 Tweets
Thiago Motta
• 12196 Tweets
Inter Miami
• 11037 Tweets
Perrine
• 10685 Tweets
Pinned Tweet
We've advertised our 300,000-token context window. But can Supermaven actually use all those tokens to improve its suggestions?
In our new post, we evaluate Supermaven's long-context performance.
7
4
64
Our Neovim plugin is ready! Check our profile for the link to try it
15
10
104
We have a Neovim plugin ready (in beta). DM us or check our Discord to try it!
13
4
79
We've added a free tier to Supermaven!
It doesn't have our unique 300,000 token context window, but it still has a great model with unmatched latency. And it can see your current diff, so it understands what you're working on.
5
7
78
The Supermaven Jetbrains plugin has been submitted to Jetbrains for review and should be ready in a couple days.
We'd be grateful to anyone who wants to beta test the plugin - DM us if interested.
10
4
77
We deployed a new scheduler that reduces latency ~3x for the most challenging subset of queries:
4
2
70
Our Neovim plugin is ready!
We'd like to thank the community for contributing PRs to make the plugin more robust and easy to use.
5
9
60
Introducing Supermaven:
8
10
57
Supermaven 0.1.23 (VSC) makes a significant change to suggestions in the middle of the line. They will now display off to the right so your text doesn't move around as you're typing:
5
3
52
There is no longer a delay for indexing when using Supermaven with a new repository. Supermaven will now return completions immediately and run indexing in the background.
5
2
40
The Supermaven Jetbrains plugin is ready (in beta). We tried to DM everyone who messaged us about it but we got rate limited by Twitter, so you can access it here:
3
3
41
Supermaven for VS Code 0.1.31 supports enabling/disabling Supermaven for specific languages. For example, you can disable Supermaven in Markdown files.
7
1
36
We're excited to announce support for Jetbrains IDEs!
Thanks to all our beta testers who have helped work out issues with the plugin over the past weeks.
4
3
34
In addition to .gitignore, Supermaven now supports .supermavenignore to give you additional control over which files are indexed by Supermaven.
Syntax is the same as .gitignore.
1
2
30
We made changes to the backend that speed up building prompts, giving latency improvements up to 30ms depending on your repo.
1
1
23
Starting from version 0.1.33, Supermaven is disabled by default in files ignored by .gitignore, and these files will not be sent to our servers.
You can re-enable Supermaven in these files by clicking the status icon:
2
1
23
We added a Code Policy to our website to give customers additional clarity on the protection of their proprietary data. We do not train models on customer code.
1
2
22
Some users on Windows reported that the Supermaven extension would keep a blank terminal window open. We reproduced the issue and it is fixed in extension version 0.1.13.
2
1
19
Using Supermaven to write a simple toy program. You can see we get streaming completions from the Jetbrains plugin:
6
1
20
A long context window doesn't just help Supermaven look up function definitions - it also lets us learn your personal style and write code the way you would write it.
@SupermavenAI
is the only AI tool I've paid for. I never got much value out of GH Copilot. It's just too slow. I am able to type out what's in my head faster than what Copilot could suggest. This is not so with Supermaven. Not only is Supermaven faster, but it writes like me.
1
0
5
2
0
19
We made changes to Supermaven's handling of large diffs that should significantly improve quality and latency when making many changes or adding large files.
0
0
16
Do you use Vim or Neovim?
Vim
26
Neovim
111
I use neither
92
9
1
16
We fixed an issue with our inference kernels that caused corruption of model state under load, leading to incorrect/degenerate completions.
3
1
14
Supermaven had an issue that would cause completions not to show in large files (200KB+). This is fixed in VS Code extension version 0.1.22.
4
0
14
We changed Supermaven to be less conservative in suppressing suggestions in the middle of a line. To get these changes, update to extension version 0.1.17.
2
1
13
There was an issue with incorrect handling of carriage returns that caused Supermaven to fail to return completions on Windows in some cases.
This issue is fixed. It is a server-side change, so no update is required.
6
0
12
VSC extension version 0.1.47 improves trimming of redundant lines in situations with trailing commas
1
0
13
You could be the 3rd view on our Youtube channel
(Uploaded because twitter was compressing our video too much)
1
0
11
VSC version 0.1.49 and Jetbrains version 1.24 fix an issue where Supermaven wouldn't work in repositories with no commits.
2
1
13
There was an issue where Supermaven would consume a large amount of system memory when the repository contained large files. This is fixed in extension version 0.1.14.
Thanks to
@PhilipKung5
for reporting the issue.
1
0
10
Join our Discord to get updates on Supermaven and raise issues or feature requests:
0
1
8
@jullerino
Fixed
VSC extension version 0.1.47 improves trimming of redundant lines in situations with trailing commas
1
0
13
0
0
8
VSC extension version 0.1.48 fixes an issue where Supermaven wouldn't return completions if large files were recently committed to the repository
0
1
7
A common evaluation for a long-context model is the "needle in the haystack", where a piece of text (the "needle") is hidden within a large context (the "haystack"). The model is tested on whether it can retrieve the needle after consuming the entire context.
1
0
7
@lino_levan
It's for easy deployment and cross-platform support - most of the complicated logic is in the backend, which is all Rust.
0
0
5
VSC extension version 0.1.35 fixes an issue where too much whitespace would be deleted before the cursor in some cases.
0
0
5
In this task, the model is given a sequence of key-value pairs. Each pair occurs twice. The model is scored on whether it can use the first occurrence of the pair to correctly guess the value when it sees the pair a second time.
2
0
4
But the needle in the haystack task is made easier because the needle stands out from the rest of the text: to get it correct, the model only needs to remember the needle.
To give a harder test, we made a "dense retrieval" benchmark.
1
0
4
@ITLSR
@cursor_ai
We are planning to add a chat feature in the future.
Note Cursor and Supermaven are fully compatible since Cursor is a VSCode fork. You'll just want to disable Copilot++ so they don't conflict
2
0
3
Lastly, we plot prediction error as a function of token index on our internal code, averaging over several hundred orderings of the files to get a smooth result.
1
0
3
@oggiesutrisna
@t3dotgg
We have a Jetbrains extension. It doesn't have this specific fix yet but we will port the fix this week.
1
0
3
@1baga
It’s in JetBrains review - we submitted a new version today that should resolve the last remaining issues
0
0
3
Here, we plot the dense retrieval performance as a function of the number of tokens separating the first and second occurrence of a pair.
Many groups have found models are best at remembering the start and end of the context, and we reproduce this finding.
1
0
3
@lino_levan
@zeddotdev
We're not actively developing a Zed plugin at the moment, but it's something we'd love to do
0
0
2
@0xwendel
It's just a better scheduler that avoids starving requests. The model is the same, p50/90 latency is unchanged.
0
0
2
@jullerino
We haven’t changed anything that would affect this in the past few days. Can you give some more context about this example? What was the suggestion that was accepted here and how did it mess up the brackets?
1
0
1
@theblondealex
We’re thinking about this. Do you enter your commit messages through the terminal or a different interface?
1
0
1
@shokkki
We’ll read a file if it’s checked into Git or it’s opened in the editor. We want to add an option to avoid uploading .env files
2
0
1
0
0
1
0
0
1
@erikkovari
Are you on the Pro version? We should pick this up if it’s common in your codebase
1
0
0
@steinerkelvin
Yes, but the scanning is based on Git repos and not the folder you have open. We ignore files in .gitignore by default
2
0
1
1
0
1
@DeiAlexTVT
We use a generic model when we don’t find that the currently active file is part of a Git repository.
1
0
1
@DeiAlexTVT
Sometimes Supermaven will not suggest. Are you saying that even when you go to a new place in the file and start typing, you get no suggestions?
1
0
1