Aide
323 posts

Aide
@aide_dev
Scalable agents working on your Github Issues, built on top of the SOTA agent on swebench-verified From the creators of Aide the AI native editor
London Katılım Haziran 2023
9 Takip Edilen1.6K Takipçiler
Sabitlenmiş Tweet

@tunahorse21 @skcd42 fixed the setting! you can DM the account directly too
English

Hey all! It is with a very heavy heart that we have made the decision to sunset Aide.
Users with an active subscription will receive a refund within the next 5-7 days, and your access to the CodeStory provider will work till the end of the month. Access for all free users is being revoked immediately.
The editor and sidecar are both Open Source, and can be run on your own with API keys indefinitely.
We made great strides this past year, shipping an editor with a small team of 4, getting to the top of swebench twice, churning through 50B tokens a week.
But, at the same time, we had a lot of bugs we couldn't keep up with, got out-executed by teams with a lot more talent and capital and importantly, failed at converting our wins into a distinct and sustainably growing product.
We are tremendously grateful for everyone who believed in our vision, stuck with us during the early days, during the times the editor was a mess, and the times when your trust in our team and the product paid off.
As a company, CodeStory is going nowhere yet and we have new avenues that we are exploring - more on which we will be sharing soon. A huge thanks to everyone again
English

you can also vibe code from your phone using agent farm
skcd@skcd42
watch me speed run adding sonnet3.7 using sonnet3.5 and making sure the code compiles 😇 all from my phone which was at 4% battery (these are tiring times)
English
Aide retweetledi

the new sonnet3.7 review as someone who has used it before:
- the new sonnet is great, on our internal evals on rust we see 14.7% (40% around) improvement (this eval is made up of 1k questions)
- it has a stronger affinity to end of context instructions, we add a reminder of the tool format at the end of our prompts and it was over indexing on it a bit which was weird but nothing out of the ordinary
- It does a good job at implicit planning: this one really made me happy, I can even throw away o1 right now and just use the new sonnet model
- we did see doom loops appear post 150k input tokens but this is still better than the 70k input tokens of the older sonnet
- its great at finding its way around issues, even when taking a wrong approach its about to course correct and does not get stuck on local maxima
- the terminal usage has clearly improved a LOT!
- one nice behavior from sonnet3.7 was that it did not need to read the file again after editing to make a new edit again a bit surprising when I first noticed it but looks like showing it the git-diff was enough for it to understand how to go about making more edits on the same file again (this is big if you are working on agentic code generation)
- the visible COT is a big difference, when it comes to debugging. Gone are the days for hoping that the system prompt will do the right thing or where it is going wrong. This made me lean into reasoning models more
- 1.0 temperature was the preferred setting, altho I am not sure if that changes with the model release today
@AnthropicAI did a stellar job with sonnet3.7 I am glad that I can use this model again, been waiting on this for weeks
English
Aide retweetledi

We are sunsetting Aide.
as an editor we did pretty good, hit some big numbers and were burning through more than 10B tokens just yesterday
the sad part is, we got out executed and out gunned by our competition
some of my most memorable memories:
- being SOTA on swebench twice
- learning about the internals of VSCode and syncing those changes upstream when we could
- people coming over to our discord surprised by how good the agent is compared to everyone else
- fighting smut content on our servers (XD)
so what's next?
we as a team know how to ship fast (real fast) and iterate quickly, we will be taking a stand against Devin and believe our agent is truly special (pun intended).
To everyone who has used Aide and supported us, I want to say thank you. It was a tremendous challenge which Naresh and I took on ourselves and started back in 2023 and kept at it until earlier this year.
we will share about our agent_farm and what is in store for the future of AI codegen tools :) I am personally very excited about this space and will share more soon
onwards and upwards!
English

Aide retweetledi

This is how i've been doing my cuda / ptx work for the last few weeks and i can both attest to R1 being particularly cracked at it AND that if you actually run a benchmark / compiler in the loop is does much better than you could possibly imagine. is this fast takeoff? almost certainly not. can you see fast takeoff from here? absolutely ...
anton@abacaj
uh it might be over... they put r1 in a loop for 15minutes and it generated: "better than the optimized kernels developed by skilled engineers in some cases"
English




