evmbench got into ICML!
when we started work on it 11mo ago, cyber risk barely even made it into model cards
superhuman cyber capabilities have since become the first major ai safety risk we face
(fable broke 80%!)
new collab from @paradigm and @OpenAI:
evmbench is a benchmark and agent harness for exploiting smart contract bugs
a few months ago, the best models found <20% of critical, fund-draining @Code4rena bugs in our benchmark. today they find > 70%
Frontiers by @Paradigm returns to San Francisco on October 12-14, 2026!
Frontiers is our intense annual conference & hackathon for those beyond the edge.
No booths, no sponsors, curated audience, stablecoins, ai, robotics, post-quantum cryptography and more.
Apply below!
We're very grateful that OpenAI has provided our teams with assistance to protect Zcash users from these nasty bugs as well. (We also have no new issues to report!)
Applications are now open for the 2026 Paradigm Fellowship: a 4-day retreat for young people who are obsessively good at something technical.
For our fourth year, we're expanding to welcome builders across every frontier — AI, robotics, energy, bio, prediction markets, or something we haven't thought of.
Last year's cohort came from 10 countries. Some were undergrads, some were dropouts, some were founders, some came from OpenAI, SpaceX, Citadel, and Kalshi.
The format is simple: firesides, whiteboarding sessions, and time to hack. What makes it special is what happens in between, and after. Fellows have met cofounders, started companies, and gone on to raise from Paradigm and others.
I was a fellow before joining Paradigm, the retreat was a transformative trip for me, and I met some of my closest friends through the program.
Apply by June 8th. Retreat runs August 12–15th.
Meta is back in the game!
It's been fun to test out Muse Spark. Beyond benchmarks, it's actually a good day to day model... surprisingly good at technical problems and making arcade games.
Never bet against @alexandr_wang@natfriedman@danielgross
Exclusive: Andromeda started out as a project by AI-focused VC firm NFDG.
Now it's a standalone startup with a run rate of $100M and a $1.5B valuation after raising $60M from Paradigm.
I spoke to CEO @WMoushey about his plans to build a better market around global AI compute.
Thrilled to back @WMoushey and @andromeda_ai to build the global market for compute
As compute becomes intelligence, it's rapidly becoming the most important commodity in the world
Andromeda is inflecting off of this. 1+ billion GPU hours and counting!
LIVE NOW - AI Can Now Find 70% of Crypto Exploits | EVMBench w/ Alpin Yukseloglu
@paradigm's @0xalpo joins Bankless to break down:
- EVMBench: a benchmark + “agent harness” for detect → patch → exploit
- Why crypto’s verifiability makes models improve fast
- Blackhat vs whitehat: a 24/7 contract-scanning world
- What happens when “superhuman AI auditors” arrive
Enjoy.
---
TIMESTAMPS
0:00 AI’s exploit leap: 12% → 70% and the “Superhuman auditors”
7:02: Staring at the singularity without losing your mind
10:31 Agency > doom: the Thiel framing
19:10 What’s most at risk (and what’s safer)
23:37 What EVMBench actually is (benchmark + harness)
27:03 Why exploiting is the key: killing false positives
29:24 AI gets “good at crypto” fast: verifiability
30:56 What “70% exploit rate” really means
33:32 Why AI labs avoided crypto (it’s not technical)
43:38 Blackhat vs whitehat: how the race plays out
47:21 Agents and “payments at the speed of light”
51:02 EVM vs Solana: network effects
56:18 AI formal verification as an endgame
58:06 EVMBench V2: expanding the frontier
59:54 Why Alpin stays in crypto