AI
-
“AI 2027” is a captivating read that offers a speculative month-by-month timeline of anticipated AI advancements and their potential global impacts. Despite its speculative nature, the book is grounded in substantial research and analysis of past events and likely future developments up to 2027. Its writing style, akin to a science fiction novel, feels realistic.…
-
The topic of MCP has been gaining traction recently. Essentially, it’s a protocol enabling AI models to discover and interact with external tools and data. OpenAI refers to it as the “USB port” for AI and has announced support for it, despite being developed by its competitor, Anthropic. Anthropic also offered insights into the inner…
-
LLM scraping poses a growing problem for websites that do not effectively restrict content access. Alarmingly, some scrapers ignore robots.txt files, which specify nonscrapeable areas, resulting in server overloads, delays, and outages for genuine users. As AI models grow larger and more data-hungry, respecting content providers’ rights becomes increasingly vital (FOSS Projects Struggle with AI…
-
Recently, major AI companies have introduced new small models: Microsoft’s Phi-4-mini and Phi-4-multimodal, Alibaba’s QwQ-32B, and Google’s Gemma 3. Benchmark tests show these smaller models offer performance nearly equivalent to their larger counterparts, such as o1-mini, and are multi-modal. With portable devices becoming more AI-capable, it’s likely we will see more localized AI applications soon,…
-
Last week, OpenAI, Meta, and xAI all released new models. However, OpenAI’s newest GPT-4.5 model has been met with mixed reviews due to its high cost and user feedback. Meanwhile, Barto and Sutton received the Turing Award for their pioneering work in reinforcement learning, which has significantly impacted the field of AI. In the realm…
-
In my view, the standout article in this issue is by top hacker Joseph Thacker, who provides a thorough guide on hacking AI applications. The guide covers essential topics such as understanding AI models, mastering system prompts, and exploring attack scenarios. While the content about Language Model Mechanics (LLM) is at a high level, the…
-
The standout news in AI and technology last week was Microsoft’s Majorana 1 chip. Microsoft says that this chip leverages a new state of matter called topological superconductivity, potentially enabling the creation of qubits that are more stable and less susceptible to errors than those in current quantum computers, addressing a critical challenge in the…
-
On February 2, 2025, the AI Act’s provisions regarding prohibited AI practices took effect. As my colleague Dereck Banks notes, one particularly interesting aspect is the ban on emotion recognition in workplaces and educational institutions. Many companies have already implemented such systems to monitor employees’ emotions, particularly in customer service. The rule aims to prevent…
-
Cisco researchers recently evaluated the DeepSeek R1 model using the HarmBench dataset and reported a 100% attack success rate. Looks like DeepSeek R1 has serious security issues, doesn’t it? However, Meta’s LLama 3.1 model also performed poorly, with a 96% success rate in the same test, while OpenAI’s closed-source model o1 had a 25% success…
-
OpenAI introduced a new tool called Deep Research last week, claiming it can generate scientific articles at a level comparable to a PhD student. This tool excites me with its potential to benefit researchers worldwide and enhance scientific progress for the good of humanity. However, as Gary Marcus has discussed (in the Opinions & Analysis…
