2025-02-06
Mister Rogers on How to Talk to Kids About Distressing News Events
In 2002, Fred Rogers wrote a parenting book as a resource for caregivers of children aged two to six. One of the topics he covered was how to talk to...
A list of all the lawsuits related to Trump administration executive orders....
A list of all the lawsuits related to Trump administration executive orders. “More than thirty lawsuits have been filed and we are trying our best to keep this page updated...
The Musk staffer who broke into the Treasury Dept system has quit...
The Musk staffer who broke into the Treasury Dept system has quit after the discovery of racist Twitter posts (gift link): advocating repealing the Civil Rights Act, “You could not...
Are People Noticing the Internet Is Slowly Becoming Unusable?
The internet is no longer free and open. It is now a prison. The open web is shrinking as companies force users to remain inside their platforms. Any free content...
“The Oligarchs Who Came to Regret Supporting Hitler”
Historian Timothy Ryback, the author of Takeover: Hitler’s Final Rise to Power who also wrote the popular article How Hitler Dismantled a Democracy in 53 Days, has a new piece...
Business foot traffic is up within the [NYC] congestion pricing zone. “People...
Business foot traffic is up within the [NYC] congestion pricing zone. “People were concerned that fewer vehicles would mean fewer people visiting the zone, and that seems to not be...
★ Bootable Mac Startup Drive Backups, and Another Ode to SuperDuper
I know how different storage is today — abundant, cheap, reliable — but I still have feelings about my data that are rooted in the distant past.
Hackers Are Becoming a Rarer Breed
Hackers have stood firm and challenged corporate capitalism and government surveillance. The history of hacking predates the internet. One of the earliest incidents of hacking existed since the telephone era....
happy first birthday to Bluesky, and what a year it's been! with every day, the need for an open n
happy first birthday to Bluesky, and what a year it's been! with every day, the need for an open network that puts people first becomes increasingly clear. we're glad to...
Resegregation, Coups, Orwell, and the Importance of Precise Language
Karen Attiah wrote a short opinion piece about how the nationwide assault on diversity, equity and inclusion led by conservatives is actually aimed at resegregation and how being precise in...
Who Owns AI? Sentient’s Massive NFT Mint Redefines AI Ownership
Sentient has completed a large-scale ownership mint with 650,000 participants. The campaign distributes NFTs tied to Dobby, the first decentralized Loyal AI model. Holders can later claim ownership and unique...
McSweeney’s: Here at DOGE, We’ve Streamlined Every Aspect of America’s Collapse. “I...
McSweeney’s: Here at DOGE, We’ve Streamlined Every Aspect of America’s Collapse. “I am proud to say that in just weeks, we have used the Tesla, SpaceX, and X playbook to...
How To Run DeepSeek R1 Locally on Your (Even Slow) Laptop Completely Free
It took me 7 minutes to set up on my Macbook.Continue reading on The Startup »
Adaptive Attacks Expose SLM Vulnerabilities and Qualitative Insights
This section reports on adaptive attacks against SLMs where attackers, aware of the defense, use a larger step size (α=0.0001) to overcome TDNF. The defense reduces attack success, especially with...
Transfer Attacks Reveal SLM Vulnerabilities and Effective Noise Defenses
This section evaluates transfer attacks on SLMs by applying adversarial perturbations from a surrogate model to victim models. FlanT5-based SLMs show more robustness in grey-box settings, but black-box experiments reveal...
Cross-Prompt Attacks and Data Ablations Impact SLM Robustness
This appendix section covers three experiments: (A.3) Cross-prompt attacks, using 10 random perturbations per target, are less effective than sample-specific ones but still beat random noise; (A.4) Training data ablations...
Safety Alignment and Jailbreak Attacks Challenge Modern LLMs
This section reviews the background on safety alignment for LLMs, highlighting the HHH criteria and red team prompt crafting used to deter harmful outputs. It examines both manual and automated...
Audio Encoder Pre-training and Evaluation Enhance SLM Safety
This appendix details the pre-training and evaluation of our audio encoder for speech language models (SLMs). The encoder is a 24-layer Conformer with 300M parameters pre-trained using the BEST-RQ method...
Integrated Speech Language Models Face Critical Safety Vulnerabilities
This study examines the safety alignment of speech language models in Spoken QA. It shows that adversaries with white-box access can jailbreak these systems using nearly imperceptible perturbations, and that...
SpeechVerse Unites Audio Encoder and LLM for Superior Spoken QA
This section details the experimental setup for SpeechVerse, our unified speech language model. It describes using a 24-layer Conformer audio encoder paired with two LLMs—Flan-T5-XL and Mistral-7B variants—for spoken QA....
Welcome to Postreads
Discover and follow the best content from across the web, all in one place. Create an account to start building your personalized feed today and never miss out on great reads.
Support Postreads
Enjoying the service? Help me keep it running and improve it further by buying me a coffee!
Buy me a coffeeContent Timeline
Trending Now
Top 5 clicked items this week
Freshly added
New feeds to discover
