Knowledge catalogue
arXiv:2607.14006v1 Announce Type: cross Abstract: Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational con
arXiv:2607.13881v1 Announce Type: cross Abstract: Human-object interaction detection (HOID) has traditionally been formulated as a supervised detection problem over predefined interaction categories.
A model drop by Thinky 🚨🚨 Have been doing some early testing on the model for the past couple of days. Here are some of my findings 1. The reasoning is sharp and concise! Always love to see models tha
as someone who does a lot of dev community and dev youtube this pace of growth has been one of the greatest mysteries to me because clearly there's something to learn here @sytses i'd love to talk to
Below Upstream Status sections are from https://github.com/PrismML-Eng/Bonsai-demo Upstream Status for Binary Q1_0 is supported out of the box in upstream llama.cpp across many backends: CPU (generic,
arXiv:2607.12252v1 Announce Type: new Abstract: Deep research agents are increasingly used to produce long-form financial reports, yet large-scale evaluation remains bottlenecked by the need for human
Inkling is our first open model from @thinkymachines and is now available on Tinker! Check out these quotes from Tinker customers on their experience with Inkling: @_Mantic_AI: 'Not only does Inkling
arXiv:2606.19387v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable success in software development. However, they are susceptible to hallucinations, meanin
arXiv:2607.12755v1 Announce Type: cross Abstract: AI-enabled systems are seeing increasing deployment across numerous domains, with many being 'black boxes' with respect to core functions and capabili
arXiv:2607.12477v1 Announce Type: new Abstract: Autonomous UAV systems increasingly rely on multimodal large language models (MLLMs) to operate in complex real-world environments. Such embodied scenar
Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat
arXiv:2607.10744v2 Announce Type: replace Abstract: Benefiting from the powerful priors embedded in large-scale pre-training data and the emerging commonsense reasoning ability, large language models
xai-org/grok-build, now open source xAI's grok CLI tool faced severe community backlash yesterday when it became apparent that running the command in a directory could upload that entire directory to
Power is AI infrastructure’s inescapable constraint. How many tokens an AI factory can generate within a fixed power budget determines its revenue and profitability. Because of this, performance per w
arXiv:2607.08331v1 Announce Type: cross Abstract: Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape art
great overview of general purpose brain! I just published a new video on OpenWiki Brains, specifically on the general-purpose brain mode. In the video I dive into: - configuring it locally - its archi
Here is a visualization of the AI Picbreeder engine in action. (From our blog: https://pub.sakana.ai/picbreeder-vlm/) To recreate a collaborative human ecosystem, we run 10 VLM “breeder” agents in par
I just published a new video on OpenWiki Brains, specifically on the general-purpose brain mode. In the video I dive into: - configuring it locally - its architecture - what the docs look like - new f
𝕏 is a great platform for product announcements, especially if done by the CEO directly. Way more interesting to the public than generic press releases. This post by Mark Zuckerberg already received o
Keeping up with AI news is becoming a full-time job. So my friend @ivan_bezdomny built HuggingNews, an AI-curated feed that surfaces the news actually worth reading. Soon, it will even personalize the
arXiv:2607.08182v1 Announce Type: cross Abstract: Vision-language-action (VLA) models aim to map multimodal inputs to robot actions. However, most existing approaches struggle to cover complex dynamic
arXiv:2607.08691v1 Announce Type: cross Abstract: Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conv
arXiv:2607.08373v1 Announce Type: cross Abstract: Connected vehicles are autonomous cyber-physical systems whose behavior must be continuously monitored during operation to detect deviations from norm
Zijing Wu / Financial Times: Sources: Manus investors and management are discussing unwinding Meta's $2B buyout at the same valuation, with Tencent in talks to become the largest investor — Chinese te
The most important thing about Grok Build and the 4.5 release is that it is genuinely so useful for real-world work Grok 4.5 just topped Perplexity’s WANDR orchestrator evaluation It scored higher tha
arXiv:2607.07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn? Today, the field largel
arXiv:2607.07029v1 Announce Type: cross Abstract: Reinforcement learning (RL) policies can be unsafe and vulnerable to attacks. Ensuring their reliability is often a pain point as existing automated t
Grok 4.5 on OpenClaw Grok 4.5 from @SpaceXAI is live on OpenClaw. No OpenClaw update required, just connect your X Premium or SuperGrok subscription, select Grok 4.5 under the xAI provider, and use an
arXiv:2607.07040v1 Announce Type: new Abstract: How can we measure intelligence beyond human capability? Human-authored benchmarks saturate, and above human capability, examiners may not know which ta
My feed has been hijacked this week by frontier model influencers who say they've had 5.6 Sol and Fable for 'months'. I think this tells an inaccurate story the field. From the outside it makes AI pro
arXiv:2601.14271v2 Announce Type: replace Abstract: Shared accountability records are often used by parties who may never agree about causation, responsibility, or normative interpretation. For such r
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts
Thank you @hwchase17 @BraceSproul @devstein64 @jeffreyhuber for the LLM Wikis session today, I absolutely loved it! Really grateful you keep these sessions open and honest about what actually works in
Token per watt — not raw compute — is emerging as the defining efficiency metric for AI data centers, putting storage at the center of an infrastructure rethink that is reshaping how the industry meas
arXiv:2607.05638v1 Announce Type: cross Abstract: Teams deploying large language models in business contexts need evaluation systems, yet most treat evaluation as static model selection: run benchmark
arXiv:2607.05462v1 Announce Type: cross Abstract: As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse. We present BioSecBench-Refu
arXiv:2607.05970v1 Announce Type: cross Abstract: Dataset search depends heavily on metadata, making LLM-generated metadata a consequential form of synthetic content in retrieval systems. We study six
arXiv:2607.05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfa
arXiv:2506.09276v4 Announce Type: replace-cross Abstract: This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories,
arXiv:2603.02277v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, cr
Rewriting Bun in Rust Jarred Sumner has been promising this blog post (since May 9th) about his Zig to Rust rewrite of Bun for significantly longer than it took him to finish the rewrite. Honestly, it
arXiv:2512.18542v3 Announce Type: replace-cross Abstract: AI coding assistants produce vulnerable code in 45% of security-relevant scenarios~ite{veracode2025}, yet no public training dataset teaches b
arXiv:2607.06374v1 Announce Type: new Abstract: Vision-language models (VLMs) have made interactive digital museums increasingly feasible by connecting 3D digitization with natural-language artifact e
You don't need heavyweight VLMs to OCR simple text-only PDFs. Doing that is like bringing a bazooka to a knife-fight, and is completely unnecessary and worse quality than a tuned OCR approach. Output
arXiv:2606.12502v2 Announce Type: replace-cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same catego
arXiv:2607.04124v1 Announce Type: cross Abstract: Employing multiple manipulators can boost efficiency and accomplish tasks that a single manipulator cannot do. However, real-time planning for multipl
arXiv:2607.02873v1 Announce Type: cross Abstract: Large language model agents driving security tool suites over the Model Context Protocol are increasingly common. Yet the factors that bound their cap
arXiv:2607.03100v1 Announce Type: cross Abstract: Modern web applications increasingly expose accessibility barriers through interaction flows rather than static page snapshots. Keyboard traps, focus
arXiv:2607.04634v1 Announce Type: new Abstract: In heterogeneous robot swarms, caste reassignment (rebinding a robot to a new capability-bound role) is a high-frequency runtime event driven by battery
arXiv:2607.04562v1 Announce Type: new Abstract: Large language models (LLMs) generate fluent outputs that can be wrong. Unlike humans, who often exhibit cues when providing false information, LLMs pro
arXiv:2607.05032v1 Announce Type: new Abstract: Background: Disease severity is a multidimensional construct difficult to capture with rule-based approaches in Electronic Healthcare Records (EHR). Age
arXiv:2607.02932v1 Announce Type: cross Abstract: Privacy is an important challenge when users interact with AI chatbots, since users may share sensitive information, explicitly or implicitly, and AI
arXiv:2607.02731v1 Announce Type: cross Abstract: Machine learning has demonstrated significant potential for real-time monitoring, optimization, and control of scientific facilities. However, deployi
arXiv:2607.04812v1 Announce Type: new Abstract: Bird's-Eye View (BEV) end-to-end instance prediction has emerged as a robust paradigm for autonomous driving perception, effectively mitigating the erro
This is the great thing about OpenWiki! It’ll maintain the docs for you automatically. Just setup a GitHub to run: openwiki —update and it’ll put up a PR once a day with changes / additions to your me
arXiv:2607.03386v1 Announce Type: new Abstract: Agentic AI systems are increasingly used to edit, refine, and repair decision policies, but evaluating these edits is difficult when per-state expert ac
big things happened over the weekend! OpenWiki is at 1.7k stars in just 3 days! Right now it's just for codebases, but we're working to expand it to everything for memory. What do you want to see in a
How do you trace one number in a 200 page ESG report back to the exact page it came from? We dug into that with the @llama_index team behind LiteParse. We tested five ways to retrieve evidence across
I predict 50% of companies will need new leadership, because the old management style won't work in the era of AI. That's exactly why I'm seeing 95%+ of so-called 'AI Transformation' initiatives fail.
In this post, we walk through how to get started with MiniMax models on Amazon Bedrock, including the capabilities supported by these models, the service tiers available, how on-demand inference scale