samsja (@samsja19) / X

samsja

5,258 posts

samsja

@samsja19

leading research at @PrimeIntellect

Joined March 2020

Pinned
samsja
@samsja19
Nov 27, 2025
INTELLECT-3 is our first model I can use daily It's build using our open source stack by scaling RL of MoE over 512 H200 and pushing the sota at its size Incredible proud of leading such a team of talented, dedicated and hard working individual collaborating together to push
Prime Intellect
@PrimeIntellect
Nov 27, 2025
Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more
00:00
samsja
@samsja19
Jul 23
prime researcher are c̶r̶a̶c̶k̶e̶d̶ cat
Red Hat AI
@RedHat_AI
Jul 23
vLLM Office Hours today at 2pm ET: RL at 1T Scale, a prime-rl performance deep dive with @m_sirovatka (@PrimeIntellect). Training trillion-parameter MoE models like GLM-5.1 on agentic RL, plus what's new in vLLM 0.25 by @mgoin_. Get a recurring cal invite: red.ht/office-hours
samsja
@samsja19
Jul 23
this is the biggest collection of RL tasks for agentic capabilities
Prime Intellect
@PrimeIntellect
Jul 22
Scaling agentic RL environments: today we're publishing 365,000+ tasks for SWE, terminal, and search agents - 23 tasksets behind one API, one sandbox lifecycle, one command.
samsja
@samsja19
Jul 17
soon 3T model supported
Prime Intellect
@PrimeIntellect
Jun 23
Today we're releasing prime-rl v0.6.0 — enabling RL at trillion-parameter MoE scale on agentic workloads at the highest efficiency. We've relentlessly optimized our RL infra. The result: GLM-5 on agentic SWE tasks at 131k context and sub-5-minute step time.
samsja
@samsja19
Jul 14
We are also releasing prime-rl 0.7.0 which has full support for verifiers v1 and bring your own harness for training. We have been battle tested it in prof for weeks now, on the menu: * Verifiers v1 integration * Full Algorithm layers (GRPO, OPD, OPSD, SFT, ECHO * Bunch of
Prime Intellect
@PrimeIntellect
Jul 12
Today, we are releasing verifiers v1 — an overhaul of our environment stack for the modern era of agentic RL and evals. We decompose environments into a taskset, a harness, and a runtime. Run complex agentic tasks like coding and computer use at scale, in any harness.