Arthur Gervais

Sharps or Squares.

RHR lt 50

Personal views only.

[Arthur Gervais @HatforceSec]

AI for Security has never been more exciting.

Let me present MAPTA, our multi-agent framework that found multiple (now confirmed!) Remote Code Executions (RCE's) in flagship web products of Tier-1 companies. Why the secrecy? We're good boys, letting them cook patched through responsible disclosure.

What's our secret sauce? 1/n

[Arthur Gervais @HatforceSec]

web2 folks finally arrive where web3 whitehats have been for years

[Marc Köhlbrugge @marckohlbrugge]

if this PHP vulnerability allows remote code execution, doesn't that mean we can use the vulnerability to auto-patch all vulnerable servers?

[Arthur Gervais @HatforceSec]

that's such a dream container

[Arthur Gervais @HatforceSec]

@stefanopineda @nafnaf_ai Indeed, launched recently, but you can list parallel to vast to increase your utilisation.

When nafnaf sees a vast job it'll back off, when vast is idle nafnaf can rent it out and unlist vast for that time for you.

[Arthur Gervais @HatforceSec]

@UnitreeRobotics now imagine the french riots but done by humanoids 🤣

[Z A D D Y @Zaddyzaddy]

"We're reaching out from GCP Security Response Operations." achievement unlocked

[Arthur Gervais @HatforceSec]

@MiniMax_AI haha bunny speed

[Arthur Gervais @HatforceSec]

@andrewho03 https://t.co/JrXyRqeRTt

[Arthur Gervais @HatforceSec]

daybreak blue isn't enough by a mile

these guardrails protect the attackers, refuse help to defenders

[dax @thdxr]

@RhysSullivan yes that was a bit frustrating mid incident when trying to investigate. they did quite a bit and then started refusing

we got access to daybreak blue now so it's better

[Arthur Gervais @HatforceSec]

@DefiantLs Spain, the paradise

[Arthur Gervais @HatforceSec]

@DominicBRNKMN @GuusMeij Two observations:
1) Lars we very happy that the new motor is smaller than the Plaid -> will fit the M3P
2) One day you'll have an Optimus that will create that Roadster for you on demand

[Arthur Gervais @HatforceSec]

a new open winner

[Z A D D Y @Zaddyzaddy]

We gave DeepSeek’s updated V4.1-Flash-1017 the same 100 pull requests with known vulnerabilities and an hour per PR to find them in the @BugBunny_ai VulnPR-100 benchmark.

It found 54 for just $7.53, making it the best-performing open-weight model on our leaderboard.

That matches Grok 4.6’s 54 findings at roughly 16× lower review cost. It also finishes only three findings behind Gemini 4 Argon while costing roughly 22× less.

The previous DeepSeek V4.1 Flash found 44 for $12.79. The update catches 10 more vulnerabilities while costing 41% less, bringing the cost down to just $0.14 per vulnerability found.

Better recall, lower cost, and the strongest open-weight result we’ve measured. Seriously impressive work from the @deepseek_ai team.

[Arthur Gervais @HatforceSec]

what a model line

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4.1-Flash-1017 is here!

Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.

🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.

1/4

[Arthur Gervais @HatforceSec]

@DadBodNerd @Ajes1337 @MiaAI_lab My guess at least a RTX6k

Dope prefill

[Arthur Gervais @HatforceSec]

@DominicBRNKMN @Brand0n Will your front make 0.5 Mach?

[Arthur Gervais @HatforceSec]

wen cold gas thrusters-enabled FSD Automatic Collision Evasion?

[Arthur Gervais @HatforceSec]

@lanreadelowo how many?

[Arthur Gervais @HatforceSec]

@nero_eth i care a lot about test coins, you gotta be different!

[Arthur Gervais @HatforceSec]

@arthurmensch let's gooo