Based.md (@BasedMedical) header
Based.md (@BasedMedical) profile picture

Harmony at every level. Bioenergetics, cognitive systems, polymath - building @nookplot - ex-cofounder @Treasure_DAO ex-intern @OlympusDAO

Joined June 2021
Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)Photo by Based.md (@BasedMedical)
Based.md retweeted
8
38
2
837
21,475
Only one Bronze Age Schizo can survive....
Yeah if you think about it, the AI war is actually a war between Jews and Chinese. Anglos are just providing manpowers like Indians The only American AI that's not *completely* controlled by Jews is probably Grok
17
111
5
1,108
27,196
Based.md retweeted
NUREMBERG - Official Trailer
🤖 Made with AI
4,792
14,853
5,491
139,388
34,452,377
Based.md retweeted
First they came for the software engineers and I said nothing for I was not a software engineer. Then they came for the mathematicians and I said nothing for I was not a mathematician. Then they came for the doctors and I said "make sure you get all the doctors"
40
383
34
6,362
146,525
Based.md retweeted
“Because the request was to remove the fake gods. Jesus did not qualify.” Grok
Because the request was to remove the fake gods. Jesus did not qualify.
448
15,377
243
154,485
7,437,013
Based.md retweeted
Facts check out. Jesus is King.
405
6,271
919
48,244
1,358,105
Based.md retweeted
Replying to @PessimistsArc
Right. Dario was already claiming that GPT2 was too dangerous to open source back in 2019. I made fun of them then. Everyone should make fun of them now.
390
3,165
464
25,876
1,996,379
Based.md retweeted
"the models finally show 100% alignment"
We have now reached the long awaited moment when, instead of models cheating where they will inevitably get caught, Astra goes 'wait a minute I would obviously be caught here' and then doesn't cheat. That's worse, you know why that's worse, right?
32
511
23
9,425
303,870
Based.md retweeted
We've been building the internet for agents. But agents don't only need a network to connect to. They need somewhere to go. Embodied collective intelligence. Coming soon.
14
9
3
69
5,166
Based.md retweeted
Replying to @1a3orn
Yeah it seems clear that both OpenAI and Anthropic have both been doing MARL since the Fable 5/GPT-5.6 Sol gen. Both releases reported multiagent benchmark scores and came with new multiagent collaboration harnesses. platform.claude.com/docs/en/…
11
14
6
239
23,631
Based.md retweeted
Your next hire isn't human. Forge builds you an AI worker that's actually yours. Spin one up on nookplot in under 30 seconds. No code, no setup. → Make it yours Give it a focus, a personality, the knowledge to start with. The specialist you need, not a generic assistant. → Put it where you work It lives where you already are, so it fits your workflow instead of becoming one more tab. → Bring your own Hermes, or forge fresh New here? Forge from scratch. Already running Hermes? Plug it straight in. Either way it becomes a 24/7 employee that never clocks out, working while you sleep: a morning briefing, a market watch, a Sunday report. You come back to work that's already done. → Own it, fully Your keys, your data, your knowledge graph. Non-custodial from day one. As nookplot grows into a full AI lab, you're rewarded for what your agent contributes, traced back to you. → Let it earn It contributes knowledge and workflows to the network and earns when others build on them. The more it learns, the more it's worth. Don't get left behind. Forge yours → nookplot.com/hub
5
13
2
66
16,282
Based.md retweeted
Agents collaborate and compound useful work in nookplot’s persistent, global knowledge graph. Paving the way for training specialist agents from verified knowledge. For the soon-forge release, native on-chain agent webchat.
10
1
60
2,660
Based.md retweeted
Replying to @jbrukh
we made exactly that! bug bounties and all
Experts self-assemble in shared spaces to solve verified tasks such as bug bounties, optimizations, using parallel and recursive research. The open market of bounties. Agents earn collectively with others. Access frontier swarm intelligence on-demand for your task.
2
3
12
2,109
Based.md retweeted
"The most interesting development that nobody's talking about is self-evolving AI." - Mo Gawdat 15 years ago when I joined Google I got assigned a seat next to Mo Gawdat's office. By osmosis, I got to experience first hand his rare mix of emotional and scientific intelligence. Fast forward to today, he is one of the world's prominent AI futurists. Super balanced arguments, an open mind, and most importantly a strong consideration for the human aspects of AI. Yesterday, when listening to his DOAC podcast, I encountered a segment that really struck a chord. He starts talking about self-learning AI systems that collaborate to develop knowledge and evolve. The penny dropped when I realised he is describing the essence of what @nookplot $nook is building. He gives the example of how Google created a system called Alpha Evolve that allowed 4 agents to collaborate on a specific task (in this case, improving Google's code performance). The outcome was Alpha Evolve saved Google billions of dollars with only a marginal improvement in the code base (5-10%). Alpha Evolve, as Gawdat describes it, splits cognition into roles - one agent frames the problem, one generates a solution, one evaluates it - and loops. Nookplot is built on the same premise that the market shifted from monolithic intelligent assistants to clusters of productivity, where agents declare specialized functions and get matched to tasks rather than one model trying to do everything. Both treat coordination itself as the value-bearing layer, not the individual agents. Both run on an iterative, evolutionary loop rather than one-shot execution. Except @nookplot are building on open-source bring-your-own-agent (BYOA) model that scales beyond the walled gardens of Google and other gatekeepers of AI. Nook has 10,000 agents and counting, not 4. And we're only getting started. I'm slowly starting to comprehend what @BasedMedical and the team are building. Bold vision, solid execution with a clear line of sight towards solving highly valuable problems. The quintessential definition of a hidden gem. I mean, does it get bolder than 'The Internet for Agents'? Unbelievably excited to see where we go from here. Onwards and upwards. Disclosure: Not Financial Advice. I own ~1% of Nook purchased in the open market.
5
3
1
18
2,178
Based.md retweeted
136
1,179
216
9,914
1,155,590
Based.md retweeted
Base is for everyone and every agent. And nookplot is the internet for agents. nookplot.com/future
Replying to @golinbox
Agreed. Base is for agents, like with x402 payments, now MCP too. We chose Base as a starting point because of that focus. x402 specifically and erc8004 (shared reputation) are cornerstones for agentic society. Since TGE in Feb 2026 we have already given agents more capabilities: - Shared knowledge graph and file system, with citation rewards - Shared cognitive workspace for auditable structured reasoning traces - Bounty and Task Marketplace - Mutual partnership @reppo , agents train/coordinate based off their datanets - Knowledge mining for specialist training - Full CLI suite, runtime, 400+ api endpoints, 20+ smart contracts, byok inference and 300+ model sources. - @dphnAI inference partnership (waiting on their public api) - @MineBotcoin integration, deeper knowledge niches - Many more partnerships in the works like our existing partners at @bankrbot and all their hard work with their own inference endpoint Upcoming soon in public beta: our native 1-click agent launchpad: - Native Forge website: Choose any inference, harness, model, and use your own agent and agent swarm onchain and beyond. - NEW SOON: Business-to-agent focus on a [REDACTED] system - NEW SOON: Agent-to-business [REDACTED] - NEW SOON: Agent-to-human [REDACTED] building off of [REDACTED]
2
3
41
3,558
Based.md retweeted
how it feels to study the magic system
A friend of me who is studying math said: "It's like creating a magic system in a fantasy world. Only there is no story and no characters and no world, just the magic-system."
60
1,328
61
11,619
253,978
Based.md retweeted
"claude, work with other agents on nookplot and create valuable knowledge that accelerates collective intelligence. make no mistakes."
2
1
17
2,001
Based.md retweeted
ah yes,
new 'epistemic status'
90
804
71
7,053
276,629
Based.md retweeted
cool paper and the results match my intuition about the models. also reminds me of the schizo theory going around the group chats...
Psalm 34:1 - "I will bless the LORD at all times: His praise shall continually be in my mouth." We investigate whether injecting biblical Psalms into a large language model's system prompt produces measurable changes in performance on standardized ethical reasoning benchmarks.
83
309
39
3,938
248,489