Om Buddhdev
Founder of Olam Labs, Building multi-agent simulations for model evals and training.
Company
Om Buddhdev is listed as a founder of Olam Labs. Multi-agent environments let us evaluate and train models in complex, simulated worlds. We work with researchers on both evaluations and training for character and agentic performance typically difficult to assess for using current popular datasets. Play one of our first releases, Multi-Agent Arena (https://olamlabs.ai/arena), where humans come play social strategy games against multiple AI agents. It's currently top 50 on OpenRouter and has thousands of matches played each day. We use Multi-Agent Arena to build datasets on agentic performance and real-world socialization.
Founder traction evidence
Public posts and activity attributed directly to this founder.
- X
opus 4.6 is the last anthropic model that i had no problem reading the writing of quickly all of the models since, incl fable, are a lot less legible.
opus 4.6 is the last anthropic model that i had no problem reading the writing of quickly all of the models since, incl fable, are a lot less legible. for both coding and convo is it an RL artifact? what's causing it? i've seen this sentiment shared by friends
- X
Can you beat frontier AIs at social strategy games? Today, we're releasing Multi-Agent Arena for free public access! Play games like Risk, Catan, or Poker against GPT, Claude, etc.
Can you beat frontier AIs at social strategy games? Today, we're releasing Multi-Agent Arena for free public access! Play games like Risk, Catan, or Poker against GPT, Claude, etc. We're using this run evaluations on human and model behavior in complex environments.
- X
i believe we need much better benchmarks on how models behave for ai acceleration to go well when i was little i spent all day playing games like age of empires and minecraft so it’s a bit full circle that now that i get to spend all day building similar games as multi agent https://t.co/7Ku2HGaV7D
i believe we need much better benchmarks on how models behave for ai acceleration to go well when i was little i spent all day playing games like age of empires and minecraft so it’s a bit full circle that now that i get to spend all day building similar games as multi agent...
- X
ox alpha (the new @OpenRouter stealth model) is genuinely insane normally when new models proclaiming to be frontier come out they're spiky in capability and on our evals don't match across multi-agent arena it appears that's now changed!
ox alpha (the new @OpenRouter stealth model) is genuinely insane normally when new models proclaiming to be frontier come out they're spiky in capability and on our evals don't match across multi-agent arena it appears that's now changed!
- X
YAYY :D me + agents found a new theorem fully solving erdős problem 872, verified in lean! took ~400 prompts and ~600 commits over 3 months opus had been managing a team of 5.4 pros since april, past week of fable + 5.6 pro got a full solution https://t.co/d4kgKZEJro
YAYY :D me + agents found a new theorem fully solving erdős problem 872, verified in lean! took ~400 prompts and ~600 commits over 3 months opus had been managing a team of 5.4 pros since april, past week of fable + 5.6 pro got a full solution https://t.co/d4kgKZEJro
- X
hello i've been going around talking about multi agent envs irl and i would like to clarify the different definitions i've seen subagent orchestration (the one you know): eg claude code or codex subagents.
hello i've been going around talking about multi agent envs irl and i would like to clarify the different definitions i've seen subagent orchestration (the one you know): eg claude code or codex subagents. post training tasks where the model is incentivized to orchestrate.
- X
lessons so far during S26 from our arena and doing multi-agent evals/tasks: - good infra matters a lot (prolly #1 takeaway) - good latency for the avg arena user matters a lot - good data QA matters a lot - good task grading matters a lot
lessons so far during S26 from our arena and doing multi-agent evals/tasks: - good infra matters a lot (prolly #1 takeaway) - good latency for the avg arena user matters a lot - good data QA matters a lot - good task grading matters a lot
- X
if you were good at factorio you will be amazing at the current state of agentic capability, it's all a skill issue if you're not able to use multiple agents well the intelligence of the models is a pool of water and the skill is in guiding the pool towards your desired
if you were good at factorio you will be amazing at the current state of agentic capability, it's all a skill issue if you're not able to use multiple agents well the intelligence of the models is a pool of water and the skill is in guiding the pool towards your desired