Knowledge catalogue
AI has a secondary intent problem. I was negotiating a rent renewal (I live in NYC and they raised rent 10% because I guess they were bored). The property manager said she would 'do everything she cou
arXiv:2605.09292v1 Announce Type: new Abstract: Large language models now achieve high final-answer accuracy on mathematical reasoning benchmarks, but accuracy alone does not capture reasoning flexibi
As AI coding agents become deeply embedded in developer workflows, defenders must evolve their definition of malicious files and rethink how to protect against them. Autonomous AI agents operate acros
arXiv:2605.09611v1 Announce Type: new Abstract: This preprint presents an empirical analysis of byte-exact chunk-level deduplication in Retrieval-Augmented Generation (RAG) pipelines. We measure conte
arXiv:2605.09168v1 Announce Type: new Abstract: A valid tool call is not necessarily a valid intervention. Tool-using language agents are guarded by schema validators, policy filters, provenance check
arXiv:2605.10005v1 Announce Type: cross Abstract: In this paper, we describe early work on a specification inference tool for the Move Prover that combines a weakest-precondition (WP) analysis over Mo
arXiv:2605.09760v1 Announce Type: new Abstract: A reliable resume-job matching system helps a company find suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a l
arXiv:2605.08112v1 Announce Type: cross Abstract: AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product dec
arXiv:2605.10597v1 Announce Type: cross Abstract: Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-fl
arXiv:2605.08614v1 Announce Type: new Abstract: Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perfor
arXiv:2605.08671v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed not only to make decisions but to explain them. While AI decision fairness has been studied ext
arXiv:2605.10141v1 Announce Type: new Abstract: Recent neural theorem provers use reinforcement learning with verifiable rewards (RLVR), where proof assistants provide binary correctness signals. Whil
arXiv:2508.20325v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted si
I put my flight preferences in my Cowork instructions, then let Opus get to work. It opened my browser, navigated a bunch of websites, and booked everything for me. The result: Cowork booked 8 flights
arXiv:2605.10039v1 Announce Type: cross Abstract: Frontier coding agents read configuration files (CLAUDE.md, AGENTS.md, Cursor Rules) at session start and are expected to follow the conventions insid
arXiv:2605.10779v1 Announce Type: cross Abstract: The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content s
arXiv:2605.08212v1 Announce Type: cross Abstract: There is an increasing number of algorithmic computations in theoretical physics. These, while conceptually simple, can nevertheless be time-consuming
arXiv:2605.08437v1 Announce Type: cross Abstract: Existing benchmarks for legal AI focus primarily on tasks where LLMs must produce legal arguments or documents, yet the capacity to judge such argumen
arXiv:2605.08941v1 Announce Type: new Abstract: The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin
arXiv:2605.09708v1 Announce Type: cross Abstract: We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes (stencils, all-pairs in
OpenAI contacted me to say “Study Mode is still live and accessible via /study and /learn shortcuts” so that’s good, although the official study mode page doesn’t mention that. (I don’t think slash co
arXiv:2510.09887v2 Announce Type: replace Abstract: Vision and language models frequently ignore semantically critical input edits, defaulting to pretraining priors. For example, models will confident
arXiv:2410.14702v2 Announce Type: replace Abstract: Multi-modal Large Language Models (MLLMs) exhibit impressive problem-solving abilities in various domains, but their visual comprehension and abstra
arXiv:2605.06524v2 Announce Type: replace Abstract: Reliable human-machine discrimination is becoming increasingly important as large language models and autonomous agents are deployed in online setti
arXiv:2512.24601v3 Announce Type: replace Abstract: We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive
arXiv:2605.09063v1 Announce Type: new Abstract: Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challengi
Voice artificial intelligence startup Vapi Inc. said today it has raised 50 million in new funding to change the way people talk to computers, experience phone calls and interact with customer support
arXiv:2601.20164v2 Announce Type: replace-cross Abstract: Prior work suggests that language models, while trained on next token prediction, show implicit planning behavior: they may select the next to
arXiv:2605.09860v1 Announce Type: new Abstract: Long-horizon reasoning requires deciding not only what actions to take, but how deeply to commit before the next observation. We formalize this as commi
arXiv:2605.06832v1 Announce Type: cross Abstract: Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assis
arXiv:2605.07147v1 Announce Type: cross Abstract: The ecosystem of Lean and Mathlib has become the de facto standard for large language model (LLM) assisted formal reasoning with remarkable successes
arXiv:2605.07919v1 Announce Type: new Abstract: Medical vision--language models (VLMs) are usually evaluated on intact image--question pairs, but trustworthy clinical use requires a stronger property:
arXiv:2603.24946v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on
arXiv:2605.06940v1 Announce Type: new Abstract: Annotation automation via Large Language Models (LLMs) is the core approach for scaling NLP datasets; however, LLM behavior with respect to closed-set i
arXiv:2605.07051v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown good performance on various science educational benchmarks, demonstrating their potential for use in science and
arXiv:2605.07647v1 Announce Type: cross Abstract: Automated short answer scoring (ASAS) is shifting from discriminative, fine-tuned models to large language models (LLMs) used in few-shot settings. Th
arXiv:2605.07823v1 Announce Type: new Abstract: Online group chats are social spaces with implicit behavior patterns that, when broken, are often met with social sanctioning from the group. The abilit
arXiv:2605.07001v1 Announce Type: cross Abstract: Architectural code smells erode software maintainability and are costly to repair manually, yet unlike localized bugs, they require cross-module reaso
arXiv:2605.07127v1 Announce Type: cross Abstract: Modern large language models (LLMs) can find a needle in a haystack (locating a single relevant fact buried among hundreds of thousands of irrelevant
Jarred tried rewriting Bun in Rust and it passes 99.8% of the existing test suite we're not being ambitious enough there will be a blog post about this. on what this means for bun, benchmarks, memory
PLEASE DO NOT PANIC about the Mythos/METR graph that everyone is panicking about. Progress is being made but people are totally overreacting. Here’s some context that is being left out from nearly eve
So many people misremember (or never read) what I said in in 2022 in “Deep learning is hitting a wall”, which was neither about revenue or AI’s potential upper limits. Rather, it was an argument that
I keep coming back to this tweet. The phrase “the list” is doing the heavy lifting. The post deserves the weight. It is a load bearing post. You should add the phrase “doing real work” to the list of
When I started to work on the alignment problem more than 10 years ago, we had no idea how AGI was going to be built or how to make it safe. The field had maybe a dozen people who were working on it a
arXiv:2605.04083v1 Announce Type: new Abstract: Much of the focus in RL today is on evaluation design: building meaningful evals that serve simultaneously as benchmarks and as well-defined reward sign
Introducing the Printing Press, a CLI-factory and a CLI-library. Built with @trevin. 🏭🖨📚 Most APIs suck for agents. Most MCPs suck for agents. Most official CLIs suck for agents. They waste tokens and
just imagine what might happen if everybody was stockpiling GPUs at high prices for a demand that didn’t quite materialize…. So, look surprised: xAI, which is now part of SpaceX, stockpiled too many N
arXiv:2605.04261v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and modera
Listen to Cat. This interview with @lennysan captures a shift we’re all feeling: what it means to be a PM (and build products) in the age of AI. My takeaways (mostly her words, with some tweaks for ho
arXiv:2605.03952v1 Announce Type: cross Abstract: Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The chal
arXiv:2605.04208v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive multilingual capabilities for well-resourced languages, yet their performance on low-resource
arXiv:2605.03353v1 Announce Type: cross Abstract: LLM-Agents have evolved into autonomous systems for complex task execution, with the SKILL.md specification emerging as a de facto standard for encaps
arXiv:2605.03195v1 Announce Type: new Abstract: Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibiliti
We've teamed up with @cerebras to offer free Windsurf plans for SWE-1.6 Fast Mode at up to 1000 tok/s! Fast Mode is built on Cerebras inference, enabling superior speed for planning and development wi
Simon Willison / Simon Willison's Weblog: While Anthropic will use the Colossus 1 data center, which has a really bad environmental record, xAI retains the larger Colossus 2 for its own AI training —
arXiv:2605.03808v1 Announce Type: cross Abstract: Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards
arXiv:2605.01727v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for automated news credibility assessment, yet it remains unclear whether they apply even-handed stan
arXiv:2605.03310v1 Announce Type: cross Abstract: Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects rather than base-model capability. Existin
arXiv:2601.03731v3 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consiste
arXiv:2601.06445v2 Announce Type: replace Abstract: Computational narrative analysis aims to capture rhythm, tension, and emotional dynamics in literary texts. Existing large language models can gener