chi (@chimcis) header
chi (@chimcis) profile picture
ottawa / sf
Joined March 2025
Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)Photo by chi (@chimcis)
chi retweeted
Replying to @PrimeIntellect
6
96
2,625
Introducing Model Factory. Train, deploy, and continuously improve your own models on one stack. Run on-demand, on dedicated clusters, or bring your own. Own your intelligence. Own your model factory.
75
217
88
2,188
227,323
This kind of crap must stop. ps. Nobody is saying Jensen's behavior is morally right.
Nvidia’s co-founder came to believe that he was too important for the normal rules to apply to him. This culture of impunity must end. It has damaged one of America’s great corporate successes and undermined its national security economist.com/leaders/2026/1…
3
7
1
91
6,239
chi retweeted
Inkling 2 Small is now available on Prime Inference!
As promised, we’re releasing Inkling 2 Small’s weights, thanks to the hard work of our team and safety testing partners
12
11
167
7,804
chi retweeted
Prime Inference running Whisper faster than Groq. 🤔 I wonder how they did it.
14
8
1
264
10,655
At 96.9%, Prime Inference has the highest cache hit rate of any provider serving Nemotron 3.5 Super VL. This brings the effective input cost to $0.024/M tokens, the lowest of any provider, and ~70% below the largest provider.
12
14
2
167
15,402
🚀 0 → 120 BILLION tokens/day in just ONE month! Just one month since onboarding Prime Inference to OpenRouter, we've scaled from zero to 120B tokens served daily. Note this is just a small portion of Prime Inference 🔥 openrouter.ai/provider/prime…
14
19
7
141
24,488
I'm doing DP. I'm doing TP. I'm doing SP. I'm doing PP. I'm doing ZP. I'm doing FSDP. I'm doing 1F1B. I'm doing CP. I'm doing ETP. I'm doing DPA. I'm doing VPP. I'm doing P/D. I'm doing ZBPP. I'm doing DPA. I'm doing HSDP. I'm doing DCP. I'm doing DWDP. I'm doing AFD.
45
35
11
692
60,762
GLM 5.3 is now 30% cheaper on Prime Inference, and also on OpenRouter when you pick Prime Intellect as the provider. We offer not only a top-tier speed but more importantly highly reliable tool call.
1
4
30
822
"We Bought the Whole GPU, So We're Damn Well Going to Use the Whole GPU"
Replying to @flappyairplanes
We’ve developed the world’s most complete megakernel framework. It can perform entire training runs, serve inference, play video games, and even do all three simultaneously in a single kernel.
90
4,677
Today we're releasing prime-rl v0.10.0 and verifiers v0.4.0 We added our new RL algorithm IPO as the default, tailored for async RL stability, as well as performance improvements and new model support
14
41
14
522
47,748
DeepSeek-v4.1-Flash-1017 is now available on Prime Inference
6
9
63
4,090
Prime Intellect has acquired Moondream We’re bringing Moondream’s open vision models and inference optimizations into our stack Train and deploy multimodal models across vision, video, voice, decision models and computer use
101
81
57
1,266
152,148
chat is this real
Prime Intellect has acquired Moondream We’re bringing Moondream’s open vision models and inference optimizations into our stack Train and deploy multimodal models across vision, video, voice, decision models and computer use
1
48
1,026
Introducing Prime Inference: We've served trillions of tokens for RL and dedicated customer deployments To own your intelligence, you need to own your inference Unpacking our inference stack
91
118
55
1,346
241,314
Inference is here
Introducing Prime Inference: We've served trillions of tokens for RL and dedicated customer deployments To own your intelligence, you need to own your inference Unpacking our inference stack
13
1
91
4,212
We’re hiring a full-time engineer to help build Prime Agent :) Own features end to end across agent harnesses, cloud agents, and self-improving loops -- integrated with our sandboxes, evals, and hosted training stack. Full-time, in person in SF: primeintellect.ai/careers/85…
26
12
3
292
16,156
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.
41
79
31
746
121,222
Last week, I joined @PrimeIntellect as an intern to help optimize their inference stack :) Very grateful to get the chance to work with such a talented team of researchers and engineers Plenty to do and much to learn, super excited for what’s ahead!
76
12
4
348
19,697