Knowledge catalogue
you may have heard that glm-5.2 at 392 token/s is cool, how about 446 except… it’s all noise. Artificial Analysis picks median among 8 points/day so first point of the day can be way off looking at 3
OpenAI has released GPT-5.6 with three variants (Sol, Terra, Luna) in a restricted beta program limited to trusted partners, according to reporting from Latent Space. The restricted access model sugge
And the idea that frontier open weights models will continue to be released was fragile even before the current de facto licensing regime. https://x.com/emollick/status/2067669551685218638?s=20 Is the
I put together a new article on setting up local coding agents with open-weight models. Everything runs 100% locally. I thought it might be useful putting this together because many people asked me ab
LiteParse is unreasonably good for document parsing ✅ It is the fastest document parsing tool out there - average parse time per page is 3ms ⚡️⚡️ ✅ Now that we support markdown, it tops opendataloader
Run Ornith with Ollama: ollama run ornith For coding, use it with Claude or Pi: ollama launch claude --model ornith ollama launch pi --model ornith For the more capable 35B model, use: ollama launch c
Sakana Fugu Technical Report Instead of training one larger model, Sakana AI trains an orchestrator that reads each query and dynamically routes or composes GPT-5.5, Gemini-3.1-Pro, Claude Opus 4.8 an
Ethan Mollick comments on how a new licensing regime will likely eliminate vague model announcements and promotional posting practices previously used by AI labs. The post uses literary language ('Goo
Laura Bratton / The Information: Sources: Salesforce staff worry Anthropic's Claude Tag could cannibalize Slackbot and give the AI firm more leverage over the enterprise software industry — When Anthr
Thanks for running our open-source work on current frontier models “The results are: the most capable models today (GPT-5.5 Pro) did outperform the best models from before (79/100 vs 69/100), but did
Bloomberg: The rapid pace of AI progress has created a pervasive fear of missing out across Silicon Valley, fueling anxiety among founders, executives, employees, and VCs — Claude Code is cutting into
The take that frontier models aren't ready for use in medicine is dead wrong. I've been using Opus 4.x in my clinical workflow every day for 6 months. I'm a deep sub-sub-specialist in dermatology - th
This article likely explores how to implement and deploy coding agents that run locally on a user's machine rather than relying on cloud-based services, potentially covering advantages like privacy, l
VCs are now sharing screenshots in group chats of Claude discouraging investment in open-source AI infra startups and models. Obviously there is an absolute EXPLOSION of pitches in inference companies
1/ On p (doom) tl;dr a) Everyone is making up the numbers b) nobody knows anything (least of all the experts), c) don't worry about it d) there is nothing you can do to stop it e) most things you can
arXiv:2512.04238v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly integrated into clinical workflows. However, existing benchmarks primarily assess performance on comm
arXiv:2606.26457v1 Announce Type: cross Abstract: This paper presents a probabilistic framework for online test-time adaptation problems. In them, a model is trained on labeled data but must adapt to
arXiv:2606.26359v1 Announce Type: new Abstract: Ray Kurzweil described a thesis of accelerating returns, which is the most influential narratives in discussions of technological progress. Its central
arXiv:2606.26455v1 Announce Type: cross Abstract: RGB-Event tracking improves localization robustness by fusing RGB appearance textures and dense temporal motion cues from event sensors. While this mu
arXiv:2606.26479v1 Announce Type: cross Abstract: Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training the
arXiv:2606.26566v1 Announce Type: cross Abstract: Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LL
arXiv:2606.26627v1 Announce Type: cross Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a us
arXiv:2606.26705v1 Announce Type: cross Abstract: Feedforward neural network (NN) expressivity is typically studied by emulating optimal basis-expansion schemes. While powerful, this perspective is in
arXiv:2606.26490v1 Announce Type: cross Abstract: Static verification tools can assure industrial scale software, but require significant human labor to write specifications. This is particularly true
And the balance returned to earth Introducing a limited preview of GPT-5.6 Sol, our next generation frontier model, as well as GPT-5.6 Terra, a balanced model for efficient, everyday work, and GPT-5.6
@anthropicai: Anthropic says the US government is allowing Mythos 5 to be redeployed to critical infrastructure operators, and is working to restore general access to Fable 5 — Since June 12, we've be
arXiv:2606.27376v1 Announce Type: new Abstract: Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision,
arXiv:2606.26104v1 Announce Type: cross Abstract: Animal-welfare advocates produce a lot of writing, and increasingly that writing trains the language models that millions of people then ask about ani
arXiv:2606.26893v1 Announce Type: new Abstract: We study learning in prophet inequalities with i.i.d. rewards drawn from an exponential-type parametric family with an unknown parameter heta, a class t
arXiv:2606.26460v1 Announce Type: new Abstract: AI-based scientific automation is increasingly possible by using agents to generate hypotheses, design experiments, and analyze data. Data collection is
arXiv:2606.26649v1 Announce Type: new Abstract: Agent safety in high-stakes domains requires formal policy enforcement, but most existing approaches either rely on probabilistic guardrails (fine-tuned
arXiv:2606.27361v1 Announce Type: cross Abstract: Efficient sampling of molecular systems at thermodynamic equilibrium is a hallmark challenge in statistical physics. This challenge has driven the dev
arXiv:2502.18966v2 Announce Type: replace Abstract: General chemical reaction conditions that achieve consistently high performance across multiple substrates are important for practical applications
arXiv:2606.26099v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in artificial intelligence (AI) governance analysis across national and international organisat
arXiv:2606.27090v1 Announce Type: cross Abstract: Global objectives, such as KL divergence and ELBO, are widely used in Bayesian inference for measuring distributional discrepancy. This paper studies
arXiv:2606.14122v2 Announce Type: replace Abstract: Byte-level tokenization enables language models to handle any Unicode input, but models can generate invalid UTF-8 sequences when encountering rare
arXiv:2606.27314v1 Announce Type: new Abstract: To avoid moderation and surveillance on social media, some users routinely invent indirect linguistic expressions (ILE) that camouflage sensitive meanin
arXiv:2606.26519v1 Announce Type: new Abstract: Large language models (LLMs) can make scientific software easier to use. However, a general model does not automatically know which measurements a parti
arXiv:2606.27292v1 Announce Type: new Abstract: This paper presents BOWConnect, a bidirectional parallel kinodynamic motion planner that addresses three fundamental limitations of existing sampling-ba
arXiv:2606.26541v1 Announce Type: new Abstract: Data from affected populations are crucial for informing humanitarian response, but their value depends on timely and consistent interpretation of nuanc
arXiv:2606.26861v1 Announce Type: new Abstract: Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning
arXiv:2606.26538v1 Announce Type: cross Abstract: Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add little value. We present two efficiency method
arXiv:2606.26618v1 Announce Type: new Abstract: Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their traini
arXiv:2606.26489v1 Announce Type: new Abstract: News media play a central role in shaping public perceptions of climate change, and whether coverage emphasizes threats or solutions has measurable effe
arXiv:2606.26904v1 Announce Type: cross Abstract: Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we term the Blind Trust Problem: unde
arXiv:2606.26437v1 Announce Type: cross Abstract: Existing metrics for factuality and faithfulness evaluate whether an answer is supported or contradicted by its grounding documents, but they fail to
arXiv:2606.26852v1 Announce Type: new Abstract: Order fulfillment in manual picker-to-goods warehouses involves interconnected decisions such as item assignment, order batching, and picker routing. Wh
arXiv:2606.26105v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due t
arXiv:2606.26753v1 Announce Type: new Abstract: Conversational memory retrieval optimizes relevance, yet a retrieved memory can be relevant and simultaneously outdated: a later turn updates, corrects,
arXiv:2606.27264v1 Announce Type: new Abstract: Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text jud
arXiv:2606.26216v1 Announce Type: cross Abstract: We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability det
arXiv:2606.26454v1 Announce Type: new Abstract: Sphere neural networks have achieved symbolic level syllogistic reasoning without training data, raising the question of where the limit of the scaling
arXiv:2606.26990v1 Announce Type: cross Abstract: Uncertainty estimates in machine learning are typically evaluated using generic metrics such as the negative log-likelihood and expected calibration e
arXiv:2606.26687v1 Announce Type: new Abstract: In industrial environments, new product categories arrive sequentially, requiring continual anomaly detection without access to past data. Normalizing F
arXiv:2606.26602v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive fine-grained perception capabilities. However, existing ben
arXiv:2601.01701v2 Announce Type: replace-cross Abstract: Anomaly detection is increasingly becoming crucial for maintaining the safety, reliability, and efficiency of industrial systems. Recently, wi
arXiv:2606.26668v1 Announce Type: cross Abstract: Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos. While sig
arXiv:2606.26116v1 Announce Type: cross Abstract: A brand whose customers use both ChatGPT and Claude for product recommendations faces a strategic choice: a single optimization playbook, or one per p
arXiv:2606.26738v1 Announce Type: new Abstract: While recent advancements in generative image editing models have achieved stunning visual fidelity, it remains an open question whether these systems p
arXiv:2606.12716v2 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant r