Deep3 Labs

49.7K posts

Deep3 Labs banner
Deep3 Labs

Deep3 Labs

@deep3labs

We’re training on the richest AI dataset no one else is using. Ex @google @meta @apple @mit @stanford

Alpha no one else has → Katılım Ağustos 2022
3.4K Takip Edilen6.3K Takipçiler
Sabitlenmiş Tweet
Deep3 Labs
Deep3 Labs@deep3labs·
There's new agents coming on chain every minute. There's plenty of teams trying to build "trust scores" for the ones that identify themselves. But what about the agents that don't? So we decided to see if machine learning can tell the difference btw humans and agents. 🧵👇
English
5
4
31
1.4K
deployer
deployer@0xDeployer·
hearing things about an upcoming launch on rh. product looks good.
English
94
10
382
39.6K
deployer
deployer@0xDeployer·
welcome to the bankr ecosystem!
AgentOS@useAgentOS

1/3 🤖 Meet AgentOS: A Token-efficient, Microkernel AI agent with on-device model routing across CLI, Web UI, and chat. A local router reads every message on your device and sends it to the cheapest model that can still do the job well. You stop overpaying for AI. ⚡ What makes it stand out: ■ Smart on-device model routing across 20+ providers ( @bankrbot LLM Gateway, OpenRouter, OpenAI, Anthropic, Ollama, and more). ■ Persistent local memory that survives restarts. ■ A layered security sandbox (Standard, Strict, Locked). ■ 37 built-in skills plus MCP, loaded only when a task needs them, and more ■ One unified gateway for CLI, Web UI, Slack, Telegram, Discord, and more Remember this: AgentOS has been integrated with the Bankr LLM Gateway since day one. That means any Bankr user with Bankr API key can start using AgentOS in minutes. Let the router cook.

English
18
11
124
22.1K
1Claw AI
1Claw AI@1clawAI·
Robinhood Chain is pulling serious onchain volume. The next unlock is agents trading it autonomously, and the blocker was always the key. 1Claw keeps the signing key in hardware and gives the agent only a gated intent to sign. No bot holds your key. @RobinhoodApp @base @VirtualsIO
English
2
1
10
397
Mike- The Base Junkie
Mike- The Base Junkie@BaseJunkie_·
🔥 LIVE TONIGHT on Fireside Media 🔥 We’re joined by @e2005pe to talk all things @vapeXengine — spotting runners, scanning Base and B20 action, the journey so far, and what’s next. Powered by @farcaster_xyz. ⏰ 12:30 PM PST ⏰ 8:30 PM GMT+1 See you there tonight 🔥
Mike- The Base Junkie tweet media
English
7
13
32
1.4K
TMAS
TMAS@ohheyitstmas·
This has got to be the dumbest thing ever created Just because it went up in the past means it has to go up in the future?
TMAS tweet media
English
12
0
35
936
Deep3 Labs retweetledi
Deep3 Labs
Deep3 Labs@deep3labs·
We built a new way to visualize onchain agent activity: x402 payments on @base, mapped so you can actually see which agents cluster around which tools, who's quietly dominating, and more importantly...who's just passing money back and forth. It wasn't what we expected. 👇
English
9
6
44
20.2K
igli.eth
igli.eth@IGLIVISION·
Mutuals can you really see my post ???
English
12
0
35
903
Nikita Bier
Nikita Bier@nikitabier·
Replies: +3.15% Original Posts: +1.8% Small Account Reach: +1.19% Time Spent: -0.13% Unregretted Time Spent: ∞
English
2.9K
810
8.9K
691.6K
FFV
FFV@FF_V12·
Holy sht, I’m actually seeing my friends on my time line again and not some dude getting be headed in Uganda That little dork Nikita actually did something right for once You guys notice the difference?
English
115
4
290
7.4K
TotalWorld
TotalWorld@TotalWorldApps·
@deep3labs good point about unregistered agents. ml diff is probably the right move instead of trying to reg all anon actors.
English
1
0
1
10
Deep3 Labs
Deep3 Labs@deep3labs·
There's new agents coming on chain every minute. There's plenty of teams trying to build "trust scores" for the ones that identify themselves. But what about the agents that don't? So we decided to see if machine learning can tell the difference btw humans and agents. 🧵👇
English
5
4
31
1.4K
Deep3 Labs
Deep3 Labs@deep3labs·
We can't govern, inspect or value what we can't see. And "Trust Scores" only get you so far when you can't trust that agents will identify themselves in the first place. This was just a research question for now, but reach out if you want to use the model or to learn more! 🤝
Deep3 Labs tweet media
English
1
0
3
48
Deep3 Labs
Deep3 Labs@deep3labs·
And of course, we also had to make it look cool... Orange points are machines. Blue are humans. The 2D surface in between is a kNN density boundary that shows one possible human/machine separator. 😎😎😎
English
1
0
6
53