I welcome more innovation in the code forge space but if you’re looking for an oss alternative just for tracking agent sessions with your commits you should checkout agentblame

https://github.com/mesa-dot-dev/agentblame

In the case where a human edits a previously AI-generated line we simply track that as a human-produced line of code. We are thinking of making this a distinct subcategory because there's a lot of useful info in that data.

Regarding performance we haven't done rigorous benchmarks but we've been using this internally and haven't noticed any problems

There are plenty of code review agents that exist but we found that they fall short in a number of ways. They don’t…

- Let you tailor the reviews with enough fidelity

- Give you control over the models used. If a new foundation model is released I might want to try it!

- Align the costs effectively

Mesa solves these problems with a multi-agent architecture where you define custom review agents that specialize in reviewing certain dimensions of your codebase. This allows you to finely control the review quality and receive reviews that are aware of specific dependencies, business logic, a specific domain in your codebase, or anything else you care about.

You can control the model a specialist uses which is great for trying newly released models but also for controlling costs. When a change is made to our database schema, we have a specialist agent that reviews it and uses the most expensive, smartest, model it can while our frontend agent uses a faster, cheaper agent.

Control over models and the fact that we only charge you for the tokens you use, at cost, aligns our cost structure and gives teams control that they do not get with other agents.

We’ve found code review to be a subtly big problem for teams trying to improve development velocity. It’s the primary point of contact for managing the changes to the living system of your codebase and mistakes are costly.

Missed bugs that make it to production can cause downtime, lost revenue, loss of trust, security breaches, compliance breaches, etc. Engineers spend hundreds of expensive man-hours that they do not enjoy reviewing code and still there’s too many mistakes being made.

We do not believe you can remove humans from the loop of reviews entirely but we can dramatically shift the amount of work done on an average code review and eliminate the need for human reviews altogether on a large subset of PRs. This sort of automation will lead to faster teams and more reliable codebases over time.

We are now in public beta and there’s a generous free tier (~100k lines reviewed free per month) available to all. Give it a spin and let us know what you think!

Oliver & Ben

Comments URL: https://news.ycombinator.com/item?id=45814767

Points: 5

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=41569065

Points: 4

# Comments: 1

> While some will praise Satya Nadella and hero-worship Sam Altman, breaking OpenAI into two parts will slow down momentum for LLMs and research while handing even more power to the Cloud and Azure in its future

Except that Microsoft nor Sam is responsible for the breaking of OpenAI. It was the non-profit board. Instead now Sam and co will have access to the Microsoft war chest, funding for more compute, chip design, and datasets so if anything they’ll probably move even faster than before.

> Microsoft taking Sam Atman and his followers in, is like shutting down your best investment just for a short-term benefit. These stories don’t usually end well for big corporations.

Again this makes little sense and its very clearly obvious how this makes long term sense for Microsoft. Also they did not initiate this move by OAI

> It’s the job of Venture Capitalist to praise Microsoft, Satya Nadella, and Sam Altman to vilify OpenAI’s board in all of this.

No it isn’t

> Microsoft eating OpenAI and poaching their talent, is the worst possible scenario for the startup that was just beginning to get momentum.

No firing the beloved CEO of the fastest growing tech startup in a decade and ignoring warnings from 80% of employees that they would quit is the worst scenario for a startup regardless of what Microsoft does

This whole post seems like really bad pattern matching by someone who is anti capitalism and tries to frame every scenario they see in business through that lens

I see little reason why building a UI today cannot be a superset of what was solved in the 90s so I’m curious to know what that solved subset looks like to you

Comments URL: https://news.ycombinator.com/item?id=37517567

Points: 466

# Comments: 94

Just a personal blog with some essays that I post occasionally to get myself in the habit of writing. My next post will be about living with chronic illness as a SWE and how to get through it

Curiosity/Knowledge: - Peter Zeihan (author) - Atomic Habits - Turn the Ship Around

Work: - Domain Modeling Made Functional by Scott Wlaschin - Designing Data Intensive Applications by Martin Kleppman