Anirudh Ravichandran

51 posts

Anirudh Ravichandran banner
Anirudh Ravichandran

Anirudh Ravichandran

@anravich94

MTS @ PrimeIntellect

San Francisco Katılım Ocak 2024
93 Takip Edilen250 Takipçiler
Anirudh Ravichandran
Anirudh Ravichandran@anravich94·
We envision verifiers V1 becoming the standard format for environments. It's built to be highly composable, support training and evaluation on rollouts and yet be highly flexible. Put plainly, these abstractions make it really easy to design your environments, and evaluate and train on them! @mikasenghaas, @xeophon and @willccbb cooked big time with this one 👊👊
Prime Intellect@PrimeIntellect

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.

English
0
4
38
5.1K
Anirudh Ravichandran retweetledi
will brown
will brown@willccbb·
when coding is fully solved, many early-career software engineers will be forced to completely pivot their careers and become forward-deployed software engineers or solutions architects or product marketing managers or AI engineers or quantitative data scientists
English
93
22
1.1K
62.6K
Anirudh Ravichandran retweetledi
will brown
will brown@willccbb·
this has been a labor of love for months with @mikasenghaas and @xeophon driving incredible progress, and `v1` is now finally ready for prime time we set out to fully modernize `verifiers` for the agent harness era, and unlocked some insane efficiency gains along the way
will brown tweet mediawill brown tweet mediawill brown tweet media
Prime Intellect@PrimeIntellect

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.

English
10
20
165
13.8K
Anirudh Ravichandran retweetledi
will brown
will brown@willccbb·
you can now train: - a 100B-parameter reasoning model - for 40-turn SWE agent tasks - in your own coding harness - for 1000 RL steps - on just 6 H200 nodes - in under 2 days infra co-design is magical
Prime Intellect@PrimeIntellect

verifiers v1 plugs straight into prime-rl for training. We have been using v1 internally for all our production runs. In this run, we train GLM-4.5-Air on ScaleSWE tasks with under-4-minute steps and 35-turn rollouts, completing 1K steps in 2 days on just 6 H200 nodes.

English
32
71
1.1K
74.5K
Anirudh Ravichandran retweetledi
Prime Intellect
Prime Intellect@PrimeIntellect·
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.
Prime Intellect tweet media
English
26
57
602
136.5K
Pavitra Bhalla
Pavitra Bhalla@pavitrabhalla·
@anravich94 Congrats! Would love to chat about RL environments if you're open to it
English
1
0
0
209
Anirudh Ravichandran
Anirudh Ravichandran@anravich94·
We raised $130M @ $1B for our series A. We have a >$100M run rate and we’re just getting started. Come join us. Prime Intellect is in a unique position in that we own the whole stack - compute, RL training and inference framework, environments, enterprise offerings. It's a highly ambitious undertaking, and so highly well suited for @PrimeIntellect. techcrunch.com/2026/07/08/pri…
English
17
12
265
83.1K
Anirudh Ravichandran retweetledi
Prime Intellect
Prime Intellect@PrimeIntellect·
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.
English
332
540
4.8K
1.3M
Anirudh Ravichandran retweetledi
Prime Intellect
Prime Intellect@PrimeIntellect·
We are grateful to serve over 6k+ customers, including many leading AI startups, neolabs and enterprises already building on our stack, from RL to compute, sandboxes, inference, environments and evals. In under a year, demand has scaled to over $100M in annualized revenue, alongside a large open-source community of 500+ environment creators and 100k+ downloads.
Prime Intellect tweet media
English
1
1
130
11.1K
Anirudh Ravichandran retweetledi
Prime Intellect
Prime Intellect@PrimeIntellect·
So we built the Open Superintelligence Stack — training, inference, and compute: › Training — hosted training, prime-rl (large-scale agentic RL), environments, sandboxes, evals › Inference — dedicated, serverless serving and continual learning › Compute — frontier liquid clusters We train our own open frontier models on it, and ship the same stack to our customers
Prime Intellect tweet media
English
2
3
142
11K
Anirudh Ravichandran retweetledi
Andrew Curran
Andrew Curran@AndrewCurran_·
Prime Intellect has raised $130M in their Series A. Angel investors (I see a well known podcaster in there): John Schulman (Thinking Machines), Karim Atiyeh (Ramp), Aaron Levie (Box), Dwarkesh Patel, Milan Kovac (Tesla), Winston Weinberg (Harvey), Mike Knoop (Zapier, Ndea), Asher Spector (Flapping Airplanes), Jeff Wang (Cognition), Rohan Anil (Core Automation), Matthew Prince (Cloudflare), Brendan Foody (Mercor), Devansh Pandey (Standard Intelligence), Harrison Chase (Langchain), Nic Ouporov (Fleet).
Andrew Curran tweet media
Prime Intellect@PrimeIntellect

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.

English
11
16
268
35.5K
Anirudh Ravichandran retweetledi
Johannes Hagemann
Johannes Hagemann@johannes_hage·
huge shoutout to our entire team! we're a small group racing the most well-funded closed labs in the world to build superintelligence in the open. we're hiring across RL, inference, distributed systems, and compute. primeintellect.ai/careers
English
1
2
33
1.1K
Anirudh Ravichandran
Anirudh Ravichandran@anravich94·
@PrimeIntellect This has got to be amongst the most concentrated list of angels ever. Dare I say it's a sign of what's coming for Series B.
English
0
0
2
52
Anirudh Ravichandran retweetledi
Prime Intellect
Prime Intellect@PrimeIntellect·
Pre-training concentrated the frontier of AI inside a handful of closed labs. RL breaks that open: teams can now own their model-optimization loop — train directly on their product, optimize for their workflows, and ship agents that continuously learn in production. Own that loop and you build a compounding moat in the agentic era. The only missing piece was the infrastructure.
Prime Intellect tweet media
English
3
10
199
15.4K

Keşfet

@mikasenghaas @xeophon @willccbb @pavitrabhalla @PrimeIntellect @elonmusk @BarackObama @taylorswift13