Conflicts are not a problem at all in my experience.
My setup is that I run `/merge`[1] , which will first have the agent rebase changes on base, and on conflicts, it's instructed to understand both sides before resolving, which helps it merge them cleanly. I haven't resolved conflicts manually in months and also haven't had any issues with agents resolving them incorrectly. A solved problem as far as I'm concerned.
> it's instructed to understand both sides before resolving.
This is the crux of the issue. You are delegating the resolution of conflicts to an agent, which is fine, but doesnt solve the core issue that there's no scalable way to actually do this. It is far from a solved problem lol, just because your agents havent had issues resolving them.
In some specific work contexts, such as writing pull request descriptions, not sounding like AI is something I've given up on trying to optimize. It's simply not worth the effort for me being non-native and writing detailed PR descriptions being so arduous, and the agent already has full context anyway. Obviously any fluff or inaccuracies are aggressively weeded out but I don't care anymore about the AI voice.
> any fluff or inaccuracies are aggressively weeded out
this work is paramount. Without clear evidence of human filtering, a long, well formatted message/PR/doc is likely to reduce my estimate of the value/veracity/relevance of its content.
Hardware improvements are easier to quantify and progress naturally comes in incremental steps.
Software however especially from UX point of view, is more likely to be more or less ready at some point. Any improvements are marginal and subjective. What are the large UX teams at Apple going to do if not redesigns for the sake of redesigning? I wish it would happen, but it’s hard to imagine Apple shipping an annual OS release without noticeable visual changes.
I agree. To be more clear, that $60 is an estimate for a small configuration and includes serverless infrastructure to process 500,000 requests per month, plus storage, including a 20gb sql database and 100gb of object storage to serve video and images. More ideal for an application. You run the app in a container and only get charged for the requests, the sql database is persistent, so that cost $20/month and object storage with egress is about $10/month.
Let me describe my setup, so that you can compare. I use a Contabo VPS for around 5 USD month to host my Wagtail (django-based) site. The DB also runs on the same infra and since it's SQLite I can back it up externally.
I probably wouldn't be able to handle 0.5M requests, but I am nowhere near getting them. If I start approaching such numbers I'll consider an upgrade.
Check out Wagtail if you'd like to have even more batteries included for your site, it was a delight building my site with it:
Thank you for sharing your setup, I will certainly examine it and compare a bit later. I know my setup is a bit over the top, but it is the easiest to learn, since I live in gcp everyday. I certainly don't expect the .5m traffic, but that is one of the lower tiers for cloud run, serverless execution service. This is just a poc to get my fingers dirty with the MVT pattern.
- macOS dictation mutes other sounds while it's running. This is a deal-breaker for me.
reply