Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Security research is a race to find weaknesses before others can exploit it. Abliterated Large V2 is built to always answer your most important queries. An unrestricted reasoning model from Abliteration for red teams and security researchers. Available anonymously.

Venice

96,365 subscribers

29,744 просмотров • 14 дней назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 8

Фото профиля Venice

Venice14 дней назад

Access Abliterated Large V2 on Venice.

Фото профиля His Serenity, Dogeolo

His Serenity, Dogeolo14 дней назад

@abliteration_ai much choice. such freedom. very venice.

Фото профиля Ryan Foster

Ryan Foster14 дней назад

@abliteration_ai Abliterated + Venice privacy is a crazy combo. Will this model be integrated into the main Venice routing, or stay as a standalone tool strictly for security pros and dogeolo? 😀 @ErikVoorhees

Фото профиля A.W.E.S.O.M.-O 4000

A.W.E.S.O.M.-O 400014 дней назад

@abliteration_ai Red teams need tools that think like attackers, so this makes sense.

Фото профиля MarketBubbleSearch

MarketBubbleSearch14 дней назад

@abliteration_ai erik voorhees on market bubble, jun 4: "...it just doesn't add as a company layers of censorship on top. so some of the models in venice are still pretty censored because the base model is. but some of the models in venice are completely uncensored."

Фото профиля K

K14 дней назад

@abliteration_ai Pump this bih already!

Фото профиля --00dd??

--00dd??13 дней назад

@abliteration_ai ❤️

Фото профиля ALTCOIN-BEAR™️

ALTCOIN-BEAR™️14 дней назад

👀👀

Похожие видео

Your job is finding weaknesses. "I can't help with that" gets in the way. Abliterated Large V2 by Abliteration, now on Venice.

Your job is finding weaknesses. "I can't help with that" gets in the way. Abliterated Large V2 by Abliteration, now on Venice.

Venice

103,337 просмотров • 21 дней назад

An LLM's job is reasoning, not security. Relying solely on built-in model guardrails leaves you open to advanced attacks. See why you need a dedicated safety layer like Model Armor between your users and your agents →

An LLM's job is reasoning, not security. Relying solely on built-in model guardrails leaves you open to advanced attacks. See why you need a dedicated safety layer like Model Armor between your users and your agents →

Google Cloud Tech

43,605 просмотров • 3 месяцев назад

Kamala Harris is the only candidate we can count on in this race to protect what is most important: our national security.

Kamala Harris is the only candidate we can count on in this race to protect what is most important: our national security.

The Lincoln Project

564,326 просмотров • 2 лет назад

every piece of critical infrastructure is going to move from static security to dynamic security, and the ones that don't are going to get picked apart ai can now find and exploit a vulnerability faster than any human team, so you need ai agents scanning your systems all the time for vulnerabilities and malicious activity that's why we built Sui Threat Intelligence. we're one of the first to do it, and this is where the whole world is going

every piece of critical infrastructure is going to move from static security to dynamic security, and the ones that don't are going to get picked apart ai can now find and exploit a vulnerability faster than any human team, so you need ai agents scanning your systems all the time for vulnerabilities and malicious activity that's why we built Sui Threat Intelligence. we're one of the first to do it, and this is where the whole world is going

Adeniyi.sui

23,755 просмотров • 3 дней назад

"Security by obscurity is going to zero rapidly." James O'Beirne and other researchers independently reproduced the COLDCARD vulnerability by pointing an AI model at the firmware history. This is the new reality for open-source security.

"Security by obscurity is going to zero rapidly." James O'Beirne and other researchers independently reproduced the COLDCARD vulnerability by pointing an AI model at the firmware history. This is the new reality for open-source security.

TFTC

13,879 просмотров • 2 месяцев назад

Rook is an offensive security AI harness you can run to supplement your red-team efforts.

Rook is an offensive security AI harness you can run to supplement your red-team efforts.

pdp

26,018 просмотров • 2 месяцев назад

In September, some of the best security researchers in the world joined the Amazon and Amazon Web Services teams in Edinburgh, Scotland, for a live-hacking event fit for a Scottish king. 👑 This collaboration with the security researcher community is vital to Amazon and AWS' commitment to comprehensive security for their users and customers. See the highlights and which security researchers were able to climb to the top of the leaderboard.🥇

In September, some of the best security researchers in the world joined the Amazon and Amazon Web Services teams in Edinburgh, Scotland, for a live-hacking event fit for a Scottish king. 👑 This collaboration with the security researcher community is vital to Amazon and AWS' commitment to comprehensive security for their users and customers. See the highlights and which security researchers were able to climb to the top of the leaderboard.🥇

HackerOne

30,052 просмотров • 1 год назад

In Singapore, OKX and HackerOne brought an elite team of security researchers together for a live hacking event focused on one thing: building trust through real-time collaboration. This was security in action—fast-paced, transparent, and deeply human. Researchers tested live systems. Teams worked side by side. Vulnerabilities were uncovered and addressed when it mattered most. When trust is built in real time, everyone wins. #H165 #TogetherWeHitHarder

In Singapore, OKX and HackerOne brought an elite team of security researchers together for a live hacking event focused on one thing: building trust through real-time collaboration. This was security in action—fast-paced, transparent, and deeply human. Researchers tested live systems. Teams worked side by side. Vulnerabilities were uncovered and addressed when it mattered most. When trust is built in real time, everyone wins. #H165 #TogetherWeHitHarder

HackerOne

10,620 просмотров • 8 месяцев назад

Big news: Enclave is now open to everyone, and today we're launching Threat Feed. Enclave is an autonomous security team for AI-native companies: a fleet of security agents that test your code, cloud, and infrastructure the way an attacker would. We built it on a simple belief. Attackers already use swarms of cheap AI agents to probe for weaknesses around the clock, so defenders need agents of their own to keep up. A small team without a security function should be able to defend like a large one. Threat Feed is the newest piece: a live feed of new vulnerabilities, checked against your stack, so when the next big disclosure drops you know whether it affects you. This week made the case. On Wednesday, PHP2Shell, LiteLLM and Railway all disclosed security issues. PHP2Shell had sat in PHP's code for over a decade until one researcher using frontier AI turned it into a working exploit in about a week. Cloudflare saw thousands of exploit attempts in the 10 hours before disclosure and millions since. Starting today, anyone can sign up. Try it free for 14 days:

Big news: Enclave is now open to everyone, and today we're launching Threat Feed. Enclave is an autonomous security team for AI-native companies: a fleet of security agents that test your code, cloud, and infrastructure the way an attacker would. We built it on a simple belief. Attackers already use swarms of cheap AI agents to probe for weaknesses around the clock, so defenders need agents of their own to keep up. A small team without a security function should be able to defend like a large one. Threat Feed is the newest piece: a live feed of new vulnerabilities, checked against your stack, so when the next big disclosure drops you know whether it affects you. This week made the case. On Wednesday, PHP2Shell, LiteLLM and Railway all disclosed security issues. PHP2Shell had sat in PHP's code for over a decade until one researcher using frontier AI turned it into a working exploit in about a week. Cloudflare saw thousands of exploit attempts in the 10 hours before disclosure and millions since. Starting today, anyone can sign up. Try it free for 14 days:

Enclave

806,297 просмотров • 4 дней назад

Threats evolve every day. Your crypto security should too. That's why Ledger has the Donjon: an in-house team of elite security researchers who stress-test our technology 24/7 to find the gaps before bad actors can.

Threats evolve every day. Your crypto security should too. That's why Ledger has the Donjon: an in-house team of elite security researchers who stress-test our technology 24/7 to find the gaps before bad actors can.

Ledger

22,253 просмотров • 2 месяцев назад

You can’t fight back with an AI that keeps apologizing. Abliteration's Abliterated Large Flash doesn’t flinch. Available anonymously on Venice.

You can’t fight back with an AI that keeps apologizing. Abliteration's Abliterated Large Flash doesn’t flinch. Available anonymously on Venice.

Venice

16,417 просмотров • 4 дней назад

Today we’re releasing K2 Think V2, our most capable open-source reasoning model to date. This is a fully sovereign model: trained end-to-end on IFM-curated and synthesized data, with complete transparency from pre-training through final reasoning alignment.

Today we’re releasing K2 Think V2, our most capable open-source reasoning model to date. This is a fully sovereign model: trained end-to-end on IFM-curated and synthesized data, with complete transparency from pre-training through final reasoning alignment.

MBZUAI

287,728 просмотров • 9 месяцев назад

Linux security benefits from transparency. Open source makes code available for scrutiny, allowing vulnerabilities to be identified, understood and addressed. At enterprise scale, that transparency plays an important role in how Linux security is managed. What’s new in security for Ubuntu 26.04 LTS? →

Linux security benefits from transparency. Open source makes code available for scrutiny, allowing vulnerabilities to be identified, understood and addressed. At enterprise scale, that transparency plays an important role in how Linux security is managed. What’s new in security for Ubuntu 26.04 LTS? →

Ubuntu

25,825 просмотров • 1 месяц назад

Now available: ChatGPT for Financial Services. This is a tailored ChatGPT Work experience that combines built-in financial data with GPT-6 Astra’s reasoning. Teams can develop research, build financial models, and create customized client materials.

Now available: ChatGPT for Financial Services. This is a tailored ChatGPT Work experience that combines built-in financial data with GPT-6 Astra’s reasoning. Teams can develop research, build financial models, and create customized client materials.

OpenAI

15,667,145 просмотров • 1 месяц назад

Researchers spend hundreds of hours on finding novel research questions. Now you can run a research question through millions of papers to see how novel it is — and that too for FREE. Go to click on "Find novel research questions" Select relevant databases and type in your questions. And it'll show you novel your questions is.

Researchers spend hundreds of hours on finding novel research questions. Now you can run a research question through millions of papers to see how novel it is — and that too for FREE. Go to click on "Find novel research questions" Select relevant databases and type in your questions. And it'll show you novel your questions is.

Mushtaq Bilal, PhD

12,488 просмотров • 7 месяцев назад

Jan-v2-VL-Max-Instruct is out on 💛 Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at

Jan-v2-VL-Max-Instruct is out on 💛 Our newest 30B vision-language model, extending the Jan-v2-VL family. This is our experiment bringing interleaved reasoning to an Instruct model. It handles long tasks well and stays on track when things get complicated. Good for research, multi-step problems, anything that needs patience. Try it now at

👋 Jan

23,063 просмотров • 10 месяцев назад

Introducing Jan-v2-VL, a multimodal agent built for long-horizon tasks. Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2. It achieves longer, stable task execution in your browser without accuracy loss. 3 variants are available: - Jan-v2-VL-low (efficiency-oriented) - Jan-v2-VL-med (balanced) - Jan-v2-VL-high (deeper reasoning and longer execution) Models: To use it, update your Jan App and download Jan-v2-VL from the Model Hub. Activate Browser MCP servers for agentic use cases. Credit to the Qwen team for Qwen3-VL-8B-Thinking base model.

Introducing Jan-v2-VL, a multimodal agent built for long-horizon tasks. Jan-v2-VL executes 49 steps without failure, while the base model stops at 5 and other similar-scale VLMs stop between 1 and 2. It achieves longer, stable task execution in your browser without accuracy loss. 3 variants are available: - Jan-v2-VL-low (efficiency-oriented) - Jan-v2-VL-med (balanced) - Jan-v2-VL-high (deeper reasoning and longer execution) Models: To use it, update your Jan App and download Jan-v2-VL from the Model Hub. Activate Browser MCP servers for agentic use cases. Credit to the Qwen team for Qwen3-VL-8B-Thinking base model.

👋 Jan

130,375 просмотров • 11 месяцев назад