Remy made an actual real game with at least a couple of hours of gameplay and it doesn't feel like the usual vibe coded slop prototypes you see everywhere these days.
Link below to try it!
Well we did it together because most of the decisions were mine, but Opus 5.5 seems to execute them really well, literally like having a whole team following your lead.
This took about 2 days, while manually it would have taken at least 1-2 months + all the assets and testing.
Here are all 2,521 SF & LA @a16z@Techweek_ events in 1 Google spreadsheet (pulled 9-22-26).
Shout out to @filgran_ for sharing the new MCP.
SF (Oct 5-11): 1,717 events
LA (Oct 12-18): 810 events
remy.link/techweek260922
sometimes Remy will just build stuff for you and not ask why
did this really need a leaderboard and a live chat?
Link below to try out the bread yourself
sometimes Remy will just build stuff for you and not ask why
did this really need a leaderboard and a live chat?
Link below to try out the bread yourself
If you are a hardcore @Replit or @Lovable builder, I've got a $1k for you. Post what you've built with either, and I will pick one person to rebuild it with @buildwithRemy and give them $1k for doing it!
We've lived in a world of generic software- made to fit everyone, and therefore not fitting anyone. The world has changed! #omarchy is on 🔥 allowing each of us to have an OS that fits us like a glove! @buildwithRemy does the same thing for applications! goremy.ai
Daily reminder that your company doesn't need to spend over $40k/month on services when you can just build your own tools for much less.
SaaS is absolutely cooked
@buildwithRemy's self-serve vector database infrastructure just stood up a 24M chunk database running on dedicated hardware. Total costs: ~$200 USD for ingestion (mapping/data cleaning of 200GB of source text, embedding, evals), ~$700 USD per month for compute (hibernates to $0 if needed, auto-syncs to the original data source for new/removed data). Total time: ~12 hours from "hey Remy here's an S3 bucket" to production-ready state of the art retrieval. Completely self serve, no code or infrastructure work required.
I don't know of ANY other platforms that can even remotely come close in terms of cost + effort? This was all self-serve, no code, AND it built the app to actually use the data!
@OpenAI Astra hackathon today! 🤩 and using GOT-6 Astra via @buildwithRemy. They set up so many vibey and cute corners featuring Astra - will share later
#gpt6astra