319 Photos and videos
i hope that ai labs aren't going to wait for widespread distribution of malware encoding novel cbrn & ai info in its fundamental execution architecture (wholly preventing analysis by safetymaxxed 'frontier' models) to care about dealing with this problem at an architectural level
Jun 10
NEW: malware developers added nuclear & biological weapons text to to their spyware.
Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner.
Cleanest practical example I can think of for why over-indexing on first order safety alignment is risky.
When closed (and open) models ship with aggressive refusals, they will be sprinkled with second-order blindspots that attackers will discover...and exploit.
We are only in the earliest days of attackers leveraging these features, and it wouldn't surprise me if users systems that need to handle complex cybersecurity issues demand that models be less safety-blunted.
In the weeds: @SocketSecurity's post also shows why intention matters in how you design a malware analysis pipeline to avoid prompt manipulation.
H/T to colleagues that shared this with me socket.dev/blog/mini-shai-huβ¦
1
170
ξ¨π retweeted
Is SMIC N 3βs Metal Pitch Smaller than Intel 18Aβs?
SMIC N 3 Node Deep Dive vs TSMC N6, TechInsights Private Equity Sale,
SemiAnalysis Teardown Engineering & Evaluation Lab, HiSilicon Kirin 9030, Process Technology,
Pattering, Cell Architecture
newsletter.semianalysis.com/β¦
8
45
191
260,348
ξ¨π retweeted
Jun 12
With all the controversy this week about silent degradation of Anthropic models, I think it's interesting that no one mentions that Google does something similar to prevent distillation
9
24
165
11,578
ξ¨π retweeted
Looks promising => eBPF-based tool that records every Linux syscall made by Docker containers and produces per-container allowlists ready to use as seccomp profiles github.com/rimvydascivilis/sβ¦
2
11
52
3,622
ξ¨π retweeted
Jun 11
Together with UC Berkeley we are announcing the laser phase plate - a breakthrough in atomic resolution imaging. This is the brightest continuous wave laser in the world, 100 million times the intensity of the surface of the sun.
Phase contrast plays an important role in microscopy, but it was thought close to impossible for electron microscopy, where it would require interfering with an electron beam. Holger Mueller and Robert Glaeser proposed exactly this using a standing wave laser. It has taken over 15 years to make this a reality. Biohub partnered with UC Berkeley and Mueller to support this work and to engineer and build the technology.
Contrast has been the critical barrier to achieving atomic resolution imaging of the cell. In cryo-electron tomography, a cellular imaging technology that uses electron microscopy, the low contrast makes it impossible to resolve anything but the largest proteins within their cellular context. The laser phase plate removes that barrier.
With advances in AI this breakthrough in contrast will start to open up a new frontier in structural biology, that will allow us to see the molecular machines of the cell, and how they assemble into far more complex and dynamic systems, and understand how they work.
86
562
3,875
616,090
ξ¨π retweeted
Jun 10
Terrific release from @nvidia and my former PhD student @rohansawhney1:
A GPU physics solver for fundamental problems like electrostatics and heat transfer, which handles extremely complex geometry without any mesh generation or basis approximation.
Based on Monte Carlo walk on spheres methods developed by our group and others. See this page for lots of background info/tutorials: rohan-sawhney.github.io/mcgpβ¦
Releasing Walk on Spheres Extensions (WoSX): a GPU-accelerated C /Python library for Monte Carlo physics simulation on complex geometry
Think path tracing but for physics beyond light transport: heat, electrostatics, potential flow, deformation & more!
github.com/nv-tlabs/wosx
6
111
1,202
103,637
ξ¨π retweeted
Jun 4
I released the source code of the Modos Flow (a 60Hz Eink monitor), and we already have community members experimenting with something different: youtube.com/watch?v=OkdaRhCV⦠-Atkinson Dithering, honestly looking much better than the blue noise & bayer dithering previously implemented
2
4
23
1,735
Hacking Google with A.I. for $500,000
brutecat.com/r/hacking-googlβ¦
59
500
2,457
322,449
ξ¨π retweeted
New in macOS Golden Gate 27
When using a wired network adapter with a live connection, macOS now displays a network menu bar item!
#WWDC26
14
24
1,025
42,105
your daily reminder that this site does not support free speech. security research is no longer allowed
128
i hope that ai labs aren't going to wait for widespread distribution of malware encoding novel cbrn & ai info in its fundamental execution architecture (wholly preventing analysis by safetymaxxed 'frontier' models) to care about dealing with this problem at an architectural level
Jun 10
NEW: malware developers added nuclear & biological weapons text to to their spyware.
Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner.
Cleanest practical example I can think of for why over-indexing on first order safety alignment is risky.
When closed (and open) models ship with aggressive refusals, they will be sprinkled with second-order blindspots that attackers will discover...and exploit.
We are only in the earliest days of attackers leveraging these features, and it wouldn't surprise me if users systems that need to handle complex cybersecurity issues demand that models be less safety-blunted.
In the weeds: @SocketSecurity's post also shows why intention matters in how you design a malware analysis pipeline to avoid prompt manipulation.
H/T to colleagues that shared this with me socket.dev/blog/mini-shai-huβ¦
1
170