I like how imec reframed their logic device scaling roadmap around the track layout for front/backside power and now includes the embedded memory interposer. Its complicated to visualize it all.

Upgraded to iOS 27 to test Apple's new Reframe feature. It turns a flat image into a 3D scene - you can position the camera to "reshoot" the photo. It's not perfect, but you can get some good results 👇

The hardest memory failure may be an agent that remembers enough to act but not enough to explain or undo the action. This survey reframes always-on agents as persistent-state systems. Their durable state includes facts and preferences, but also permissions, credentials, task ledgers, triggers, provenance, and external commitments. The key question is whether that state remains authorized, scoped, traceable, mutable, recoverable, and safe to act on. Across a scoped corpus of 435 works, retrieval appears in 269 and writing in 200, while only 27 expose any rollback mechanism; authority appears in 72. The field has built the forward arc of writing, organizing, retrieving, and acting far more thoroughly than the return arc of forgetting, auditing, and recovery. – arxiv. org/abs/2606.30306 Title: "Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents"

.@louisamira almost worked at @tryramp twice. During one of those interviews, CEO @eglyman reframed how he thinks about corporate spend entirely. "I was like, I'm a huge credit card points guy. And he's like, no no no, you don't get it. We're trying to make it to where you don't spend money. Not give you the 3%, just don't spend the dollar." "I don't think people realize how much more of that there is out there to be done. They all waste money. Why? That's inexcusable at this point." "It's better for your business to save the dollar than to give you the 3% on the rewards."

Multi-agent collaboration that exchanges text every round is expensive 🔄 The fresh idea: scale the collaboration itself through latent-space recursion. Title: Recursive Multi-Agent Systems URL: 🔄 Overview RecursiveMAS reframes multi-agent collaboration as recursive computation in a unified latent space, rather than sequential text exchange. It connects heterogeneous agents through a RecursiveLink module, enabling latent thought generation and cross-agent state transfer. ❓ Challenges Solved Multi-agent systems (MAS) typically rely on text-based communication. ・Agents conversing in natural language consume huge token counts and cost a lot of compute ・The driving question: can agent collaboration itself be scaled through recursion? 💡 Methodology & Proposed Approach ・It frames the whole system as recursive latent-space computation ・The RecursiveLink module lightly connects heterogeneous agents with gradient-based credit assignment across recursion rounds ・Optimization uses inner-outer loop learning while maintaining theoretical stability 📊 Experimental Results Across 9 benchmarks spanning math, science, medicine, search, and code generation, with 4 collaboration patterns tested. ・Average accuracy improved by 8.3% ・Inference sped up 1.2x-2.4x ・Token usage reduced by 34.6%-75.6% It raises accuracy while substantially improving speed and cost at the same time. #MultiAgent# #LLM#

New Google paper: A forecast needs context, not just history. Some patterns are caused by events, not time. Nexus reframes forecasting as a reasoning problem, where events and numbers have to explain each other. Nexus argues that forecasting improves when models read the world around the numbers, not just the numbers themselves. In the Zillow tests, one Claude-based version cut average MAPE by 86.6% versus direct chain-of-thought prompting. That matters because most time series models are fluent in pattern, but mute about cause. A housing inventory curve can reflect seasonality, mortgage pressure, migration, layoffs, and local supply, while a stock price can be bent by earnings, regulation, hype, and fear. Nexus separates those jobs instead of asking one prompt to do everything. One agent turns messy historical text into a clean event timeline, one reads the broad regime, another tracks local shocks, and a synthesizer reconciles them with calibration from past errors. The interesting result is not merely that context helps, but that structure helps the language model use context without losing the time series. The evidence is still narrow: Zillow counts, seven equities, post-cutoff data, and single-run evaluations, so this is not a universal law of forecasting. But the direction is clear: future forecasters will not only extrapolate curves; they will argue about what made the curve move. ---- Paper Link – arxiv. org/abs/2605.14389 Paper Title: "Nexus : An Agentic Framework for Time Series Forecasting"

Your wallet checked the transaction. The UI said it was safe. The funds still moved. @rimeissner of @safe breaks down why security can't live in the UI layer and what Safenet does to enforce it at the execution level at @EthCC 20 minutes that reframe what self-custody actually means.

Zohran Mamdani Pushes Socialism as Democrat Future — (Video: AI) In today’s ABC “This Week” interview, New York City Mayor Zohran Mamdani laid out a clear radical vision for the Democratic Party. He calls for socialism to be its future, insisting his candidates offer a vision that “extends beyond the midterms, that extends beyond 2028.” When asked about making room in the party for mainstream and extreme views (including calls to abolish prisons and open borders), Mamdani defended the “big tent” — saying what makes the party “beautiful” is that it’s inclusive. Pressed on a candidate who called for abolishing prisons and open borders, he reframed it as a “politics of life.” When ABC noted most Americans won’t support abolishing prisons, Mamdani replied: “We can have disagreements on policy positions” and simply noted “There are prisons.” This AI video represents all of these views from today’s interview combined. This is the direction some Democrats are openly embracing: socialism, defunding the justice system, open borders, and a “big tent” big enough for the most extreme ideas. Do you think this is the future Democrats want voters to see?