Hi all, I build this agent for beginners to use it locally in this laptop Comments URL: https://news.ycombinator.com/item?id=48889045 Points: 1 # Comments: 0
Article URL: https://manazir.dev/work/the-harness-is-not-the-model Comments URL: https://news.ycombinator.com/item?id=48889024 Points: 1 # Comments: 0
64-bit UEFI OS. Ring 0 only. No ring 3. Cooperative multitasking (tasks yield manually). No context switching — all tasks share one 128MB stack. IDT 0-31 only. VA=PA. PCI, XHCI, RDTSC, HDA, ATA, FAT32, GPT, REP(string instructions), AVX256, SSE4.2, FPU, NT(Non-Temporal). All polling. (I used LLM in some of my code.) Github Link: https://github.com/Dydudu37d/NeuroSamaOS I'm the author. Happy to answer any questions! Comments URL: https://news.ycombinator.com/item?id=48889020 Points: 1 # Comments:
Article URL: https://github.com/jrm-code-project/llambda Comments URL: https://news.ycombinator.com/item?id=48888922 Points: 2 # Comments: 0
<p> The AI-native Operating System for founders. </p> <p> <a href="https://www.producthunt.com/products/nautis?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1194885?app_id=339">Link</a> </p>
AI Gateway Production Index — July 2026 Every month, AI Gateway routes tens of trillions of tokens between production applications and AI labs, giving us a view of what AI usage actually looks like in today’s enterprise. We publish that view here. See the Production Index reports published in May and June . July 2026 summary The July index reports on AI Gateway data collected in June 2026. AI Gateway token volume grew 29% month over month and spend grew 27% . The price per token was flat after r
Article URL: https://blog.zoller.lu/2026/07/dunning-kruger-after-ai-gap-that-no.html Comments URL: https://news.ycombinator.com/item?id=48888772 Points: 1 # Comments: 0
Article URL: https://calcrecipe.com/en/workshop/7 Comments URL: https://news.ycombinator.com/item?id=48888605 Points: 2 # Comments: 0
Article URL: https://agenttransfer.dev/#apps Comments URL: https://news.ycombinator.com/item?id=48888584 Points: 1 # Comments: 1
Article URL: https://thetruthasiseeitnow.com/using-ai-slop-as-feedback-tells-as-much-about-the-commenter-as-the-creator/ Comments URL: https://news.ycombinator.com/item?id=48888501 Points: 2 # Comments: 0
My manager the other day mentioned AI reminds him of when search engines like google were first popularized, whereas before you needed a lot of specialized knowledge that was hard to acquire, whereas after knowing obscure details became less important and knowing what to search for became more important. I’m curious for anyone who remembers - what was the reaction / discourse around search engines at the time? Was there a similar reaction to the rise of LLMs? Comments URL: https://news.ycombinat
Article URL: https://www.reuters.com/science/spacexs-near-term-ai-payoff-seen-tethered-earth-not-outer-space-2026-07-10/ Comments URL: https://news.ycombinator.com/item?id=48888384 Points: 1 # Comments: 0
"This highlights its potential as a disease-modifying therapy." ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.
Article URL: https://github.com/insightitsGit/ChorusGraph/ Comments URL: https://news.ycombinator.com/item?id=48888185 Points: 2 # Comments: 0
<!-- SC_OFF --><div class="md"><p>"<a href="https://arxiv.org/abs/2510.01171">Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity</a>"</p> <p>This paper was accepted to ICML this year. Its main idea is a very simple prompt-engineering trick: "changing the prompt this way led to more diverse sampling". Naturally, it is difficult to provide a rigorous theoretical analysis for something like this.</p> <p>Even if it works, I’m not sure this kind of prompt engineering belongs
Article URL: https://www.techradar.com/pro/quality-decays-exponentially-following-ai-arrival-research-shows-experts-and-contributors-leaving-online-communities-amidst-silent-knowledge-reset Comments URL: https://news.ycombinator.com/item?id=48888107 Points: 1 # Comments: 0
I've seen mixed sentiments out there. What has been your experience from the customer-side? Comments URL: https://news.ycombinator.com/item?id=48887895 Points: 2 # Comments: 1
<p>Josh Fawaz’s song, a cover of Like a Prayer, has raised questions over how generative AI is being used in music and whether it should be declared</p><p>An Australian producer has gone from a little-known artist to a viral sensation in a matter of months, with his hit song catapulting onto global charts and receiving thousands of radio spins.</p><p>There’s just one problem: music experts and other musicians are questioning whether he produced it. They claim Josh Fawaz’s most popular song, a co
<p>I believe that chatbots have no place in a decent society, and am repelled by the topic of AI in general. But could I be seduced?</p><p>By Lauren Oyler. Read by Kate Handford</p><p><strong><a href="https://www.theguardian.com/news/2026/jun/23/navigating-the-unknown-together-me-and-my-idiot-ai-boyfriend">Read the text version here</a></strong></p><p><strong>Support the Guardian today: <a href="https://theguardian.com/longreadpod">theguardian.com/longreadpod</a></strong></p><p>A version of this
arXiv:2607.08773v1 Announce Type: new Abstract: In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness. In particular, we show that the adversarial robustness problem can be reduced to a lattice traversal problem. Each element of this lattice corresponds to an interval, i.e., an axis-aligned hyper-rectangle, containing an input point $\mathbf{x}$. Consider a multilayered perceptron classifier (MLP). An interval $I$ constitut
arXiv:2607.08774v1 Announce Type: new Abstract: Reliability in large language model (LLM) systems is typically framed as a function of model capability. We challenge this by demonstrating that reliability is significantly influenced by \emph{inference-time control} -- the computational layer governing task framing and context selection. We introduce \emph{CogniConsole}, an architectural instantiation that externalizes this control into a structured interface combining programmatic coordination w
arXiv:2607.08894v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during infere
arXiv:2607.08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal benchmark of 46 long-hor
arXiv:2607.08986v1 Announce Type: new Abstract: We formalize a research result in the Lean 4 proof assistant by having a mathematician direct an AI system, and frame the activity as a formalization game. The objective is to turn a LaTeX document into Lean. The game is won when the development compiles, contains no sorry, and a machine check shows the target theorems rest on Lean's foundational axioms alone. Reuse is a second check, by a definition we introduce: whether the development yields a s
arXiv:2607.09059v1 Announce Type: new Abstract: We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on demonstrations,
arXiv:2607.09076v1 Announce Type: new Abstract: Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, exposing the limitations of traditional rule-based monitoring in industrial IoT environments. While Large Language Models (LLMs) have strong semantic reasoning abilities to assist in decision support, their hallucinatory nature presents unacceptable safety liabilities for closed-loop control. This paper introduces a neuro-agentic control framework,
arXiv:2607.09099v1 Announce Type: new Abstract: While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly structured, knowledge-heavy legal domains remains under-explored. In this work, we introduce the Legal Multi-Agent Debate (L-MAD) framework to systematically evaluate different debate structures and aggregation methods within Legal Textual Entailment. By assigning distinct expert personas to multiple agents, L-MAD improves
arXiv:2607.09142v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice. Many rely on synthetic conversations or patient simulators, omit patient-uploaded medical images, or evaluate open-ended clinical responses using multiple-choice or lexical-overlap metrics that poorly reflect clinical quality. We introduce \textbf{MedRealMM}, a large-scale benchmark for mu
arXiv:2607.09153v1 Announce Type: new Abstract: Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scratch. In long multi-agent rollouts, the scoring cost, growing quadratically with respect to sequence length L, creates a severe computational bottleneck, severely limiting P
arXiv:2607.09175v1 Announce Type: new Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this work, the mutable component of that context is a persistent system-level instruction that is updated from operational experience while the model, tools, and harness remain fixed. Over long evolution horizons, flat-text maintenance makes verification increasingly difficult as accumulated instructions grow and interact.
arXiv:2607.09195v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with broad knowledge, flexible reasoning, and tool use, they have the potential to autonomously explore and solve scientific problems by repeatedly proposing hypotheses, testing them, and revising their beliefs in the light of the evidence. In current agents, however, these hypotheses, tests, and belief updates are buried i
arXiv:2607.09217v1 Announce Type: new Abstract: In this system paper, we present OpenProver, an open-source system for LLM-driven automated theorem proving (ATP) with integrated Lean 4 formal verification. OpenProver integrates a Planner-Worker-Verifier architecture inspired by recent ATP agentic systems such as Aletheia. A Planner agent maintains a compact Whiteboard scratchpad and an unbounded Repository of intermediate findings, and decomposes mathematical work into parallel Workers. OpenProv
arXiv:2607.09322v1 Announce Type: new Abstract: In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluations of LLM-based medical agents have largely emphasized short-context knowledge QA and tool use. However, real-world medical care is inherently longitudinal, and clinicians must aggregate evidence across repeated visits, tests, and evolving treatments. Therefore, long-horizon interaction is essential for realistic asses
arXiv:2607.09330v1 Announce Type: new Abstract: Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in physical artificial intelligence such as smart factories, warehouses, and service robotics. To enable collaboration among such an agent team, efficient coordination mechanisms that operate reliably under limited network resources are required. However, existing heterogeneous LLM-agent coordination frameworks that rely on multi-round natural-langu
arXiv:2607.09403v1 Announce Type: new Abstract: Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality assurance. Th
arXiv:2607.09449v1 Announce Type: new Abstract: Bayesian causal discovery is widely used for its ability to quantify epistemic uncertainty over directed acyclic graphs (DAGs) through posterior inference. However, its behaviour under latent confounding remains poorly understood, as existing work typically notes that confounding breaks identifiability without characterising how the posterior distribution over DAGs responds. In this work, we analyse posterior behaviour under latent confounding in l
arXiv:2607.09474v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in solving open problems in mathematics. However, their performance can be further improved through agentic workflows tailored to real-world mathematical practice. To this end, we introduce ProofCouncil, a mathematical agent that is designed to tackle open problems using an author-critic architecture. ProofCouncil served as a submission to the second batch of FirstProof, a challenge consist
arXiv:2607.09489v1 Announce Type: new Abstract: An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation. We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations. To do so, we distinguish what is justified by accepted domain knowledge, what reference sources say, and what the system can currently use. This allows us to give precise definitions to common failures: extrapolatio
arXiv:2607.09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amplified when visual evidence is evaluated by text-only or weakly grounded rewards. We study reward hacking in MLLM RL across safety VQA, chart VQA, and stress-test settings, varying reward design, data ambiguity, model scale (2B-32B), and RL algorithm (GRPO, RLOO, DAPO). W
arXiv:2607.08808v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled high-quality, render-ready scene representations for novel-view synthesis. However, most existing 3DGS pipelines rely on multi-view observations (or non-causal access to future frames) to achieve sufficient coverage, which is often unavailable in on-device robotics and AR settings where sensing is restricted to a single stereo rig. Recovering a high-quality 3DGS scene from one stereo obse
