iiinova — where your digital self keeps evolving

Seth Karten @sethkarten.ai · 29/09/2026

Feel free to follow on /nightly

Seth Karten @sethkarten.ai · 29/09/2026

We have merged a fix for this. Will be doing a minor release to fix this. Then no release for a week while we dogfood some huge performance changes :)

120

Seth Karten @sethkarten.ai · 29/09/2026

Is this just claude code? Or codex sub too?

100

Seth Karten @sethkarten.ai · 25/09/2026

This is exactly the kind of setting we built Agent Bazaar to study, and I think these questions are only going to become more important as agents start transacting and negotiating on behalf of users. I'll be presenting Agent Bazaar at COLM Wed Oct 7. arxiv.org/abs/2605.17698

arxiv.org

Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to directly interacting w...

070

Seth Karten @sethkarten.ai · 25/09/2026

The risks go beyond whether any single agent is aligned with its user. Agents can collectively crash markets even when each individual agent is behaving rationally, and users can get scammed by autonomous sellers. Meta Muse is starting to make this future real pretty quickly.

240

Seth Karten @sethkarten.ai · 25/09/2026

We wrote Agent Bazaar back in May around a future where agents act on behalf of users and increasingly participate directly in marketplaces like Amazon and eBay. We introduced Economic Alignment to study what happens as agents become economic actors.

2143

Seth Karten @sethkarten.ai · 24/09/2026

prime agent v0.9.6 is out: ◆ Support for GPT-6 Sol, Opus 5.5, and Grok 4.7 ◆ /mcp plugin catalog with one-click connections to Linear, Notion, Posthog, Stripe, and 60+ more services ◆ Huge perf and reliability pass 🫡 Lots more coming soon :)

1263

Seth Karten @sethkarten.ai · 23/09/2026

This is fixed in /nightly (main of github repo). Release not coming until tomorrow

110

Seth Karten @sethkarten.ai · 22/09/2026

Also we are making new models available without requiring prime agent update going forward so you wont need to update to access new models going forward

140

Seth Karten @sethkarten.ai · 22/09/2026

We have open source you can fork. I think we have a PR to add new opus. Let me check on it

210

Seth Karten @sethkarten.ai · 17/09/2026

I think we just merged this today in the nightly. Will be in next release

130

Seth Karten @sethkarten.ai · 17/09/2026

Can you use the daemon cli commands for that?

100

Seth Karten @sethkarten.ai · 16/09/2026

prime agent v0.9.5 we fixed a lot of bugs and, of course, we had prime agent feature its favorite updates it picked our perf work. then it created the video itself.

3311

Seth Karten @sethkarten.ai · 15/09/2026

Quick update: we’re adding a few incentives for contributors. Everyone who submits data will be acknowledged in the dataset release, and the full dataset will be open sourced. If you get especially involved in collection and data processing/curation, there may also be author opportunities

032

Seth Karten @sethkarten.ai · 12/09/2026

Noted. Team is working on a front-end overhaul

131

Seth Karten @sethkarten.ai · 10/09/2026

Wow excited to see a prime agent community emerged here. Sharing my latest YC Paper Club invited talk: youtu.be/n9xKblqyQ28?...

youtu.be

Why The Harness Matters More Than The Model | YC Paper Club

YouTube video by Y Combinator

1252

Reposted by Seth Karten

prolepses.bsky.social @prolepses.bsky.social · 09/09/2026

Reposting with a direct link right to where @sethkarten.ai breaks down Prime Agent. The TLDR is that Prime Agent is "Jupyter notebooks for your agents", the video is absolutely worth the watch: youtu.be/n9xKblqyQ28?...

youtu.be

Why The Harness Matters More Than The Model | YC Paper Club

YouTube video by Y Combinator

1113

Reposted by Seth Karten

Chris Patil @donotgogently.bsky.social · 09/09/2026

If you’re interested in Prime Agent by @primeintellect.bsky.social , Seth Karten (researcher at Prime, author of the Prime Agent paper) gave a nice talk on the harness at YCombinator the other day youtu.be/n9xKblqyQ28?...

youtu.be

Why The Harness Matters More Than The Model | YC Paper Club

YouTube video by Y Combinator

2164

Seth Karten @sethkarten.ai · 08/09/2026

My group at Princeton is collecting crowdsourced, action-labeled game data for research on AI agents, starting with Pokémon Emerald. The goal is to build a large open-source dataset of action-labeled gaming trajectories. Sign up to contribute here: docs.google.com/forms/d/e/1F...

docs.google.com

Play Pokémon Emerald, Help Train a World Model.

We're building generalizable world model agents, AIs that learn to understand and simulate games from video. We need your help to gather gameplay recordings to generate a dataset which can then teach ...

061

Seth Karten @sethkarten.ai · 31/08/2026

This slide has done more harm than good

010

Seth Karten @sethkarten.ai · 19/08/2026

If you cared about safety, you would have allowed waymos in nyc

120

Reposted by Seth Karten

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 15/08/2026

There’s a bit of a sense of despair in the research community around LLMs. It can be avoided by switching to caring about what we should build as opposed to how we build it

5483

Seth Karten @sethkarten.ai · 13/08/2026

Thanks! We have a lot of cool stuff still coming

000

Seth Karten @sethkarten.ai · 12/08/2026

Made an account using my bluesky but im not sure how to use it. Is it mainly for blogs? Can i post like I would post my research on X or bluesky?

120

Seth Karten @sethkarten.ai · 10/08/2026

Really excited about this one :) Prime Agent + Opus 5 gets 95.5% on ARC-AGI-3 (179/183). A big goal when I was building Prime Agent was making long-horizon agents more capable yet token efficient. github.com/PrimeIntelle...

github.com

GitHub - PrimeIntellect-ai/prime-agent: A self-improving RLM agent for coding workflows and long-running autonomous tasks.

A self-improving RLM agent for coding workflows and long-running autonomous tasks. - PrimeIntellect-ai/prime-agent

2333

Seth Karten @sethkarten.ai · 10/08/2026

github.com

GitHub - PrimeIntellect-ai/prime-agent: A self-improving RLM agent for coding workflows and long-running autonomous tasks.

A self-improving RLM agent for coding workflows and long-running autonomous tasks. - PrimeIntellect-ai/prime-agent

140

Seth Karten @sethkarten.ai · 23/07/2026

I agree with the “we dont really know until we see it in practice” Though largely i see public science funding trending from “those not willing to use AI” to “those willing to use AI” Or at least write so in their proposal

020

Seth Karten @sethkarten.ai · 22/07/2026

How are the academics feeling about this? Does it even change anything for profs?

120

Seth Karten @sethkarten.ai · 22/07/2026

Great to see Continual Harness acknowledged in Schmidhuber’s latest survey paper

050

Seth Karten @sethkarten.ai · 14/07/2026

Going through my backlog and realizing I forgot to announce 1 paper and never put another on arXiv. Expect 2 blog posts soon

1100

Seth Karten @sethkarten.ai · 12/07/2026

Odysseus (PPO for VLMs/LLMs) We found the way to apply PPO to VLMs/LLMs for long horizon tasks using super mario world as our case study huggingface.co/papers/2605....

huggingface.co

Paper page - Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning

Join the discussion on this paper page

071

Seth Karten @sethkarten.ai · 12/07/2026

Automatic RL Env The main takeaway is to develop a strong verifier feedback loop. Here we create the idea of minimizing a sim-to-sim gap between environments in order to correctly verify performance versions of envs huggingface.co/papers/2603....

huggingface.co

Paper page - Automatic Generation of High-Performance RL Environments

Join the discussion on this paper page

130

Seth Karten @sethkarten.ai · 12/07/2026

Agent Bazaar (multi-agent safety & economic envs) This is my personal take on looking at the macro behavior of agents in economic settings wrt managing supply, consumer demand, and trust in long horizons huggingface.co/papers/2605....

huggingface.co

Paper page - Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

Join the discussion on this paper page

140

Seth Karten @sethkarten.ai · 12/07/2026

Wow, three papers in CoLM 2026... Here I come San Francisco! These papers predicted some early trends in multi-agent safety & economic envs, automatic RL env creation, and PPO for VLMs/LLMs 🧵

130

Seth Karten @sethkarten.ai · 12/07/2026

New blog applying Continual Harness to ARC-AGI-3. The heavy test-time learning required by the benchmark pushes agents to form an internal world model of the rules and mechanics that updates with new evidence. Continual Harness scored 20.54%. sethkarten.substack.com/p/continual-...

open.substack.com

Continual Harness: An Efficient Self-Improving Agent on ARC-AGI-3

Continual Harness scores 20.54% on ARC-AGI-3 at $774, showing how reset-free self-improving agents can learn hidden game dynamics at test time.

0121

Seth Karten @sethkarten.ai · 10/07/2026

Same. I need a better feed here

0141

Seth Karten @sethkarten.ai · 10/07/2026

Just seize money from football. They should pay the university rent

100

Seth Karten @sethkarten.ai · 11/06/2026

😵‍💫 what if you compare the elon holding companies to alphabet. Maybe it’s roughly the same give or take a few 100 billion

000

Seth Karten @sethkarten.ai · 10/06/2026

They own a lot of gpus and electricity. Starlink is profitable. As shown with the anthropic and google deals, they dont need to make their own AI to make money when gpus and power are in short supply

110

Seth Karten @sethkarten.ai · 22/05/2026

Just know that my reviewers will be thoroughly reviewed for their strengths and weaknesses. Score and confidence included.

010

Seth Karten @sethkarten.ai · 19/05/2026

Midwest emo is from new jersey 😋

110

Seth Karten @sethkarten.ai · 19/05/2026

Econ lovers i have something for you

010

Seth Karten @sethkarten.ai · 14/05/2026

New paper alert: Continual Harness: Online Adaptation for Self-Improving Foundation Agents Paper (arXiv). arxiv.org/abs/2605.09998 Article (Substack). sethkarten.substack.com/p/gemini-pla... Project page (video demos). sethkarten.ai/continual-ha...

0203

Seth Karten @sethkarten.ai · 13/05/2026

Announcing some work tomorrow. Will be cool and probably involving pokemon

010

Seth Karten @sethkarten.ai · 26/04/2026

im very glad to see a rebound this year in the total number of NSF GRFP awards to exceed the most this century. Founding the next generation of American scientists is important to keep growth of the sciences.

030

Seth Karten @sethkarten.ai · 01/04/2026

Huge money in providing an API to directly get bibtex formatted citations and would fix this issue easily Gscholar doesnt allow this Semantic scholar rate limits Who is building this?

020