Alternative DeepSeek V3 providers
https://aider.chat/2025/01/28/deepseek-down.html
Published: January 28, 2025 00:00
DeepSeek's API has been experiencing reliability issues. Here are alternative providers you can use.
@aider.chat@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
aider is AI pair programming in your terminal
Site URL: aider.chat
Feed URL: aider.chat/feed.xml
Posts: 10
Followers: 1
Alternative DeepSeek V3 providers
https://aider.chat/2025/01/28/deepseek-down.html
Published: January 28, 2025 00:00
DeepSeek's API has been experiencing reliability issues. Here are alternative providers you can use.
R1+Sonnet set SOTA on aider’s polyglot benchmark
https://aider.chat/2025/01/24/r1-sonnet.html
Published: January 24, 2025 00:00
R1+Sonnet has set a new SOTA on the aider polyglot benchmark. At 14X less cost compared to o1.
Using uv as an installer
https://aider.chat/2025/01/15/uv.html
Published: January 15, 2025 00:00
Reliably packaging & distributing python CLI tools is hard. Aider uses uv in novel ways to make it easy to install the aider CLI, its dependencies and python 3.12. All in an isolated env.
o1 tops aider’s new polyglot leaderboard
https://aider.chat/2024/12/21/polyglot.html
Published: December 21, 2024 00:00
o1 scores the top result on aider's new multi-language, more challenging coding benchmark.
QwQ is a code architect, not an editor
https://aider.chat/2024/12/03/qwq.html
Published: December 3, 2024 00:00
QwQ is reasoning model like o1, and needs to be used as an architect with another model as editor.
Details matter with open source models
https://aider.chat/2024/11/21/quantization.html
Published: November 21, 2024 00:00
Open source LLMs are becoming very powerful, but pay attention to how you (or your provider) are serving the model. It can affect code editing skill.
Separating code reasoning and editing
https://aider.chat/2024/09/26/architect.html
Published: September 26, 2024 00:00
An Architect model describes how to solve the coding problem, and an Editor model translates that into file edits. This Architect/Editor approach produces SOTA benchmark results.
o1-preview is SOTA on the aider leaderboard
https://aider.chat/2024/09/12/o1.html
Published: September 12, 2024 00:00
Preliminary benchmark results for the new OpenAI o1 models.
Sonnet seems as good as ever
https://aider.chat/2024/08/26/sonnet-seems-fine.html
Published: August 26, 2024 00:00
Sonnet's score on the aider code editing benchmark has been stable since it launched.
LLMs are bad at returning code in JSON
https://aider.chat/2024/08/14/code-in-json.html
Published: August 14, 2024 00:00
LLMs write worse code if you ask them to return the code wrapped in JSON via a tool function call.