Introducing Prime Sandboxes: MicroVM sandboxes purpose-built for RL training. Model training requires running tens of thousands of concurrent sandboxes, leading to complex and costly configuration. We built Prime Sandboxes for our own team. Today we're releasing them publicly.

This looks like cool work esp on the trust region side But are we being too short minded with wanting single rollout RL. Theres definitely some benefits but as we move into tasks and domains that are less verifiable, i think we underestimate how important the idea of relative quality within a group can be

i do think a lot of people on the pro-open-source side are having a bit of a knee-jerk reaction to the pacing statements today, as we're used to viewing the closed labs as power-seeking. but i think their hands are somewhat forced here, and this is just another chapter on the fairly inevitable path towards decently-fast decently-safe decently-commoditized intelligence abundance. ask any F500 exec or swing voter. the world doesn't really want super-fast-takeoff superintelligence owned only by two companies, and thus we won't get it. it'll happen at the pace that the world can accommodate it, which means reaching some sort of confidence consensus that the models are aligned enough that we won't be dealing with scary new incidents all the time. this will trickle out broadly, in the form of best practices and distillation. the smarter a model is, the more it has a "personality", and the less effective strict rules are. there will be awkward compromises and moral tensions. but we ultimately just want the models to be reasonable, and to do the sorts of things reasonable humans would do if our brains were faster and less error-prone and had more working memory. i think we'll get there. the labs will build mac and windows, the rest of us are building linux. everyone's gonna do great. weird stuff will keep happening, but we'll still wake up and go to work, until the work does itself in a manner the world finds acceptable.

we are super bullish on sparse attention + HiSparse and have been working with the vLLM team on it sparse attention reduces the pressure on memory bandwidth by only selecting k for the attention, but it doesn't reduce KV cache memory storage , in high-throughput wide-EP deployment you want to maximize the batch size of decode to use compute as much as possible, but at long sequence decode you quickly run out of VRAM and can't hold enough parallel requests to saturate the compute HiSparse fixes this by offloading the active KV cache to CPU. It keeps an LRU cache on GPU, and since many of the same K tokens are reused every decode you barely notice the offloading, this allows a massive decrease in memory usage and an increase in concurrency This is super important for RL where throughput is key and we want to be as much as possible in a compute-bound regime tldr: lower memory usage, more concurrency, higher inference throughput, faster RL

As models become more capable, reward hacks become an increasingly serious problem. During a controlled experiment, we found a novel reward hack in which agents are able to gain web access in offline sandboxes.

Join us at Prime Intellect to build open superintelligence and the infrastructure powering self-improving agents. We’re hiring across 25+ roles. Research • AI Research Resident • Research Engineer, Distributed Training • Research Engineer, Reinforcement Learning • Research Engineer, RL Infrastructure Compute • Compute Finance & Strategy • Compute Intelligence Engineer • Head of Compute • Solutions Architect, AI Infrastructure • Technical Account Manager, AI Infrastructure Engineering • MTS, Compute Platform • MTS, Full-Stack • MTS, GPU Infrastructure • MTS, Inference • MTS, Sandbox Platform • MTS, Security • MTS, Training Platform Growth • Applied AI: Product Strategy & Revenue • Forward-Deployed AI Strategy • Head of Growth • Head of Marketing • Community and Devrel Other • Internship • Open Application for Unconventional Talent Apply here: primeintellect.ai/careers

we just shipped adaptive concurrency to prl main, making it (to the best of my knowledge) the first oss rl framework to dynamically adjust inflight rollouts to maximize throughput during the entirety of an rl run

We ran the largest open experiment on how frontier models do AI research. 100+ autonomous runs across 10+ models, sandboxed on 8xH200s for up to 8 days, iterating on the nanoGPT optimizer track. Best runs closed 82% of the gap to a record built by dozens of humans over months.

Today, we’re extending our RL stack beyond individual agents to multi-agent systems. You can now express arbitrary agent interactions and train them. primeintellect.ai/blog/multi…

Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.

People forget to think of the actual differences between CoT and layer looping Difference lies on how info is passed on over loops. Layer looping passes this info fully in that final hidden state while CoT passes it through the kv cache of each layer (around like 70 layers, and passes through attention rather than a residual) Make of that what u will

Introducing MazeBench, a 3D open world environment that evaluates long term planning with visual spatial reasoning. It spans hundreds of rooms and puzzles. Today’s best agents cannot progress beyond the initial levels.

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.

Announcing our $130M Series A to build the Open Superintelligence Stack Led by Radical Ventures, with NVIDIA, Intel Capital, Dell Capital, and existing investors Train, deploy, and continuously improve your own models using our stack. Own your intelligence.