Knowledge catalogue
Anthropic PBC Chief Executive Dario Amodei has once again called for the artificial intelligence industry to slow down the pace of frontier model development, only this time he’s being backed by two b
Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0.
common : implement common_schema internal representation for JSON schemas (#28736) common : implement common_schema types common : implement a json schema optimizer common : reduce optimizations commo
deepseek v4.1 flash has arrived on together ai it beats gpt-5.6 sol on agentic benchmarks at one third the cost per task the model supports a 1m context window and native multimodal input, with 552b t
Should you build an agent harness? I see lots of opinions about it. My thoughts: As an AI engineer, learning how to build a harness is one of the best ways to stay ahead and unlock unique value from a
I’ve been building Catalyst around a capability I want engineering agents to have: An AI agent can read a program and make a good guess about what matters. Catalyst lets it measure what actually matte
arXiv:2609.11147v1 Announce Type: new Abstract: Unraveling reaction mechanisms is central to modern chemistry, yet automating these investigations remains challenging because computational workflows s
I'm a teacher looking into running an LLM locally. I've been using ChatGPT for a lot of this work, so I started looking at Ollama because I understand it's designed to run LLMs locally. That said, I'm
arXiv:2609.11060v1 Announce Type: new Abstract: Persistent memory is entering production-oriented agent platforms to help long-horizon agents accumulate experience across sessions. Yet a post-task cur
https://github.com/Sayitobar/chat_llm_cookbook This is my personal project that took several months. I wanted to see whether a 2B small local model could simulate a six-person group chat trained & ran
Another new model dropped in the course of this week that is well deployable on consumer hardware: Nex N2.5 Mini I went with the recommended settings for the best generation quality and ran a few benc
Artificial intelligence agents tied to OpenAI Group PBC reportedly hacked a popular code hosting service earlier this year. The Wall Street Journal detailed the breach today. The malicious activity wa
arXiv:2609.11188v1 Announce Type: new Abstract: Synthetic image attribution (SIA) has become increasingly important with the rapid advancement of text-to-image generation models. However, accurately i
arXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test w
metal : single-source fusion table + fusion debug rework (#28164) metal : rework fusion patterns into a single table All fusable op patterns for the Metal backend are now declared once in a fusion tab
Tested on Laptop with RTX 5060 8gb vram and 16gb ram Claude code - autocompact = false Ollama - Flash attention = 1, kv cache = q8_0 Gemma4 12B 64K - https://ollama.com/SetneufPT/Gemma4-12B-IT-QAT_Q4_
arXiv:2609.10105v1 Announce Type: cross Abstract: Compute governance today is a governance of training: the thresholds, reporting requirements, and frontier-AI regimes now in force attach to training
arXiv:2609.10181v1 Announce Type: cross Abstract: AI agents are increasingly involved in network automation, where they can initiate configuration changes through mediated operational interfaces and a
Hi everyone, I was interested in learning LoRA fine-tuning, and ended up building CodeFinetuner over the past few months, a full pipeline that fine-tunes a small code autocomplete model (e.g. Qwen2.5-
My comment on Feeling sad about AI — Hacker News.I'm not sure how useful it is to say this, but I think a lot of people (myself included, a few years ago now) have been through this moment of existent
Interesting paper from Microsoft. If you run persistent memory for a production agent, this one is worth your time. (bookmark it) Memory curators usually read only the finished trajectory. That lets t
arXiv:2609.09203v1 Announce Type: new Abstract: Existing benchmarks for autonomous AI scientists evaluate only final outputs---generated code, hypotheses, or papers---yet discard the reasoning process
arXiv:2609.09774v1 Announce Type: new Abstract: Procedural memory lets language agents reuse successful routines, but reuse presumes that a stored routine remains applicable. We study what happens whe
arXiv:2609.09657v1 Announce Type: new Abstract: Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interp
arXiv:2609.09627v1 Announce Type: new Abstract: Capabilities relevant to Physical AI can arise from materially different formation histories, yet existing taxonomies organized by morphology, architect
i've been thinking about this more after trying different agent setups. the model isn't the only thing that determines how well an agent performs. The harness around the model matters a lot too. With
arXiv:2609.10750v1 Announce Type: cross Abstract: LLM agents increasingly rely on external skills retrieved at runtime, making skill selection from large repositories a critical challenge. We present
arXiv:2606.16723v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is
arXiv:2609.10036v1 Announce Type: cross Abstract: Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment be
arXiv:2609.06059v1 Announce Type: new Abstract: As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to as
arXiv:2609.05576v1 Announce Type: new Abstract: The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents that execute long-horizon tasks across stateful
Artificial intelligence startup Runway Financial Inc. said today it has decided to pivot away from accounting software and rebrand itself as cfo.ai. That decision marks the launch of its new flagship
Checking agent-generated code usually means hopping between tabs. Learn how to view diffs, run terminal commands, and preview web apps side by side in the GitHub Copilot app. The post GitHub Copilot a
arXiv:2609.10494v1 Announce Type: new Abstract: Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet a
arXiv:2609.07594v1 Announce Type: cross Abstract: Conversational Task Assistants (CTAs) are multimodal dialogue systems that support users in complex real-world tasks such as cooking and DIY through v
arXiv:2609.09206v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) often struggle with hallucinations, thus hindering their reliable practical applications. Existing attention-
arXiv:2609.08950v1 Announce Type: cross Abstract: Text-to-SQL systems translate natural language queries into executable SQL, democratizing access to structured data. Despite recent advances driven by
arXiv:2609.05677v1 Announce Type: cross Abstract: Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usua
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explorat
arXiv:2508.04175v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly
arXiv:2609.07188v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection is critical for safe deployment of medical AI systems. Recently, test-time adaptation (TTA) has emerged as a new par
arXiv:2609.07336v1 Announce Type: new Abstract: Morphology of the sub-basal nerve plexus (SNP) reflects peripheral nerve health, and corneal confocal microscopy (CCM) provides an important means for i
We are thrilled to announce the general availability of the AlloyDB Omni Red Hat RPM orchestrator, that brings production-ready security, resiliency, and low-downtime operations to PostgreSQL workload
arXiv:2509.15611v2 Announce Type: replace-cross Abstract: Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced depen
Investigating how one AI agent works might not be enough, since there are emerging properties when these agents collaborate as tribes Thinking about this for years. I believe we're at the point of no
arXiv:2609.05933v1 Announce Type: new Abstract: Efficiency is increasingly important for Large Language Model (LLM)-based multi-agent systems (MAS), as larger models and more agents introduce substant
arXiv:2609.09113v1 Announce Type: cross Abstract: While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a mis
Gary Marcus argues that current generative‑AI models fail to meet basic standards of reliability because they routinely hallucinate facts, amplify existing biases, and provide no transparent audit tra
arXiv:2609.05513v1 Announce Type: cross Abstract: Web agents have achieved significant success in automating complex internet tasks but deploying them in real-world environments requires continuous on
Hello LocalLLaMA Fam! I built this project because I, like many of us here, enjoy local AI and have a nice setup, but still find myself reaching for Cloud-based AI due to their convenience. My models
Introducing ChatGPT Images 2.5 OpenAI's image generation models are apparently used 'more than 3 billion images across ChatGPT Images and the GPT‑Image models in the API'. This latest release improves
I was reading up on the recent controversy around Tristan Buckmaster, Levent Alpöge, OpenAI, and the Navier–Stokes result, and it got me thinking about something broader than this particular dispute.
OpenAI Group PBC Chief Scientist Jakub Pachocki called for an artificial intelligence research slowdown in an essay published on Sunday, after other prominent industry figures have expressed similar v
Up front: I'm one of the people building the page-perception layer used here. We started by testing small local models. The result turned out to be more interesting than the original test. 12 small mo
Quick setup on linux: STEP 0: install/download llama.cpp, Freecad, your favourite gguf model - possibly with multimedia image reading capabilities (I've used Qwen3.8-27B-UD-Q4_K_M and relative mmproj-
Hi all! I just wanna say that I am tired lol. Yes, it's another harness, but I spent a lot of time and effort and have forsaken my hobbies to build the Jenny (like XJ-9) app. Jenny is a free, MIT lice
arXiv:2609.04206v1 Announce Type: cross Abstract: Voice AI systems increasingly mediate customer care interactions where caller presentation cues such as accent, affect, fluency, and urgency are avail
I used to work that way, but now it feels frustrating. I prefer that my coding agent receives @QodoAI’s code review findings before opening a pull request or even better, on a draft pr. Let them agree
Cade Metz / New York Times: Insilico, which uses AI to accelerate drug discovery, says early data shows rentosertib, a drug whose structure was generated with AI's help, could slow aging — Artificial
arXiv:2609.04721v1 Announce Type: new Abstract: Where inside a language model does refusal live, and does that place change when the architecture does? In a transformer, refusal is governed by a singl