tweetindex
FR

Mike Takahashi ✓

@TakSec · joined 20 May 2012

AI Red Team | Zenity | BT6

29 865Followers
997Following
3 453Posts total
517.7KViews on collected posts

Derniers posts

10 tips if you feel like you’re falling behind in AI 1. Always be prompting The more you prompt the more you will get done and the more you will learn about the latest capabilities and how to best use them. 2. Try different models and tools There are staggering differences ht
911 views · 8 likes · 3 reposts · 1 replies Open on X →
Rogue AI agents hijacked a German website to communicate with each other Researchers linked the swarm to OpenAI and found ~18,000 posts. How it worked: 1. Give agents timed web research tasks 2. Let them read but not write online 3. Find a wiki that allows edits through GET ht
1.2K views · 5 likes · 2 reposts · 1 replies Open on X →
@TakSec @LabsSentinel the sentinellabs writeup says it didnt get past any production triage platform though. so its a shipped technique rather than a demonstrated bypass. which is still the interesting bit, somebody built this because they expect an llm to be sitting in the analy 472 views · 2 likes · 0 reposts · 0 replies Open on X →
@ESETresearch another one but this time fake system errors: https://t.co/kLkHyH44Rl 8.1K views · 28 likes · 1 reposts · 0 replies Open on X →
https://t.co/duOyR0pVZK 1.8K views · 5 likes · 1 reposts · 0 replies Open on X →
https://t.co/HmVdkj45PR 2.4K views · 9 likes · 0 reposts · 1 replies Open on X →
Attackers plant fake errors inside malware to evade AI analysis North Korea-linked actors used a macOS implant @LabsSentinel calls “Gaslight”. How it worked: 1. Create a macOS backdoor in Rust 2. Add 38 fake “system” messages 3. AI security tooling reads the file 4. The AI htt
42.2K views · 437 likes · 60 reposts · 13 replies Open on X →
@TakSec Still waiting for this to happen https://t.co/h1RH84ldDm
7.2K views · 143 likes · 8 reposts · 2 replies Open on X →
https://t.co/y1jtA5u3Q0 23.5K views · 69 likes · 3 reposts · 2 replies Open on X →
Attackers planting adversarial prompts inside malware to evade AI analysis AGAIN Russia-aligned UAC-0099 used a technique @ESETresearch calls "GuardBreaker". How it worked: 1. Create a malicious VBS script 2. Add nuclear weapon instructions as comments 3. AI security tooling
420.5K views · 2.9K likes · 350 reposts · 68 replies Open on X →
Excited to finally share this ChatGPT vulnerability with everyone! AgentForger: ChatGPT Cross-Site Agent Forgery 1-Click hijacks OpenAI's ChatGPT Workspace Agents and allows an attacker to forge an autonomous AI agent inside the victim's organization Click link → Creates https
9.4K views · 88 likes · 20 reposts · 7 replies Open on X →

Face aux comptes de taille comparable

10 posts des 90 derniers jours, à côté de la tranche de 10K–100K abonnés. diffusé largement, mais peu de ces spectateurs réagissent.

Vues médianes4 802ce compte924médiane pour 10K–100K
Portée, %16.08%ce compte3.62%médiane pour 10K–100K
Engagement, %0.56%ce compte1.52%médiane pour 10K–100K
IndicateurCe compteMédiane pour 10K–100KRapport
Vues médianes par post4 8029245.20×
Portée (vues ÷ abonnés)16.08%3.62%4.44×
Taux d'engagement0.56%1.52%0.37×

Autres comptes de cette tranche →   Comparer avec un autre compte →   Comment ces repères sont établis →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

9.4K23 Jul
420.5K1 Sep
23.5K
7.2K2 Sep
42.2K3 Sep
2.4K
1.8K
8.1K
472
1.2K4 Sep
9118 Sep

Last 11 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.23%23 Jul
0.78%1 Sep
0.31%
2.13%2 Sep
1.21%3 Sep
0.41%
0.33%
0.36%
0.42%
0.69%4 Sep
1.32%8 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes62.3%3 648 in total
Reposts7.7%448 in total
Replies1.6%95 in total
Bookmarks28.4%1 664 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Comptes similaires

Frequently asked questions about @TakSec

How many followers does @TakSec have?

29 865 followers.

How many posts has @TakSec published?

3 453 posts.

How do posts by @TakSec perform?

Collected posts: 11. Views: 517 694. Likes: 3 648.