Search: “engineering”

Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepS

arXiv:2609.21493v1 Announce Type: new Abstract: Multimodal large language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whet

The Information: Sources: OpenAI is developing features to counter SpaceX's Grok Bot “teammates”, and has discussed creating a personal AI assistant to compete with Meta's Muse — OpenAI pioneered AI t

I shipped something I've been building for the last few weeks : phantom-kv , a refusal-removal system for large language models that doesn't touch a single weight. Instead of editing the model, it loa

I forked llama.cpp to implement Declarative Attention (arXiv:2609.02737, Google DeepMind and KAIST AI). The model declares in its own output which context chunks it needs <focus magic_chunks='N'>), an

Impressive paper showing the impact of a good harness. Improves Qwen3-8B from 41.2% to 91.8% on long-horizon robot tasks without any change to the model. The gain comes from the harness. GAVEL keeps a

Sharing my successful experience here. My setup: RTX 5060 Ti 16GB (x16 PCIe slot) RTX 3060 12GB (x4 PCIe slot) RAM: 32GB CPU: Ryzen 5 5600 OS: Linux So I have a total of 28GB. Average tk/s: 50, and th

Note: This writeup was put together with the help of AI. So I've got dual AMD MI50 32GB cards. If you know these cards, you know the story - AMD dropped official ROCm support for gfx906 after ROCm 5.7

I have always posted about budget builds on here, and often asked how we are going to run the next big models. Often Plenty of downvotes too or folks telling me that it's not running if I'm getting 5t

Vector search is a critical component of generative AI, retrieval-augmented generation (RAG), and data agent architectures, but sometimes vector search alone isn't enough. While vector embeddings are

Grok Bot summary of SpaceX CFO Bret Johnsen’s new interview with Tony Kim at SpaceX Mission Control. Bret’s path - Came from semiconductors (Qualcomm, Broadcom; was CFO of MindSpeed) - Barely knew Spa

As enterprises invest in generative AI, tech leaders keep seeing the same pattern: Developers test AI tools for a week, hit setup problems, and then drift back to the backlog. Nothing ships. The real

arXiv:2609.19588v1 Announce Type: new Abstract: Mechanical intelligence, loosely defined as the reduction in control burden afforded by a robot's physical form, has become a prominent concept in robot

arXiv:2609.19615v1 Announce Type: cross Abstract: Modern applications generate massive volumes of raw telemetry data, but translating those noisy, heterogeneous event streams into actionable business

arXiv:2601.07315v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning. However, they can have spatial blindness and log

A database knows where your data is. A vector database understands what your data means. It finds information based on similarity and meaning, not just exact keywords, powering semantic search, RAG, r

arXiv:2609.18298v1 Announce Type: cross Abstract: Agentic-AI based software development offers the promise of faster completion of the software, greater programmer efficiency, and more reliable code.

arXiv:2609.18520v1 Announce Type: new Abstract: Collective intelligence is a collaborative autonomy paradigm in which multiple agents pursue shared objectives through local perception, information exc

arXiv:2509.21891v3 Announce Type: replace-cross Abstract: Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been t

arXiv:2609.18849v1 Announce Type: cross Abstract: An agentic request spends substantial wall-clock time waiting for tools, and its KV cache holds GPU memory the whole time. Serving systems decide whet

arXiv:2609.18278v1 Announce Type: new Abstract: Artificial Intelligence (AI) is currently only applied to non-safety critical applications due to the strict standards and regulations for railway indus

arXiv:2609.17590v1 Announce Type: cross Abstract: Evolutionary Ensemble Search (EES) constructs machine-learning procedures through expert-guided program evolution. A role-specialized council turns ta

Romeo Lupascu has criticized the prevailing AI agency framework, which relies on repeatedly looping an LLM core with identical context. He calls this strategy “deeply flawed” and argues that it should

At Google, we see firsthand how the speed, scale, and sophistication of cyber threats continue to challenge traditional enterprise defenses. Today’s defenders can’t rely on reactive triage or fragment

arXiv:2609.18434v1 Announce Type: new Abstract: Teaching robotics relies on screen-based simulation, showing robot motion in an abstract coordinate frame rather than at real scale in the learner's own

arXiv:2609.17633v1 Announce Type: new Abstract: The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of the fastest heuristics for it despite producing colorings that typically use mor

🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-w

Today’s LLMs still write like typewriters: one token at a time. This sequential process creates a hard inference bottleneck. We're introducing Uno, a diffusion-augmented LLM that delivers autoregressi

Two weeks. That's how long it took to go from GLM-5.3-Flash's first run on domestic accelerators to serving all of its production traffic, with 3.2× end-to-end throughput along the way. What I keep th

arXiv:2609.17527v1 Announce Type: cross Abstract: An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectiv

arXiv:2609.16679v1 Announce Type: new Abstract: Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems mod

Manufacturing artificial intelligence startup CADDi Co. Ltd. today announced it has raised 114 million in new funding at a valuation of 1.2 billion, partly to expand in North America. CADDi builds sof

arXiv:2609.16096v1 Announce Type: cross Abstract: Large language model coding agents have recently become useful for software tasks, but weaker or open-weight agents still struggle to reliably interpr

arXiv:2609.15997v1 Announce Type: new Abstract: Improving safety at intersections requires identifying crash mechanisms and recommending appropriate countermeasures. However, this process traditionall

Artificial intelligence agents have become table stakes in enterprise software, but in financial reporting, audit and compliance, speed counts for little if the output cannot be defended. That gap bet

arXiv:2609.16739v1 Announce Type: new Abstract: Background: Large language models (LLMs) have achieved physician-comparable performance on multiple-choice medical knowledge examinations, but their cap

MLPerf Inference v6.1 introduced the first agentic workload run on datacenter hardware and evaluated a model with more than one trillion parameters (Kimi K2), setting a new benchmark for scale. The te

My name is Chris Painter, and I'm the President of METR (Model Evaluation and Threat Research). I know we've made a lot of new friends on the internet the last couple of days, so I thought I'd take th

It's late at night in the lab, I've been working on a basic script for a virology project, and holy hell the safeguards have been pissing me off. Mirroring detectEVE data over rsync to my laptop by ma

arXiv:2609.16461v1 Announce Type: cross Abstract: Agentic large language model (LLM) systems rely on long interaction histories to preserve instructions, tool states, intermediate decisions, and unres

arXiv:2607.09709v2 Announce Type: replace Abstract: Post-training a code generator against a learned judge can optimize proxy features that raise the score without improving the artifact. We study the

arXiv:2609.14858v1 Announce Type: new Abstract: Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across com

arXiv:2609.15015v1 Announce Type: new Abstract: Synthetic perturbations appear to offer inexpensive calibration data for LLM evaluators in biomedical ML, where expert review is scarce. Yet a planted m

arXiv:2609.13879v1 Announce Type: new Abstract: An acquired representation can enlarge a system's cognitive repertoire without transferring the capacities exercised in producing that representation. T

arXiv:2511.19046v2 Announce Type: replace-cross Abstract: Medical image segmentation is fundamental for biomedical discovery. Existing methods lack generalizability and demand extensive, time-consumin

arXiv:2609.14857v1 Announce Type: new Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution