Avyay Varadarajan

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

[Avyay Varadarajan @avyvar]

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.

[Avyay Varadarajan @avyvar]

@CTewey @TryKeythorn congrats guys, looks super cool 🐐

[Casey Tewey @CTewey]

Today we’re launching Keythorn.

AI isn’t just thinking anymore. It’s moving money, talking to customers, and taking action. Every new agent brings new risk.

The future runs on AI. We’re building the insurance for it.

Meet @TryKeythorn ↓

[Toby Kim @_doyeob_]

Today we're launching
> the world's fastest TTS endpoint at 50 ms time-to-first-audio (TTFA)
> the world's cheapest modern TTS endpoint at $5 / 1M characters

Powered by Qwen3-TTS 1.7B on Nari Labs inference engine.

🚀 5x faster than Cartesia
💸 10x cheaper than ElevenLabs
🎙️ expressive voices, outperforming industry average
🎁 available FREE for a limited time

We believe open-source will win: not just in LLMs, but also in multimodal AI. Nari Labs is here to accelerate that future, starting with speech.

Try now at https://t.co/5XXG3WvnYB

[Paulina Xu @paulinazhxu]

A 14B open model on a single RTX 4090 matched our hosted frontier model on text-to-SQL.

That wasn’t supposed to happen.

We ran 28 configurations, graded 25,000+ answers, and benchmarked against Snowflake + Databricks.

What we learned:

model size, model reputation, and vendor benchmark scores are bad shortcuts for predicting performance on your database.

So today we’re open-sourcing mnemiq.

Test it on your own data ↓

[Steven Heidel @stevenheidel]

token pricing is effectively meaningless now. 3.8 flash looks 13x cheaper when measured per token, but Astra is cheaper per task since it's far more efficient. measure your costs per task, not per token.

[Avyay Varadarajan @avyvar]

https://t.co/89bRTj5Elq

[Avyay Varadarajan @avyvar]

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 :)

[Chubby♨️ @kimmonismus]

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 frustrating. seriously.

oh, and btw. For subscription users, Anthropic has not announced lower prices or higher usage limits regarding Fable 5.1s efficency gains; the savings explicitly apply “wherever usage is billed by token,” so greater efficiency within Pro or Max subscriptions possible not gonna happen.

[Avyay Varadarajan @avyvar]

if you’re not cost-insensitive, though, it’s super important to benchmark multi-agent *within your codebase/the environments where you are doing work*

harness/thinking level are important to benchmark as well, but subagents naturally have the potential to spike your $/outcome

[Avyay Varadarajan @avyvar]

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]

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

[Avyay Varadarajan @avyvar]

of course, the appeal of multi-/sub-agent is massive. you essentially get infinite context if done right

(the hugging face exploit is clear evidence of the potential/danger of multi-agent)

the labs will obviously continue with multi-agent RL and performance will only improve.

[Patrick Collison @patrickc]

Overall, I’m very surprised at how little media coverage there’s been around the OpenAI / Hugging Face attack. It’s clearly one of the most important things to happen this year.

[Avyay Varadarajan @avyvar]

this is why we built self-bench! (https://t.co/zYfPrbem2P) - it's fully open-source and lets you build simple @harborframework evals from your PRs

[Avyay Varadarajan @avyvar]

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]

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.

[Avyay Varadarajan @avyvar]

@deeznutshahalol today we're going to talk about the crossover and intersection between routing, evals, and ROI, in combination with raising awareness, leveraging your platform and influence and investing in the sustainable future.

[Avyay Varadarajan @avyvar]

Public evals are saturated. What matters is that a model reliably works in your codebase.

To solve this, we built self-bench (https://t.co/zYfPrbem2P) - an open source package to automatically build evals on your own private PRs.

One CLI command -> get a clean Harbor dataset.

[Avyay Varadarajan @avyvar]

If you want to reduce your token costs without sacrificing performance, you can now:

- build an eval on your repo
- run open weight models, frontier models, and our router
- see cost/performance/latency tradeoffs!

book a call to reduce token cost: https://t.co/t7HCa87kED

[Avyay Varadarajan @avyvar]

Companies are trying to reduce token costs by using smaller / open-source models, but switching without evals is flying blind.

We built evals based on some popular OSS packages like Next.js and Vite. @daridotdev 's auto-router is on the pareto-frontier in all of our tests!

[Avyay Varadarajan @avyvar]

@jtdavies what are you getting for prefill on your m4 pro?

[Avyay Varadarajan @avyvar]

@Ani_da_dev we made our router cache aware (basically make decisions based on warm / cold cache costs)

built a little tool to visualize too https://t.co/yQvUvmYPLT

some super cheap models are even cheaper than cached frontier model rates (ie deepseek flash vs. sol)