Search: “gpt”

arXiv:2610.01023v1 Announce Type: cross Abstract: Coding agents can return plausible patches that omit required behavior. These failures are hard to review because long traces and confident summaries

I've been experimenting with running larger models locally with Ollama, mainly because I'm interested in using them for agentic coding. I kept seeing benchmarks expressed as something like: 40 tokens/

Hey guys, Last time I tested Qwen3.8-Flash-Next on its own. This time I put three Qwen3.8 checkpoints through the same 10 tests on the same RTX PRO 6000: RadixArk/Qwen3.8-27B-NVFP4 (dense) orcarouter/

arXiv:2610.02196v1 Announce Type: cross Abstract: We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills,

arXiv:2610.00087v1 Announce Type: cross Abstract: The advancement of natural language processing (NLP) has expanded AI-based text classification in the legal domain. However, accurately classifying le

I've been on Plus for over a year and have never once agreed to an upgrade to Pro, yet I've now been charged for it twice. This is ridiculous. Plenty of other users have been reporting the exact same

arXiv:2610.01222v1 Announce Type: new Abstract: As generative AI (Gen AI) systems take on increasingly autonomous roles in economically and socially consequential interactions, understanding their pro

arXiv:2610.00526v1 Announce Type: cross Abstract: In-context learning (ICL) can be amortized into latent objects (task vectors, function vectors, context vectors) that recover few-shot behavior at zer

arXiv:2610.01046v1 Announce Type: cross Abstract: Collaboration depends on shared context, and technical documentation is one way that context persists across people and AI teammates. Specificity, the

@tavus: Tavus unveils Griffin, the “first Human Interaction Model”, which it says passed the “video Turing test”, with 48% of users thinking it was human in live chats — Introducing Griffin, the first

arXiv:2610.00833v1 Announce Type: cross Abstract: Fluent LLM explanations may not follow the evidence from a structured system. We present VERITYGATE, a four-gate checker for declared evidence IDs, en

arXiv:2610.00373v1 Announce Type: new Abstract: Attention-head ablation, zeroing a head and measuring the resulting change in task performance, is a common method for inferring which components of a l

arXiv:2609.39714v1 Announce Type: new Abstract: Top researchers have good intuition, but do language models have as good intuition about model training as top AI researchers? To measure model intuitio

arXiv:2609.40353v1 Announce Type: new Abstract: The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general

arXiv:2609.39035v1 Announce Type: cross Abstract: Passenger access doors are safety-critical subsystems in railway vehicles, yet detecting abnormal door behavior in real operation is challenging becau

arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present

arXiv:2510.17932v5 Announce Type: replace-cross Abstract: We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (L

arXiv:2609.39243v1 Announce Type: new Abstract: Causal interventions such as activation patching and distributed alignment search (DAS) are the main tool for making mechanistic claims about neural net

arXiv:2609.38647v1 Announce Type: new Abstract: Direct preference optimization (DPO) models binary preferences through a Bradley-Terry model with a common noise scale, without explicitly accounting fo

arXiv:2609.38621v1 Announce Type: new Abstract: Two scientific findings can disagree without contradicting each other. Determining whether they conflict requires knowing whether they describe comparab

arXiv:2609.37887v1 Announce Type: new Abstract: Activation and key-value cache precision change what a quantized language model computes without altering its stored weights. Direct weight-code bounds,

arXiv:2609.35841v1 Announce Type: cross Abstract: Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However, traditional rule-based tools often generate l

A new report out today from Google LLC’s Google Threat Intelligence Group finds that monthly software vulnerability disclosures doubled between January and August. Not surprisingly, artificial intelli

arXiv:2609.36550v1 Announce Type: new Abstract: Retrieval-augmented generation is widely used in professional writing, yet whether retrieval grounds revision or merely injects templates is rarely test

arXiv:2609.36278v1 Announce Type: new Abstract: Generative agent-based models (GABMs) are increasingly used to simulate social media dynamics, including misinformation spread. For such social simulati

SynthID Bio is a protein‑generation platform developed by AlphaProteo that delivers custom-designed peptides for use in biology and health research. It was highlighted in the September 2024 issue of *

Last Week in AI #345 notes that Anthropic and OpenAI are in a close race to launch more capable but cheaper models this month: Anthropic unveiled Claude Opus 5.5 with stricter cybersecurity safeguards

arXiv:2609.36380v1 Announce Type: new Abstract: A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program w

arXiv:2609.35381v2 Announce Type: replace-cross Abstract: Many Model Context Protocol (MCP) servers wrap web APIs built for human developers, and their error messages tell the reader to run a command,

arXiv:2609.37583v1 Announce Type: new Abstract: Vision-language models can coordinate long-horizon robot manipulation, yet successful task reasoning still depends on whether local physical interaction

Bloomberg: Sources: some Google employees say Gemini 4 performs well on benchmarks but struggles with some real-world coding tasks; Google disputes that characterization — As Alphabet Inc.'s Google pr

arXiv:2609.36808v1 Announce Type: cross Abstract: Current embodied models do not respond to their own failures, although what just went wrong could inform a small adjustment on the next attempt, the k

arXiv:2506.08140v2 Announce Type: replace Abstract: Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-qualit

Codex Security Cloud is getting a major upgrade, with access to cyber-capable models through Daybreak Blue included by default. It scans entire GitHub repos, continuously reviews new commits, investig

OpenAI introduced “Dots,” an AI system built to run continuously and free users’ time so they can focus on higher‑level tasks. The announcement was posted on September 29 2026 by CEO Sam Altman via Tw

arXiv:2604.05137v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate functionally correct programs that differ substantially in execution efficiency. Existing inference-

arXiv:2609.32653v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to abstain from unanswerable questions is as important as their ability to answer answerable ones accurat

OpenAI just announced the 200 Pro plan is back but with half the total API spend included, offset by some of their smaller (NOT Astra!) getting a 50% price drop. Does this impact the average user? No.

arXiv:2609.32862v1 Announce Type: new Abstract: A foundation model should not act in isolation as an embodied agent. Yet, existing methods often optimize individual components of the agent stack, such

arXiv:2511.20104v2 Announce Type: replace Abstract: Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed 'emergent

What is a way to test human-level generality in artificial intelligence? 'The meta-benchmark of being able to pass ARC-AGI-(n+1) immediately upon release' @Jabaluck @DAcemogluMIT The meta-benchmark of

arXiv:2606.18383v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are increasingly used to study internal representations in language models (LMs), but it remains unclear when an SAE-base

arXiv:2609.30954v1 Announce Type: new Abstract: Large language models operating in multilingual contexts must resolve target response languages early in generation, yet the causal circuitry governing

arXiv:2609.31234v1 Announce Type: new Abstract: Problem. Ultra-high-resolution (UHR) remote sensing with vague user intents has two bottlenecks: visual tokens are expensive, and tool calling must be f

arXiv:2609.30716v1 Announce Type: cross Abstract: When a language model receives two conflicting documents as input, how does it decide which one to prioritize? Does it rely on how the sources are fra

I run my own LLM while also having a Openai subscription. Also tried DeepSeek (latest flash now). I run Qwen 3.8 flash Next at an amazing speed on my 2x3090 + Ram! But local LLM never did worked for m