Autonomous Agents

Opening — Why this matters now Enterprises are suddenly discovering that “deep research agents” are not magical interns but probabilistic engines with wildly variable costs. Every additional query to an LLM carries a token bill; every recursive branch in a research workflow multiplies it. As agentic systems spread from labs to boardrooms, a simple question emerges: Can we control what these agents do—rather than hope they behave? ...

Agents Without Prompts: When LLMs Finally Learn to Check Their Own Homework Opening — Why this matters now Reproducing machine learning research has become the academic equivalent of assembling IKEA furniture without the manual: possible, but unnecessarily traumatic. With papers ballooning in complexity and code availability hovering around a charitable 20%, the industry is grasping for automation. If LLMs can write papers, reason over them, and generate code — surely they can also reproduce experiments without melting down. ...

Opening — Why this matters now Explainability in AI has become an uncomfortable paradox. The more powerful our models become, the less we understand them—and the higher the stakes when they fail. Regulators demand clarity; users expect trust; enterprises want control. Yet most explanations today still amount to colourful heatmaps, vague saliency maps, or hand‑waving feature attributions. ...

Opening — Why this matters now Critical minerals have become the uncomfortable bottleneck of the energy transition. Governments want copper, nickel, and cobalt yesterday; investors want clean balance sheets; and society wants green electrons without digging more holes. Meanwhile, exploration economics remain bleak: more spending, fewer discoveries, and an industry still pretending the 1970s never ended. The uploaded paper by Caers (2024) argues the quiet part out loud: if exploration keeps relying on deterministic models and guru-style intuition, the false-positive drill holes will keep piling up. ...

Flame Tamed: Can LLMs Put Out the Internet’s Worst Fires? Opening — Why this matters now The internet has always been a bonfire waiting for a spark. A single snarky comment, a misread tone, a mild disagreement—suddenly you have a 42‑reply thread full of uppercase righteousness and weaponized sarcasm. Platforms have responded with the usual tools: flagging, downranking, deleting. Moderation keeps the house from burning down, but it doesn’t teach anyone to stop flicking lit matches indoors. ...

Opening — Why This Matters Now The industry’s guilty secret is that long-context models behave beautifully in demos and then slowly unravel in real usage. The longer the conversation or chain-of-thought, the less the model remembers who it’s supposed to be—and the more creative it becomes in finding trouble. This isn’t a UX quirk. It’s a structural problem. And as enterprises start deploying LLMs into safety‑critical systems, long-context drift is no longer amusing; it’s a compliance nightmare. ...

Opening — Why this matters now Radiology sits at the awkward crossroads of two modern pressures: rising imaging volumes and shrinking clinical bandwidth. CT scans get bigger; radiology teams do not. And while foundation models now breeze through captioning tasks, real clinical reporting demands something far more unforgiving — structure, precision, and accountability. The paper Radiologist Copilot (Yu et al., 2025) introduces an alternative future: not a single model that “generates a report,” but an agentic workflow layer that behaves less like autocomplete and more like a junior radiologist who actually follows procedure. ...

Opening — Why This Matters Now Large language models now behave like overeager junior analysts: they think harder, write longer, and try very hard to sound more certain than they should. Iterative reasoning techniques—Chain-of-Thought, Debate, and the new wave of inference-time scaling—promise deeper logic and better truth-seeking. Yet the empirical reality is more awkward: the more these models “reason,” the more they entrench their initial assumptions. The result is polished but stubborn outputs that deviate from Bayesian rationality. ...

Opening — Why this matters now Human behavior is the final frontier of prediction. Chess—arguably the world’s most intensely instrumented strategy game—used to be about best moves. Today, it’s increasingly about human moves. As analytical tools migrate into coaching apps, anti-cheating systems, and personalized training platforms, understanding how different players actually behave (not how they ideally should) becomes commercially relevant. ...

Opening — Why this matters now Every few months, the AI industry proclaims another breakthrough in “reasoning.” Models solve Olympiad geometry, pass graduate-level coding contests, and produce clean explanations that sound almost insultingly confident. The narrative writes itself: AGI is practically here; please adjust your expectations accordingly. Then you hand the same models a chessboard—and they implode. ...