Top all-time · #3624
Qodo
Company blog · qodo.ai/blogaiprogramming
Qodo is the company blog at qodo.ai, writing about ai and programming. Since 2024, 21 different Hacker News readers have linked it 39 times, most often “We benchmarked GPT-4.1: it's better at code reviews than Claude Sonnet 3.7”. It is still writing: the last post was on 2026-10-29, and you can follow it by feed.
Too few sampled comments (10) to say how often HN recommends it.?
Why HN links it
HN readers link Qodo's blog for product announcements and benchmarks on AI code review, test generation and codebase Q&A. Comments mostly cite posts for context rather than judge the writing.
Summarised by Claude from a sample of 10 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Qodo is an AI code review tool giving teams deep codebase context to move faster and improve code quality, with 15+ agentic workflows for IDEs, PRs and security.
Most-linked posts?
- We benchmarked GPT-4.1: it's better at code reviews than Claude Sonnet 3.73 people · 3 mentions · first linked 2025-04-14
- We chose LangGraph to build our coding agent2 people · 2 mentions · first linked 2025-03-24
- Building Agentic Flows with LangGraph and Model Context Protocol2 people · 2 mentions · first linked 2025-03-18
- Comparison of Claude Sonnet 3.5, GPT-4o, o1, and Gemini 1.5 Pro for coding2 people · 2 mentions · first linked 2024-11-21
- Qodo automatically verifies PR complies with Jira ticket or GitHub issue2 people · 2 mentions · first linked 2024-11-26
What Hacker News says?
From OpenAI's announcement: > Qodo tested GPT‑4.1 head-to-head against Claude Sonnet 3.7 on generating high-quality code reviews from GitHub pull requests. Across 200 real-world pull requests with the same prompts and conditions, they found that GPT‑4.1 produced the better suggestion in 55% of cases. Notably, they found that GPT‑4.1 excels at both precision (knowing when not to make suggestions) and comprehensivenes…
Comment linking /blog/benchmarked-gpt-4-1/
on “GPT-4.1 in the API”Submitted Qodo CLI agent scores 71.2% on SWE-bench Verified as a story · 139 points
HN discussionTesting against unspecified other "leading" models allows for shenanigangs: > Qodo tested GPT‑4.1 head-to-head against other leading models [...] they found that GPT‑4.1 produced the better suggestion in 55% of cases The linked blog post goes 404: https://www.qodo.ai/blog/benchmarked-gpt-4-1/
Comment linking /blog/benchmarked-gpt-4-1/
on “GPT-4.1 in the API”Submitted AlphaCodium outperforms direct prompting of OpenAI's o1 on coding problems as a story · 87 points
HN discussion> Where are the "code-review" agents at? OpenAI's Codex Cloud just added a new feature for code review, and their new GPT-5-Codex model has been specifically trained for code review: https://openai.com/index/introducing-upgrades-to-codex/ Gemini and Claude both have code review features that work via GitHub Actions: https://developers.google.com/gemini-code-assist/docs/review... and https://docs.claude.com/en/docs/c…
Comment linking /products/qodo-merge/
on “If you are good at code review, you will be good at using AI agents”Submitted DeepCodeBench: Real-World Codebase Understanding by Q&A Benchmarking as a story · 84 points
HN discussionThis is in relation to their newly-announced "context agent": https://www.qodo.ai/blog/introducing-qodo-aware-deep-codebas...
Comment linking /blog/introducing-qodo-aware-deep-codebase-intelligence-for-enterprise-development/
on “DeepCodeBench: Real-World Codebase Understanding by Q&A Benchmarking”Submitted We chose LangGraph to build our coding agent as a story · 83 points
HN discussionSeems like an interesting benchmark, but my takeaway from the results is that Codex is almost as good enough as their custom solution (no mention of the underlying model) and only requires a $20 ChatGPT subscription to start using it (of course with limits), without having to shell out $$$ for an enterprise Qodo plan to use Qodo Aware - https://www.qodo.ai/products/qodo-aware/ . The "free" plan in Qodo Aware only le…
Comment linking /products/qodo-aware/
on “DeepCodeBench: Real-World Codebase Understanding by Q&A Benchmarking”Submitted Benchmarking GPT-5 on 400 real-world code reviews as a story · 72 points
HN discussionHuh, look at that. I completely mixed them up too. Thankfully they have an article which "helpfully" clarifies things: > We’ve noticed that there’s been some confusion between our company, Codium (now Qodo (formerly Codium)), and another company, Codeium. https://www.qodo.ai/blog/codiumai-or-codeium-which-are-you-l...
Comment linking /blog/codiumai-or-codeium-which-are-you-looking-for/
on “Support for Claude Sonnet 3.5, OpenAI O1 and Gemini 1.5 Pro”Submitted Support for Claude Sonnet 3.5, OpenAI O1 and Gemini 1.5 Pro as a story · 69 points
HN discussionApparently that's Codium, who have recently renamed themselves to Qodo: https://www.qodo.ai/blog/introducing-qodo-a-new-name-the-sam... (TIL)
Comment linking /blog/introducing-qodo-a-new-name-the-same-commitment-to-quality/
on “Support for Claude Sonnet 3.5, OpenAI O1 and Gemini 1.5 Pro”Submitted Introducing Qodo Gen CLI: Build and Run Coding Agents Anywhere in the SDLC as a story · 55 points
HN discussionAll these arguments remind me of early LLMs. In fact, most of the arguments are nearly identical. Heck, even Bitcoin back 10 years ago was demonized and now governments are pushing for national reserves. If you have used GPT o3, you have used Agentic models. If you use Claude Code or Cursor, you have used Agentic models. If you have used Claude + MCP, you have used agentic models. This isn't theoretical - its alread…
Comment linking /blog/building-agentic-flows-with-langgraph-model-context-protocol/
on “AI agents get office tasks wrong around 70% of time, and many aren't AI at all”Submitted Effective AI code suggestions: less is more as a story · 52 points
HN discussion> validates each test to ensure it runs successfully, passes, and increases code coverage This seems to be based on the cover agent open source which implements Meta's TestGen-LLM paper. https://www.qodo.ai/blog/we-created-the-first-open-source-im... After generating each test, it's automatically run — it needs to pass and increase coverage, otherwise it's discarded. This means you're guaranteed to get working tests…
Comment linking /blog/we-created-the-first-open-source-implementation-of-metas-testgen-llm/
on “Introducing Qodo Cover: Automate Test Coverage”Submitted 2025 State of AI Code Quality as a story · 45 points
HN discussionApparently this is in support of their 2.0 release: https://www.qodo.ai/blog/introducing-qodo-2-0-agentic-code-r... > We believe that code review is not a narrow task; it encompasses many distinct responsibilities that happen at once. [...] > Qodo 2.0 addresses this with a multi-agent expert review architecture. Instead of treating code review as a single, broad task, Qodo breaks it into focused responsibilities han…
Comment linking /blog/introducing-qodo-2-0-agentic-code-review/
on “We built a real-world benchmark for AI code review”Submitted Evaluating RAG for large scale codebases as a story · 41 points
HN discussionSubmitted Using tests as a debugging tool for logic errors as a story · 38 points
HN discussionSubmitted Building Agentic Flows with LangGraph and Model Context Protocol as a story · 18 points
HN discussionSubmitted Why we chose LangGraph to build our coding agent as a story · 17 points
HN discussionSubmitted Solving key challenges in AI-assisted code reviews as a story · 16 points
HN discussionSubmitted Introducing Qodo Cover: Automate Test Coverage as a story · 16 points
HN discussionSubmitted Google's Reverse Acquihire of Windsurf and the Future of AI Developer Tools as a story · 14 points
HN discussionSubmitted We built a real-world benchmark for AI code review as a story · 12 points
HN discussionSubmitted How to debug Python code in Visual Studio Code as a story · 12 points
HN discussionSubmitted SOTA Code Retrieval with Efficient Code Embedding Models as a story · 11 points
HN discussionSubmitted Comparison of Claude Sonnet 3.5, GPT-4o, o1, and Gemini 1.5 Pro for coding as a story · 10 points
HN discussion
