Submissions from aider.chat

		LLMs are bad at returning code in JSON (aider.chat)
		5 points by pcwelder 8 months ago \| past \| 1 comment
		Gemini 2.5 Pro Preview 03-25 benchmark cost (aider.chat)
		6 points by amrrs 11 months ago \| past
		QwQ is a code architect, not an editor (aider.chat)
		2 points by amrrs on March 7, 2025 \| past
		Aider: AI pair programming in your terminal (aider.chat)
		21 points by vishesh92 on Feb 14, 2025 \| past \| 3 comments
		R1+Sonnet set SOTA on aider's polyglot benchmark (aider.chat)
		1 point by k__ on Feb 3, 2025 \| past
		Using uv as an Installer (aider.chat)
		1 point by tosh on Feb 1, 2025 \| past
		Aider is AI pair programming in your terminal (aider.chat)
		3 points by jhund on Jan 28, 2025 \| past \| 1 comment
		Percent of new code written by aider for aider (aider.chat)
		2 points by yagizdegirmenci on Jan 28, 2025 \| past
		R1+Sonnet set SOTA on aider's polyglot benchmark (aider.chat)
		2 points by kalendos on Jan 25, 2025 \| past
		R1+Sonnet set SOTA on aider's polyglot benchmark (aider.chat)
		6 points by ingve on Jan 24, 2025 \| past
		Using Uv as an Installer (aider.chat)
		7 points by anotherpaulg on Jan 23, 2025 \| past \| 1 comment
		Using Uv as an Installer (aider.chat)
		12 points by ingve on Jan 16, 2025 \| past
		Aider in Your IDE (aider.chat)
		22 points by hboon on Jan 10, 2025 \| past \| 9 comments
		O1 tops new aider polyglot leaderboard (61.7% vs. 45.3% for Claude) (aider.chat)
		1 point by m_ke on Dec 22, 2024 \| past
		Details matter with open source models (aider.chat)
		2 points by amrrs on Nov 28, 2024 \| past
		Separating Code Reasoning and Editing (aider.chat)
		2 points by TiredOfLife on Oct 1, 2024 \| past
		Separating code reasoning and editing with Architect and Editor models (aider.chat)
		5 points by sweca on Sept 29, 2024 \| past \| 1 comment
		OpenAI o1-preview is SOTA on the aider leaderboard (aider.chat)
		5 points by anotherpaulg on Sept 13, 2024 \| past \| 1 comment
		Building a better repository map with tree sitter (aider.chat)
		2 points by ingve on Aug 31, 2024 \| past
		Repository Map (aider.chat)
		1 point by ingve on Aug 29, 2024 \| past
		Sonnet Seems as Good As Ever (aider.chat)
		4 points by anotherpaulg on Aug 27, 2024 \| past
		AI pair programming in your terminal (aider.chat)
		3 points by rob on Aug 22, 2024 \| past
		LLMs are bad at returning code in JSON (aider.chat)
		8 points by anotherpaulg on Aug 16, 2024 \| past \| 2 comments
		Coding with Llama 3.1, New DeepSeek Coder and Mistral Large (aider.chat)
		32 points by anotherpaulg on July 25, 2024 \| past \| 7 comments
		Aider (aider.chat)
		1 point by josephscott on July 11, 2024 \| past
		Sonnet Is the Opposite of Lazy (aider.chat)
		4 points by anotherpaulg on July 1, 2024 \| past \| 1 comment
		Claude 3.5 Sonnet takes the top spot on Aider LLM Leaderboards (aider.chat)
		14 points by Terretta on June 21, 2024 \| past
		Deepseek Coder V2 Beats GPT-4o, Opus (aider.chat)
		28 points by anotherpaulg on June 17, 2024 \| past \| 6 comments
		#1 agent on swe-bench wrote 7% of its own code (aider.chat)
		9 points by andyk on June 9, 2024 \| past \| 1 comment
		Aider Is SOTA for Both SWE Bench and SWE Bench Lite (aider.chat)
		5 points by vok on June 5, 2024 \| past
		More

HN For You