Knowledge catalogue
mythos will be bad ON PURPOSE on ai 'frontier llm research' tasks, this is very very sad for the research community also the fact that this is un purpose not visible to the user is crazy Introducing C
arXiv:2606.08948v1 Announce Type: cross Abstract: Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large mul
arXiv:2510.17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de
I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything
arXiv:2606.07711v1 Announce Type: cross Abstract: Memory is the key component for transforming a stateless LLM into a persistent, evolving agent through experience accumulation, long-horizon planning,
arXiv:2606.08529v1 Announce Type: new Abstract: Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well
arXiv:2606.07889v1 Announce Type: cross Abstract: LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway. We call this pattern strained coherence: a saf
arXiv:2606.07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by
arXiv:2606.07462v1 Announce Type: new Abstract: As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-
Oh my God! @METR_Evals’s coding benchmarks are saturated! 🤯 Mythos broke the METR graph 🤯 4 weeks later, out comes a new coding task, this time from @cognition: “FrontierCode Diamond remains unsaturat
Rubrics are even more flexible than /goal You can define a custom subagent for the grading, including custom tools, prompt, and iteration limits. Try it out and let us know what you think! we just shi
So excited to be opening up OpenEnv to the whole community. It will now be owned by @huggingface , Meta-PyTorch, @reflection_ai , @UnslothAI , @modal, @PrimeIntellect , @NVIDIAAI , @mercor_ai , and @f
we just shipped support for rubrics in deepagents ✅ give your agent a clear definition of what 'done' looks like, and force it to run in a loop until said goal is complete this is similar to /goal in
Release: datasette-agent-edit 0.1a0 I'm planning several plugins for Datasette Agent which can make edits to existing pieces of text - things like collaborative Markdown editing, updating large SQL qu
arXiv:2602.13255v2 Announce Type: replace Abstract: We present DPBench, a benchmark for evaluating coordination in multi-agent systems built from large language models. Existing benchmarks measure tas
arXiv:2606.06322v1 Announce Type: new Abstract: GUI agents - vision-based models that control desktops, web browsers, and mobile devices through graphical user interfaces - promise to automate a wide
arXiv:2606.05632v1 Announce Type: new Abstract: Within the past few years, the ability of Large Language Models (LLMs) to generate formal mathematical proofs has improved drastically. We provide a com
it’s a bad day when @scaling01 goes all Gary Marcus on the media 🤣 This is a good example of how AI news gets distorted. The example is from Tagesschau, the most watched news program in Germany. Anthr
I've been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics I've been lookin
arXiv:2606.05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and r
arXiv:2606.05525v1 Announce Type: new Abstract: Recent advances in agentic visualization have enabled the translation of natural language into executable scientific visualization (SciVis) workflows. W
arXiv:2606.05403v1 Announce Type: cross Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions. Whether they evaluate the qual
arXiv:2606.06055v1 Announce Type: new Abstract: Long-term memory enables language model agents to support personalized interactions, but it remains unclear when available memories warrant integration
arXiv:2606.06460v1 Announce Type: cross Abstract: As autonomous LLM agents increasingly hold real credentials and operate infrastructure without a human in the loop, operators have no standard way to
arXiv:2606.05924v1 Announce Type: new Abstract: Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary
arXiv:2504.10823v4 Announce Type: replace Abstract: Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been li
arXiv:2606.05647v1 Announce Type: cross Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to cod
arXiv:2606.05233v1 Announce Type: cross Abstract: Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster
arXiv:2606.05874v1 Announce Type: new Abstract: Current evaluations for Multimodal Large Language Models (MLLMs) overwhelmingly focus on utility-driven objectives, leaving model behavior under logic-n
arXiv:2606.05176v1 Announce Type: new Abstract: While large language models (LLMs) show strong performance in natural language understanding and generation, their evaluation and adaptation to domain-s
arXiv:2606.05836v1 Announce Type: new Abstract: Large language models have substantially advanced Text-to-SQL systems, yet applying them to enterprise-scale databases remains challenging. Real-world d
arXiv:2606.06454v1 Announce Type: cross Abstract: Large language models increasingly write, review, and judge code, and a fast-growing practice equips them with prompt 'skills' that ask the model to r
arXiv:2606.05308v1 Announce Type: cross Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-la
Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write code, so they'll just rebuild every tool from scratc
A couple of weeks ago we started rebuilding the 𝚑𝚏 CLI with AI agents in mind. it now detects when an agent is using it and gives clean, token-efficient output, next-command hints, and more, all desig
arXiv:2606.04781v1 Announce Type: new Abstract: Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-derive how to act in every session. This imposes tw
arXiv:2606.05080v1 Announce Type: new Abstract: Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and c
arXiv:2606.04816v1 Announce Type: new Abstract: Large language models (LLMs) increasingly translate natural-language optimization problems into executable solver code. Yet for constraint-dense operati
Finally! the first eval ship from cog!!!!!!!!!! 👼🏼 To contextualize: @METR_Evals cap out at ~16 hours. Cog has private enterprise evals up to 100hrs, and is confident enough to put a financial guarant
I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HT
arXiv:2602.04101v2 Announce Type: replace Abstract: We present Interfaze, a native hybrid model that fuses task-specific deep neural networks (CNNs and DNNs) directly into a transformer decoder throug
arXiv:2606.05104v1 Announce Type: new Abstract: Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotat
Outstanding paper on long-horizon agents. (bookmark it) Similar to humans, how do you make agents persist on a difficult task, and how is that useful? And which models today work well on this? This ne
arXiv:2606.04970v1 Announce Type: cross Abstract: We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding ext
Financial Times: Sources: Anthropic has embedded around half a dozen forward-deployed engineers within the NSA to help the agency deploy Mythos for offensive cyber operations — Arrangement comes as AI
arXiv:2606.04152v1 Announce Type: new Abstract: Large language models are reshaping research practice while quietly eroding researchers epistemic accountability. This commentary introduces PEEL - Prot
arXiv:2606.04037v1 Announce Type: new Abstract: Pre-deployment verification of enterprise artificial intelligence (AI) agents remains a critical gap between large language model (LLM) capability bench
arXiv:2606.04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5
At Google Cloud, our goal is to let you run large-scale analytical and data science workloads with maximum efficiency so you can process big data pipelines, machine learning, and ETL tasks. We recentl
When you burn so much money you run out of options… Anthropic co-founder and President Daniela Amodei said the high cost of developing AI models is driving firms like hers to look to the public market
This post appears to be a query from Swyx asking @_catwu for an update on a previously shared chart, specifically regarding developments or changes that occurred after the release of Opus 4.8. The pos
A workflow audit is no longer the best way to figure out how to use AI in your job. Despite the advice from AI labs, I'm more convinced, because of AI's reasoning capabilities and long context horizon
arXiv:2606.03410v1 Announce Type: new Abstract: Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through d
arXiv:2606.03144v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning as
If this prompt feels well written to you, it's because Suzanne is a writer in her little spare time! You can read her short story, Mall of America here: https://suzannewang.com/mall-of-america It's on
Jerry Liu built one of the most installed pieces of AI plumbing of the last three years. Then he sat down and told me the framework era he helped create is over. The agent harness ate the abstraction
arXiv:2606.03743v1 Announce Type: new Abstract: While Large Language Models (LLMs) have shown strong performance in generating formal proofs, their outputs often remain less readable, modular, maintai
arXiv:2606.03907v1 Announce Type: cross Abstract: Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from s
This is really intellectually dishonest. I have not been arguing that LLM token prices are increasing (though the all you can eat buffet is over), I have been arguing the *opposite*, viz that they wil
This story was so implausible that the only way it even (kind of) made sense if it is some sort of internal accounting placeholder at a cloud provider using their own compute. And even then it seems u