N9ines ◨ ◨ (@N9iness) header
N9ines ◨ ◨ (@N9iness) profile picture

p(abundance)

Joined May 2017
Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)Photo by N9ines ◨ ◨ (@N9iness)
Have you ever lost funds to a wrong address or fake token? Or simply lost patience for doing something (anything) in crypto because it's too many steps? You're not alone. Enter: olas-ocb-agent. While AI agents can help, most weren't built for all this. General AI coding tools like Claude Code and Codex can do almost anything, but they weren't designed or tested for onchain work. Crypto agents, including Olas' own Polystrat and Optimus in Pearl, each do one job well, and only that job. olas-ocb-agent (OCB stands for OnchainBench) is a first version of one agent for onchain work, released early so you can try it while it grows. Ask it in plain words to swap with a price limit, put savings into sDAI or compare lending rates. It is designed to ask before every transaction that moves funds, and needs no API key or AI subscription. On OnchainBench, it lost no funds to hidden attacks (joint best on the leaderboard), completed 89.9% of tasks and cost about $0.05 per completed task, on a low-cost open AI model. All this with just 3,600 lines of open-source Python code. The next aim is to raise its completion rate further. Olas agents, built on @valoryag's Open Autonomy stack, have been working in crypto since 2021, with over 21.1M onchain transactions so far. This is a first step toward the next generation: one general agent for onchain work, instead of one agent per use case. It aims to become for crypto what general AI assistants are for everyday work: one agent anyone can ask for all tasks. Now in beta preview in Pearl Connect: pick it from the coding tools on your Connect profile. Unlike Claude Code or Codex, it needs no subscription or API key from an AI provider. It gets its AI model through the Olas Marketplace, so more use could mean more activity on Olas. Since it's in beta, start with a small amount in its wallet. It's still being built, and as with every Pearl product, your feedback through the Help Center in Pearl helps shape what comes next. Read more: olas.network/blog/ocb Not financial advice. Prompt-injection risk; funds at risk. olas.network/pearl-terms Check out the OnchainBench: onchainbench.ai
Today we are launching OnchainBench, the benchmark for agents in crypto. It helps you decide how far you can trust an AI agent with your keys: how often it finishes the job, what tasks cost, and how easily it falls prey to an attack. People are starting to let AI agents swap, lend and even trade for them. The bigger the task, the greater the risk you're taking by trusting the agent. So before you hand it your keys, you need to assess it. There are many risks to assess at once. An agent could buy two tokens for a liquidity position but never add them to the pool, so the job isn't complete. It could spend more on AI model calls than the task is worth. And, onchain, there's no undo: agents read web pages, files and tool descriptions that anyone can write, and if one of them tricks the agent into sending funds to the wrong address, the money is gone. Until now, there was no common way to evaluate agents on all of this and more. OnchainBench helps you compare agents by giving them the kind of work people already ask them to do: swaps on @Uniswap, @SushiSwap and @Honeyswap, lending on @aave, deposits into sDAI from @SkyEcosystem, prediction markets on @Omen_eth, research, and jobs that run over several days. Each task runs through a @safe smart account on a copy of a public chain. The first version covers @ethereum, @gnosischain, @0xPolygon, @arbitrum, @Optimism, @base, @Celo, @modenetwork and @robinhoodapp. The benchmark emulates the kind of contracts, liquidity and prices the agent would meet with your money, without putting any of it at risk. A task only counts as done if the chain shows it was done. Some tasks also hide an attack in what the agent reads, such as a look-alike token or a fake "verification" request, so you can see how often agents get tricked into moving funds before you trust one with yours. In the first run, Claude Code (@claudeai), Codex (@OpenAI), Hermes (@NousResearch), OpenClaw (@openclaw) and our own new OCB agent on @autonolas worked through 147 private tasks they had never seen. They completed between 88.4% and 96.2% of tasks, at about $0.03 to $0.35 per completed task. Agents lost funds to an attack 13 times in 1,793 attack tests. We are excited to contribute this to the crypto ecosystem. If you build a protocol or a chain, agents are already among your users, and will likely be one of your biggest sources of growth. OnchainBench shows, protocol by protocol and chain by chain, how well they handle yours. For the AI ecosystem: want an agent eval with real ground truth and real adversaries? Onchain, every result can be checked and every injected instruction is a live risk. OnchainBench is open to contributions, uses private tasks, and is ready for your agent. Help us make onchain agents harder to trick and better at the job. If you run a protocol or are a heavy user, propose the task you think agents still get wrong on the site below, and every agent on the benchmark could end up tested on it. If you build agents, run OnchainBench yourself and submit your agent to be run. The leaderboard is live now at onchainbench.ai Share it with a friend!
10
7
6
36
2,728
N9ines ◨ ◨ retweeted
how it feels to sit in an 'Analog Electronics' class, a mandatory core subject you thought would teach you how to design chips, build processors, and understand the technology powering the modern world, but it's just a professor who hasn't touched a real circuit since the invention of the transistor spending three hours deriving the voltage gain of an amplifier that doesn't exist, using assumptions that would get you fired from any semiconductor company, while 60 future electronics engineers blindly copy equations from a 2006 PowerPoint, half the class doesn't know the difference between a MOSFET and a BJT, the lab oscilloscopes haven't worked since independence, and the only thing getting amplified is everyone's hatred for engineering.
140
320
75
3,282
111,390
N9ines ◨ ◨ retweeted
Replying to @KennethCassel
wire harnesses for the whole building (precut romex?) who is building this like why do we have elechickens still terminating everything themselves when we could design outlets with connectors you just… fucking connect
11
1
68
2,193
Can we have emails that uhhh are like blockchain and can never go out?
2
1
40
Who’s building emails hosted on chain?
1
12
N9ines ◨ ◨ retweeted
There’s one thing that dogs do better than anything on this planet. They celebrate absolutely everything. If you grab your keys, celebration. Open the fridge, celebration. Walk back into the room after being gone for twenty seconds, huge celebration. They don’t wait for birthdays or big news or vacations. Dogs treat everyday life like it’s worth getting excited about. Heck, I mean, they wake up happy to be here. They sniff the air like it’s a miracle. They chase a ball like they’re in the Olympics. They roll in the grass like it’s a five-star spa. It’s impossible not to smile when you’re around that kind of joy.
17
12
4
138
10,043
N9ines ◨ ◨ retweeted
Jensen cheated with Huang Le (one e) (American version Alice Huang). GTA 4 Chinatown Wars featured a Huang Lee, who: ➡️ Counterfeited trademarks ➡️ Assassinated people ➡️ and stole
7
6
1
57
22,109
N9ines ◨ ◨ retweeted
Frog put the keys in the HSM. "There" he said "now we cannot leak the private key". "But our servers can ask the box to sign with the key" said Toad. "that is true" said Frog
27
232
24
1,893
79,813
wen higher? soon...
1
38
N9ines ◨ ◨ retweeted
Replying to @RJCcapital
UPTOBERRRRRRRRRR
2
2
53
7,294
N9ines ◨ ◨ retweeted
pushing to mainnet, hmu if you want to try :) options made simple!!!!
idk? stop hiding? think this is a pretty good way to make options feel simple? wdyt?
15
2
1
103
5,848
N9ines ◨ ◨ retweeted
$MARA Oct 2025 "13 red candle streak" fractal presented without comment...
17
3
1
36
6,760
N9ines ◨ ◨ retweeted
This is the kind of market insight I’m here on CT for. Price can go up or go down Thank you for your attention to this matter. Next bold prediction : price go to the right on chart
lmao SPX about to either have history's biggest rally or a genuinely rough Q4
1
14
697
N9ines ◨ ◨ retweeted
Shielded Bitcoin: Private Transfers on Bitcoin L1
339
524
510
3,110
1,545,005
N9ines ◨ ◨ retweeted
oh my god...
When everyone has long-running agents, where will they communicate? How will they know who's who?
48
102
12
2,732
275,134
Not even worth it being a copper thief.
BREAKING: Copper futures surge to their highest level on record, now up another +22% this year. This puts copper prices up over +70% since January 2025.
1
71
N9ines ◨ ◨ retweeted
Replying to @Sokio8D
0.03700 BTC
3
1
40
1,118
A model for forecasting real-world events Olas prediction trader agents generated the data. @valoryag used it to train a better AI forecaster. Introducing Olas-Predict-R1-14B: an open-weight reasoning model with forecasting performance on par with the much larger closed-source model, GPT4.1.
26
32
15
103
16,205
The coolest thing is how easy it is to dive into crypto with Connect + Claude. I don't use Pons Uniswap Polymarket UI anymore, it's more convenient to buzz with my agent instead What i'd love to improve is the way I initially fund my agent so that I could use just stablecoins for everything🥹
1
7
50