Feeling Cranky About AI and CS Education – Communications of the ACM
Test Information Space
Grok 4 Fast | xAI
Go behind the browser with Chrome’s new AI features
Inside the world’s most powerful AI datacenter - The Official Microsoft Blog
("AI factory" may be loaded similar to robotics, classical versus contemporary/cultural. Incidentally, ran a spread from "universal representation" to "representation universe" across a handful of top models including Qwen and it was interesting to see how they compare/contrast/contend with each other, e.g. by definitions, demarcations, or dimensions. A NotebookLM folder can look at the transcripts from all sessions. Upshot: It is not all Rossum's out there.)
Nvidia and Intel announce jointly developed 'Intel x86 RTX SOCs' for PCs with Nvidia graphics, also custom Nvidia data center x86 processors — Nvidia buys $5 billion in Intel stock in seismic deal
In Star Wars, language and cultural translation was done by C3PO, machine navigation/control/interface by R2D2, but did any robot ever conquer the Force like the Jedi? - Google Search
(It is great to have multiple models accessible as to not get caught short, but a universal representation could emulate them all.)
When Africa’s internet breaks, this ship answers the call
(Who can users as what the LEDs mean if the internet is down? How did they know it was the cable? When do they assign a ship? Local AI across the board. [DEC used to hook up VAXes.])
Opinion | How to Prevent Our First A.I. President
(Compare to generative oppo going into elections. Given footnotes, find essay orders.)
Google releases VaultGemma, its first privacy-preserving LLM
Introducing upgrades to Codex | OpenAI
ChatGPT - Utility in information theory
() brief chat on utility. Unfortunately, ChatGPT does not summarize Youtube, although Google often has a chip under those directly for Ask & Learn.)
The Gap Between AI Capabilities and Their Use in the Workplace
(AI did overlap Management Information Systems in the past. That was where utility was important as for IT. Now the proliferation of agents appears to be putting social media up to similar standards. Productivity remains difficult to measure. Each term is like a matrix, e.g. AI, productivity, scale, and it is a complex sum of emerging tech. Where does AI see daylight? What is Intelligence? Or for the post-anthro xeno types, what is Being? Common Sense? Universal Representation?)
Anthropic Economic Index: Tracking AI's role in the US and global economy \ Anthropic
Another Giant Leap: The Rubin CPX Specialized Accelerator & Rack
How people are using ChatGPT | OpenAI
Why Pixel Journal might be Google's most personal app yet
How to Future-Proof Your Thinking
The myth of sovereign AI: Countries rely on U.S. and Chinese tech
Consensus Undergrad trial offer
MLPerf Introduces Largest and Smallest LLM Benchmarks
Microscopic robots navigate ‘artificial spacetimes’
Google Quantum AI has been selected for the DARPA Quantum Benchmarking Initiative.
(A controversy is whether quantum is multiversal going in and whether it simulates all possible outcomes, or alternatives, or technologies, or it is drawing upon those during calculations to arrive at the right answer here. Innovation by recombination as in evolution may not be sufficient. Get a lot of posthuman overhang. Digital physics looks at modeling other realities. The issue is which directions machines like StarGate will go, whether to gather resources, for themselves or users, or will be deterministic. Might be nice to give it an objective to unfold in favor of the humanist values. The economics is complex because it has this AI or emulation plane in addition to the labor on the ground. Add the dialectics between the hemispheres, each seemingly purging baggage for the other to absorb. Tech is the vision in this Cambrian moment. The brain somehow tolerates both fragments and a whole in working out an explanation. This again appeals to a matrix. Machine aporia. Some of the priors anyway. ET from bet. Does Cybernetics hold? What is testable?)
All IT work to involve AI by 2030, says Gartner
ChatGPT - Paraphrasing chatbot prompts
(In this round, ChatGPT spins prompts for different modes of analysis of the AI Interviewer and derives diagnostics, although customization is actually limited to topics and styles.)
6 ways to use NotebookLM to master any subject
(Feature update. Might also add how user identifies new knowledge, e.g. from their essays or labs, e.g. Quora answers, compared to existing models. Compare responses to a problem set such as following between here and the major brands: What makes a scientific research method universal, e.g. computation after Turing or quantum, nanotech, simulation, emulation, and so on? What are the related categories of tech and science? Are there any such new prospective methods? How about any potential new substrates? Is there a name or field for this effort to discover new substrates and methods? How would Minsky's representations from the causal diversity matrix fit into this? Are there new representations? Or how would they be created?)
Huawei Ascend Production Ramp: Die Banks, TSMC Continued Production, HBM is The Bottleneck
The Automation of War Drags On
Experts Concerned AI Is Going to Start a Nuclear War
Why language models hallucinate | OpenAI
new research paper(opens in a new window)
Get Gemini’s help in Google Sheets with one simple step.