Avyay Varadarajan

@avyvar

co-founder @daridotdev // prev @ycombinator, @caltech, basketball data @lakers, software @uber, startups

Fremont, CA

dari.dev

Replies Reposts Media Articles

Pinned
Avyay Varadarajan
@avyvar
Jul 24
Today, we're releasing our open-weight, auto-routing model @daridotdev, built for coding agents. We're state-of-the-art on the Pareto Frontier, w/ 70% cost reduction + comparable coding performance to Fable. Bring your own evals, choose your models, or use our defaults.
15
Avyay Varadarajan
@avyvar
Sep 3
if you're running out of Fable weekly limits try running `dari --claude` Use Fable + open models and make your subscriptions last for 2x longer with no quality degredation :)
00:00
Chubby♨️
@kimmonismus
Sep 1
Literally unusable. The rate limits are absurd. Oh, and by the way, Fable’s automatic continuation is bugged and doesn’t even work. I honestly don’t know why I still bother using Claude at this point. 5.6 is simply better overall anyway. Give me GPT-Astra and im fine. its so
2
Avyay Varadarajan
@avyvar
Sep 1
some thoughts re: subagents subagents are *great* if you’re selling tokens. increasing token throughput is a massive win for a token seller. nobody has the bandwidth to manage 100 agents concurrently, but if all it takes is one prompt and “ultracode”, you can easily 10x usage!
David Cramer
@zeeg
Aug 31
hot take: you dont need subagents for most work (esp wrt coding agents) yes, it can save context, compaction is fine yes, it can make fanout better, except coordinated work often still sucks yes, its good for adversarial verification, but you prob are doing that elsewhere
1
Avyay Varadarajan
@avyvar
Aug 20
Model routers and evals go hand-in-hand - router decisions should be based on evals, and you need to eval different models/harnesses within the exact (or very similar) environments that your agents act in to properly measure savings
Pedro Franceschi
@pedroh96
Aug 20
And people think building model routers is the hard part of "token spend management". :) If you're serious about AI costs, priorities 1 through 10 is having good evals.
2
Avyay Varadarajan
@avyvar
Aug 14
Public evals are saturated. What matters is that a model reliably works in your codebase. To solve this, we built self-bench (github.com/mupt-ai/self-b…) - an open source package to automatically build evals on your own private PRs. One CLI command -> get a clean Harbor dataset.
00:00
10