Knowledge catalogue
arXiv:2608.06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet m
if you have been following his excellent work, @shloked has been breaking down every frontier labs' harness engineering for the last few months. excited to publish his deepest dive into ChatGPT yet as
Introducing Muse Code and Muse Spark 1.2 Yet more evidence that the most important characteristic of any model these days is long-sequence agentic tool calling. Meta shipped their own coding agent as
arXiv:2608.01810v1 Announce Type: new Abstract: Rubric-based LLM-as-judge pipelines often assume that evaluation criteria provide independent signals. In practice, however, criteria can be behaviorall
Introducing Sakana Namazu: An LLM API with Japanese-vibes! Today we’re rolling out an upgraded version of our LLM, Namazu, now available as an API. Try Sakana Namazu API: https://sakana.ai/namazu 🐟 🐟
Hello fellow local AI people! I took 'you must create your own benchmarks' literally, and built a website for this. How does the end result look like Let's say I want to know which model has most comm
arXiv:2607.27755v1 Announce Type: new Abstract: We address the problem of recovering the full-body mesh from only the head pose. This task has become essential for various applications based on head-m
Here is my experience, which I would like to share with you and I also would like to hear your thoughts and valuable tips&tricks. Hardware: Mac Mini M4 (32GB Unified Memory) Model Server: Ollama Orche
https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B-FP8 https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B-NVFP4 https://huggingf
Osmosis_AI claims that an open‑source model can rival a foundation model by leveraging reinforcement learning techniques. To demonstrate this, they will use the Y Combinator‑dedicated GPU cluster on T
Release: llm 0.32rc2 Hot on the heels of RC1, this fixes a dependency issue and also adds two neat new features: The default model for users who have not set their own default is now GPT-5.6 Luna. It
Traditional business intelligence alerts can only tell you that a metric changed, leaving data analysts to manually hunt through dashboards to figure out why. Today, we are introducing Looker Agentic
arXiv:2607.22948v1 Announce Type: cross Abstract: The ORBIT (Operations Responses and Business Intelligence Toolkit) project was initiated to assess agentic AI for the upcoming ESnet 7 initiative and
It has only been two days since I move 100% from Qwen3.5-27B F16 to ThinkingCap-Qwen3.6-27B F16. Where I was getting tps in 30-40 range (depending on the size of the context), I am definitely getting
In the prehistoric days of 2018, we incorporated the company as Runway AI, but could not afford to buy the domain runway dot com. Since the field was still mostly called machine learning back then, we
This is our biggest comparison yet. We've taken 23 Gemma 4 E4B models from huggingface and ran them through the abliterlitics gauntlet. We also have a new abliterlitics discord, feel free to jump on a
At Bitwize, we've been building Logue, a native macOS app for AI meeting notes and writing, and we just open-sourced it (MIT). We're sharing it here because the whole point is that it runs 100% on-dev
I've spent the last year or so playing around with open source MLX and GGUF models on iPhone hardware. Given the limitations in memory, GPU/CPU/ANE, and in turn the context window I've been trying to
arXiv:2501.19337v5 Announce Type: replace Abstract: A name alone measurably reshapes a language model's next-token distribution before a single token is sampled. We measure full-vocabulary Shannon ent
If you're running Laguna S 2.1 on llama.cpp and hitting thinking loops because it won't close its </think> tags, you might want to look at your quant before you spend too much time tweaking settings.
This is a surprisingly large real-world deployment: 'GovGPT' is part of Austria’s Public AI initiative, running on sovereign infrastructure (in their BRZ - federal datacenter) with Mistral open-weight
Hey HN, Henry & Roman here from Cactus. A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-t
@Engomar_10 @huggingface @alihfadel @Almalki_io We've seen the outpouring of support for ASRs in under-resourced languages, and we hear you. As a start, we've partnered with @HUMAIN to keep working wi
Together AI and Y Combinator have announced the launch of a dedicated GPU cluster for the YC portfolio. The cluster allows YC startups to access high‑performance compute with a commitment period of on
YC and Together AI are partnering to bring the first dedicated YC GPU cluster online, giving YC startups easier access to the compute they need to build and scale. In this Founder Fireside, YC's @agup
Automated lint: 20 errors, 8743 warnings, 3 info
Automated lint: 26 errors, 6728 warnings, 3 info
Creating my own interfaces in real-time to do the stuff I want to do is ridiculously empowering. Here's an example: - took ~10 app screenshots of things I wanted to fix - asked Claude to make a feedba
arXiv:2607.07277v1 Announce Type: new Abstract: Harmful online communication often contains slang, coded terms, abbreviations, and community-specific expressions, which make messages difficult to inte
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:2607.00048v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in exam- and certification-style question answering tasks, where their ability to retrieve, interpr
A candid hallway track interview with the man himself - @swyx Mini Podcast if you will, he's told me about a huge milestone tomorrow, things that have surprised him about @aiDotEngineer and ... a few
Businesses run on fast decisions, but the teams who hold the answers are often buried under a backlog of routine requests, leaving users waiting in line for insights they need now. Today, we are bring
Vercel’s open-source agent framework — durable sessions, sandboxes, HITL, tools/skills as files; positioned as Next.js for agents.
When you hear AI 'safety' you should hear 'censorship' and 'control' instead. All of us surveilled and spied by safeguards of loving grace. Today it's intelligent Terms of Service control. You can't d
arXiv:2606.09751v1 Announce Type: new Abstract: Foundation models are moving from response generation into operational roles. They plan across steps, call tools, request human input, coordinate with o
As generative AI moves from experimental pilots to massive production environments, the efficiency of your infrastructure becomes the ultimate differentiator. One way to get the most out of it and min
arXiv:2603.07294v2 Announce Type: replace Abstract: Fine-grained understanding and species-specific multimodal question answering are vital for advancing biodiversity conservation and ecological monit
arXiv:2606.05121v1 Announce Type: cross Abstract: Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only
arXiv:2606.04315v1 Announce Type: new Abstract: LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tun
arXiv:2606.00462v1 Announce Type: cross Abstract: Short-form text rewriting is a constrained variant of paraphrasing in which limited context and high semantic density leave little room for variation.
arXiv:2605.30574v1 Announce Type: new Abstract: Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries
arXiv:2605.26731v1 Announce Type: new Abstract: A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models n
arXiv:2605.24583v1 Announce Type: cross Abstract: We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qw
arXiv:2605.24279v1 Announce Type: new Abstract: A frontier language model's acknowledged 'helpful programming assistant' persona does not survive long agentic-coding sessions in the deployment regime
arXiv:2605.23825v1 Announce Type: cross Abstract: It has generally been assumed that geopolitical bias in language models originates from the training data used during the pre-training phase. We teste
arXiv:2605.23904v1 Announce Type: new Abstract: Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning
arXiv:2605.19329v1 Announce Type: cross Abstract: Conventional vision-language models (VLMs) struggle to interpret scenes captured under adverse conditions (e.g., low light, high dynamic range, or fas
arXiv:2605.15848v1 Announce Type: cross Abstract: Conversational interfaces powered by large language models (LLMs) are widely used for ideation and analysis, yet their linear structure limits explora
arXiv:2603.24586v2 Announce Type: replace-cross Abstract: As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial
Join us for a live build session exploring Hermes Agent integrated with ComfyUI. If you're already comfortable navigating ComfyUI workflows and want to understand what an agent layer brings to the tab
arXiv:2602.00327v2 Announce Type: replace Abstract: We explore the use of large language models (LLMs) for next-utterance anticipation in human dialogue. Despite recent advances in LLMs demonstrating
Managing a modern database fleet is both a scale and cognitive problem. As database estates grow, the effort required to monitor, troubleshoot, and optimize them often outpaces teams’ capacity, who fi
Wow! Wonder how many people on this site hyped this paper – and how many of them will walk back their hype now that the paper has been retracted. A year-old nature paper that advocated the use of Chat
arXiv:2605.00300v1 Announce Type: cross Abstract: Public inference benchmarks compare AI systems at the model and provider level, but the unit at which deployment decisions are actually made is the en
arXiv:2604.28138v1 Announce Type: cross Abstract: Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restor
> be me > 'the internet is polluted by ai slop, we need low-background tokens' > 'wouldnt it be cool if we could time travel and see what our ancestors 100 years ago would say to us' > all the existin
arXiv:2603.29080v2 Announce Type: replace Abstract: Many modern multi-modal models (e.g. CLIP) seek an embedding space in which the two modalities are aligned. Somewhat surprisingly, almost all existi
arXiv:2604.22973v1 Announce Type: new Abstract: Predicting future trajectories of surrounding traffic agents is critical for safe autonomous navigation and collision avoidance. Despite all advances in
Congrats to @poolsideai on Laguna XS.2 release. Day 0 support in @vllm_project. FP8, INT4, and NVFP4 quantized checkpoints created with LLM Compressor also ready today. 33B params, 3B active. Apache 2