digitado

About digitado

https://www.digitado.com.br

Posts by :

Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity

⋅

We investigate the integration of human-like working memory constraints into the Transformer architecture and implement several cognitively inspired attention variants, including fixed-width windows based and temporal decay based attention mechanisms. Our modified GPT-2 models are trained from scratch on developmentally plausible datasets (10M and 100M words). Performance is evaluated on grammatical judgment tasks (BLiMP) and alignment with human reading time data. Our results indicate that these cognitively-inspired constraints, particularly fixed-width attention, can significantly improve grammatical accuracy especially when […]

Ver mais

Liked Liked
Google unveils two new TPUs designed for the "agentic era"

Google unveils two new TPUs designed for the “agentic era”

⋅

Most of the companies that have fully committed to building AI models are gobbling up every Nvidia AI accelerator they can get, but Google has taken a different approach. Most of its cloud AI infrastructure is based on its line of custom Tensor processing units (TPUs). After announcing the seventh-gen Ironwood TPU in 2025, the company has moved on to the eighth-gen version, but it’s not just a faster iteration of the same chip. The new TPUs come […]

Ver mais

Liked Liked

Efficient Multi-Cohort Inference for Long-Term Effects and Lifetime Value in A/B Testing with User Learning

⋅

In streaming platforms churn is extremely costly, yet A/B tests are typically evaluated using outcomes observed within a limited experimental horizon. Even when both short- and predicted long-term engagement metrics are considered, they may fail to capture how a treatment affects users’ retention. Consequently, an intervention may appear beneficial in the short term and neutral in the long term while still generating lower total value than the control due to users churn. To address this limitation, we introduce […]

Ver mais

Liked Liked
Tabloid reports linking 10 missing and dead scientists spur FBI probe

Tabloid reports linking 10 missing and dead scientists spur FBI probe

⋅

The US is investigating a possible conspiracy after at least 10 scientists connected to US nuclear secrets and rocket technology went missing or died under shadowy circumstances over the past few years. Pointing to tabloid reports from The Daily Mail and The New York Post, Republican members of the House Committee on Oversight and Government Reform sought information about each missing or departed scientist. In letters to the Department of Energy, Department of Defense, Federal Bureau of Investigation […]

Ver mais

Liked Liked
Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

⋅

Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model Big claims from Qwen about their latest open weight model: Qwen3.6-27B delivers flagship-level agentic coding performance, surpassing the previous-generation open-source flagship Qwen3.5-397B-A17B (397B total / 17B active MoE) across all major coding benchmarks. On Hugging Face Qwen3.5-397B-A17B is 807GB, this new Qwen3.6-27B is 55.6GB. I tried it out with the 16.8GB Unsloth Qwen3.6-27B-GGUF:Q4_K_M quantized version and llama-server using this recipe by benob on Hacker News, after first installing llama-server using […]

Ver mais

Liked Liked

Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems

⋅

Federated continual learning (FCL) allows distributed autonomous fleets to adapt collaboratively to evolving terrain types across extended mission lifecycles. However, current approaches face several key challenges: 1) they use uniform protection strategies that do not account for the varying sensitivities to forgetting on different network layers; 2) they focus primarily on preventing forgetting during training, without addressing the long-term effects of cumulative drift; and 3) they often depend on idealized simulations that fail to capture the real-world heterogeneity […]

Ver mais

Liked Liked
Company-wise memory in Amazon Bedrock with Amazon Neptune and Mem0

Company-wise memory in Amazon Bedrock with Amazon Neptune and Mem0

⋅

This post is cowritten by Shawn Tsai from TrendMicro. Delivering relevant, context-aware responses is important for customer satisfaction. For enterprise-grade AI chatbots, understanding not only the current query but also the organizational context behind it is key. Company-wise memory in Amazon Bedrock, powered by Amazon Neptune and Mem0, provides AI agents with persistent, company-specific context—enabling them to learn, adapt, and respond intelligently across multiple interactions. TrendMicro, one of the largest antivirus software companies in the world, developed the […]

Ver mais

Liked Liked
Reversing enterprise security costs with AI vulnerability discovery

Reversing enterprise security costs with AI vulnerability discovery

⋅

Automated AI vulnerability discovery is reversing the enterprise security costs that traditionally favour attackers. Bringing exploits to zero was once viewed as an unrealistic goal. The prevailing operational doctrine aimed to make attacks so expensive that only adversaries with functionally unlimited budgets could afford them, thereby disincentivising casual use. However, the recent evaluation by the Mozilla Firefox engineering team – using Anthropic’s Claude Mythos Preview – challenges this accepted status quo. During their initial evaluation with Claude Mythos […]

Ver mais

Liked Liked
Physicists think they've solved the muon mystery

Physicists think they’ve solved the muon mystery

⋅

Physicists have spent the last 20 years pondering an apparent discrepancy between experimental results and theoretical predictions for the magnetic properties of the muon, the electron’s heavier cousin—a mismatch that hinted at a possible fifth force. But according to a new paper published in the journal Nature, the discrepancy is due to a calculation fluke, not exciting new physics, so the Standard Model of particle physics is still holding strong. “There were many calculations in the last 60 […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2026