The scores are a combination of review accuracy, noisiness of the reviews, and the ability of the model to use evidence in its reviews to justify comments.

How does GPT-5 stack up when it comes to code reviews? We ran OpenAI's new family of models through our code review benchmark to see how they stacked up 1. GPT-5 - 8.17/10 2. Claude Sonnet 4 - 8.03/10 3. GPT-5 Mini - 7.71/10 4. GPT-4.1- 7.66/10 5. GPT-5 Nano - 6.74/10

o1 has surpassed sonnet 3.5 for aider's code editing benchmark. But it has to use the whole files rather than the diff for now. It'll be interesting to see how tools are able to adopt to use o1

I wasn't sure about the hype around @cursor_ai - but after a few days I'm thinking of fully replacing vim with cursor. I'll miss vim-test + projectionist.vim which is the best combination ever

You won’t believe how good @SourceryAI’s code reviews are! https://t.co/RLBik0eQEN #dev #ai

We've been playing around with different ways to validate and test LLM responses to help us move faster. It turn out one of the best approaches is pretty simple. Creating unit tests for the LLM responses -

Getting GPT4 to stop praising code changes is surprisingly frustrating

Should AI dev tools/assistants look and feel like tools? Or should they be designed to feel more "human"?

Really enjoyed chatting with @digiglean and @nthapen on the @realpython podcast about code reviews https://t.co/XuDpaxdzpi

🐍🎧 Episode #183 of the Real Python Podcast is live: “Exploring Code Reviews in Python and Automating the Process” with @brendan_m6s, @nthapen #python #podcast

Ep.10 Drop 🎤 @JensLapinski, one of Europe's most active angels and all round legend, joined me in the hot seat for #20Angel 💥 We 🗣️ how investors are like 'glorified trashmen', why secondaries should be viewed differently and much more Get out the 🍿 https://t.co/FGxH6sj3NB

And then a demo off @SourceryAI and damn, the tool they are building to help us read code is really impressive!

@brendan_m6s reminisces upon the historical moment he completed his first project, exclaiming ‘I’m the King of the World!’ #pythonlearning #brightontech #brightonmeetups @brightonpy @eagle_labs_sth

Brendan is over the moon with a tidy code - @brendan_m6s @SourceryAI @brightonpy #pythonprogramming #kingoftheworld #brightontechcommunity #brightoncode #brightoncoding #pythonlearning

Amazing to see the huge progress made by the @SourceryAI team from @brendan_m6s at @brightonpy last night!

I'm really looking forward to talking tomorrow!

Food for thought for the weekend: The 1st part of our conversation with @SebaWitowski Chatting about working in teams, setting common standards, and respecting individual preferences. https://t.co/JuZ8KqH3HU

I'm speaking at @brightonpy on 3rd Nov about "How @SourceryAI implemented the Google Python Style Guide as code" https://t.co/FnJOPUN1MV

We've very excited about the return of @brightonpy! ☺ #Python developers - join us for our first meetup back featuring a talk from @SourceryAI CEO @brendan_m6s 👇

Today we are launching Sourcery 2.0! Now you can: - Extend Sourcery to handle your best practices - Leverage Pre-Built Rulesets, like the Google Python Style Guide - Bulk review your project from the command line - Review every commit with Sourcery in CI https://t.co/m1AEvbB5iN