CodeRabbit
@coderabbitai.bsky.social
Supercharge your dev team with AI code reviews. Get your free trial now: https://coderabbit.ai!
Keep up to date with everything we ship by checking out our changelog!
docs.coderabbit.ai/changelog
Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later. 🧡
docs.coderabbit.ai/changelog
Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later. 🧡
November 19, 2025 at 4:29 PM
Keep up to date with everything we ship by checking out our changelog!
docs.coderabbit.ai/changelog
Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later. 🧡
docs.coderabbit.ai/changelog
Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later. 🧡
Invite/Approval only so apply here: luma.com/gf2zg5ol
CodeRabbit & Anthropic: MCP Anniversary Mixer · Luma
One year has already flown by since MCP redefined how developers connect LLMs to real-world systems and data. CodeRabbit and Anthropic invite you to celebrate…
luma.com
November 15, 2025 at 2:19 AM
Invite/Approval only so apply here: luma.com/gf2zg5ol
What devs should expect:
+ Cleaner reviews
+ Higher-impact comments
+ Patch-like tone
+ Less scanning, more signal
+ Real bugs caught even beyond the seeded diff
Learn more below!
www.coderabbit.ai/blog/gpt-51...
+ Cleaner reviews
+ Higher-impact comments
+ Patch-like tone
+ Less scanning, more signal
+ Real bugs caught even beyond the seeded diff
Learn more below!
www.coderabbit.ai/blog/gpt-51...
GPT-5.1 for code-related tasks: Higher signal at lower volume
We tested GPT-5.1 on code related tasks and this is what we found: it led to cleaner code reviews, had a patch-like tone and great recall.
www.coderabbit.ai
November 13, 2025 at 6:21 PM
What devs should expect:
+ Cleaner reviews
+ Higher-impact comments
+ Patch-like tone
+ Less scanning, more signal
+ Real bugs caught even beyond the seeded diff
Learn more below!
www.coderabbit.ai/blog/gpt-51...
+ Cleaner reviews
+ Higher-impact comments
+ Patch-like tone
+ Less scanning, more signal
+ Real bugs caught even beyond the seeded diff
Learn more below!
www.coderabbit.ai/blog/gpt-51...
The model feels different, too. Leaner. More assertive.
Less like a research paper, more like a senior engineer leaving a targeted code comment at 2am.
Less like a research paper, more like a senior engineer leaving a targeted code comment at 2am.
November 13, 2025 at 6:21 PM
The model feels different, too. Leaner. More assertive.
Less like a research paper, more like a senior engineer leaving a targeted code comment at 2am.
Less like a research paper, more like a senior engineer leaving a targeted code comment at 2am.
On our hard EP benchmark, GPT-5.1 tied best-in-class recall while posting less than half the comments of competitors.
Precision shot up. Fatigue dropped.
Signal-to-noise is the best we’ve seen.
www.coderabbit.ai/blog/gpt-51...
Precision shot up. Fatigue dropped.
Signal-to-noise is the best we’ve seen.
www.coderabbit.ai/blog/gpt-51...
GPT-5.1 for code-related tasks: Higher signal at lower volume
We tested GPT-5.1 on code related tasks and this is what we found: it led to cleaner code reviews, had a patch-like tone and great recall.
www.coderabbit.ai
November 13, 2025 at 6:21 PM
On our hard EP benchmark, GPT-5.1 tied best-in-class recall while posting less than half the comments of competitors.
Precision shot up. Fatigue dropped.
Signal-to-noise is the best we’ve seen.
www.coderabbit.ai/blog/gpt-51...
Precision shot up. Fatigue dropped.
Signal-to-noise is the best we’ve seen.
www.coderabbit.ai/blog/gpt-51...
Hear from CodeRabbit's Director of AI, David Loker, on how to give the nuanced feedback that actually improves performance over time.
www.coderabbit.ai/blog/why-em...
www.coderabbit.ai/blog/why-em...
Why emojis suck for reinforcement learning (& what actually works)
The next generation of AI code tools won’t be trained on likes. They’ll be trained on context, consequence, and course correction.
www.coderabbit.ai
November 7, 2025 at 4:27 PM
Hear from CodeRabbit's Director of AI, David Loker, on how to give the nuanced feedback that actually improves performance over time.
www.coderabbit.ai/blog/why-em...
www.coderabbit.ai/blog/why-em...
CodeRabbit's Senior Software Engineer Howon Lee walks us through why AI is better when it's slower and why most AI dev tools still choose stupid over slow!
www.coderabbit.ai/blog/the-ri...
www.coderabbit.ai/blog/the-ri...
The rise of Slow AI: Why devs should stop speedrunning stupid
AI isn't magic. It's inference. That's why optimizing for speed means optimizing for bad answers and worse performance. Why Slow AI is the way forward.
www.coderabbit.ai
November 5, 2025 at 7:10 PM
CodeRabbit's Senior Software Engineer Howon Lee walks us through why AI is better when it's slower and why most AI dev tools still choose stupid over slow!
www.coderabbit.ai/blog/the-ri...
www.coderabbit.ai/blog/the-ri...
