Varun Latthe

Co-founder, Acyclic Labs (YC F26) building faster, cheaper and bigger agent swarms
Cambridge CS 22-25: research on parallel PL

[Varun Latthe @var1377]

Hello SF, I'm Varun!

@RamV2003 and I just moved here for YC F26 with the goal of getting all agent work to log time execution via swarms.

Would love to connect with those building super ambitious infrastructure and crazy agent setups. If you have any wild projects, please send them my way!

[Aaron Epstein @aaron_epstein]

Acyclic Labs just open-sourced the infra to run 10,000 agent swarms efficiently in a single session. This will take every long-running agent task from hours to minutes.

Congrats on the launch @var1377 @RamV2003!

[Varun Latthe @var1377]

@rishi_desai2 they generally do well at tasks like cyber, adversarial review, deep research and reverse engineering where adding more actions usually doesn't have a chance at reducing performance

[Varun Latthe @var1377]

@RamV2003 their way of saying "don't fall into ai psycosis pls ty xox"

[Varun Latthe @var1377]

@uxduck @UXDuckHQ @ycombinator congrats on the launch!!

[Varun Latthe @var1377]

@Petrichorbios congrats on the launch!!!

[Varun Latthe @var1377]

@Petrichorbios congrats on the launch guys!!!

[Varun Latthe @var1377]

it's amazing when you see improvements that are totally obvious in hindsight, we're still so early

[Weili Xu @_weilix]

Introducing FlashState ⚡: an inference system that flexibly manages the prefix cache of hybrid LLMs, designed for agentic workloads.

On GLM 5.3 Flash, FlashState more than doubles vLLM's throughput and provider profit, while cutting latency by 3.7× and user cost by 2.5×.

[Varun Latthe @var1377]

@OrdoLabs_ @SebApelgren congrats on the launch!!!

[Varun Latthe @var1377]

@theo the strat is to just keep shouting bitter lesson at them; they usually get it eventually

[Varun Latthe @var1377]

how tf do I stop twitter recommending TV show clips???

[Varun Latthe @var1377]

@surlymochan more subagents => we need fewer threads and less context switching

[Varun Latthe @var1377]

has anyone seen a model use multi-agent effectively recently? feels like with this new generation of models they seem less and less trigger-happy on subagents

and if they were better at multi-agent coordination, do you think you would have fewer concurrent coding agent threads?

[Varun Latthe @var1377]

@karatzas_thomas love the style

[Varun Latthe @var1377]

anyone know where the best place is for sandbox comparison benchmarks?

[Varun Latthe @var1377]

@danielmcneil_ @vorelios @krish_k07 @ycombinator great video lads you're gonna do amazing

[Varun Latthe @var1377]

@karatzas_thomas hype

[Varun Latthe @var1377]

@sulansart @vyraverse_ lfg guys congrats on the launch!!

[Varun Latthe @var1377]

@chaaai lfg

[Chaitanya @chaaai]

Today I'm announcing Workers IO to solve the slowest part of engineering, verification!

AI agents can now write years’ worth of code in days, but it still takes significant engineering effort to verify what’s being built.

It’s impossible to predict all scenarios that could lead to a failure and that’s why most expensive failures are found in production.

Workers IO runs millions of simulated production scenarios on your entire system, including dependencies. These simulations run inside a deterministic hypervisor which injects faults like network delays, disk errors, clock skew, and process failures to verify how your system handles these conditions.

Deterministic execution allows us to systematically explore the state space of the system and perfectly reproduce failures.

We are already helping customers do years worth of production hardening in days and build confidence in what they’re shipping.

If you are working on systems that you can never afford to break, DM me and we can help you battle test them!

[Varun Latthe @var1377]

@karatzas_thomas congrats on the launch guys!!!