Search: “gpt”

arXiv:2608.03913v1 Announce Type: cross Abstract: Dense pretrained transformers do not naturally expose interpretable units for circuit extraction. Existing approaches obtain such units by learning au

arXiv:2607.27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task

arXiv:2608.03018v1 Announce Type: new Abstract: Modern cities rely on an increasing number of digital services to operate, but residents' daily needs are still difficult to meet. Services are fragment

arXiv:2608.03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense s

arXiv:2608.01968v1 Announce Type: new Abstract: Transformer models are most often understood through what they do: their benchmark performance, generation quality, or behavior on downstream tasks. Yet

arXiv:2608.00004v1 Announce Type: new Abstract: Grading natural-language mathematical proofs is a recurring cost in evaluating math-reasoning systems, and frontier LLM judges are expensive. We ask whe

I really like to use this one SQL benchmark when testing new models. I had another post some time ago with my benchmarks, but I decided to post a new one because of how well Deepseek did. I like the b

arXiv:2608.01816v1 Announce Type: new Abstract: In this work we investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis of three models spanning three param

arXiv:2603.03320v2 Announce Type: replace Abstract: Effective communication often relies on aligning a message with an audience's narrative and worldview. Narrative shift involves transforming text to

arXiv:2608.01918v1 Announce Type: cross Abstract: Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable

If you missed today's K3 on Fireworks webinar, we've got you covered. We'll be partnering with @arizeai to chat more models on Thursday, August 6th. Sign up below! Next session, August 6 we'll be co l

arXiv:2608.02059v1 Announce Type: new Abstract: Recent advances in unified multimodal models have significantly improved text-guided image editing abilities. In particular, models such as Nano-Banana-

arXiv:2608.02091v1 Announce Type: new Abstract: A bfloat16 transformer can train normally for many steps and then collapse abruptly. Distinct low-precision errors can trigger the same failure, leaving

arXiv:2608.00979v1 Announce Type: cross Abstract: Large language models are increasingly used as synthetic research participants and are often validated by whether their marginal responses resemble hu

arXiv:2608.01678v1 Announce Type: cross Abstract: Existing skill generation methods largely rely on heuristics or pipeline-style consolidation, which must be specially designed for different evidence

Running fast is not enough, you need fast AND correct An excellent addition from @ArtificialAnlys to make sure that the flashy speed numbers are backed by 100% matching accuracy Announcing the Artific

arXiv:2608.02214v1 Announce Type: new Abstract: Visual AutoRegressive Modeling (VAR) has excelled in natural image generation via next-scale prediction, but its use on topology-structured data like hu

arXiv:2608.01388v1 Announce Type: cross Abstract: Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call sequenc

arXiv:2608.00582v1 Announce Type: new Abstract: Pretrained byte-level BPE tokenizers can segment underrepresented languages inefficiently. Replacing a tokenizer changes the meaning of nearly every tok

arXiv:2603.28568v2 Announce Type: replace Abstract: Vision-language models (VLMs) share visual-textual representations across zero-shot classification, image captioning, and visual question answering

arXiv:2607.29549v1 Announce Type: new Abstract: Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challen

🚨ASI/AGI is imminent fans don’t realize that they ALREADY lost the argument around Astra. My argument (spelled out in detail in my Substack today) was that Astra was unlikely to be the dramatic leap f

arXiv:2607.29064v1 Announce Type: cross Abstract: Police crash narratives contain information that may supplement structured crash databases, but manual review is labor-intensive and it remains unclea

Does anyone have an idea, when OpenAI will fix ChatGPT's glitched images? Since the 2.0 image generator was released, there is ugly glitches when you use generated image as a reference or just change

arXiv:2607.29310v1 Announce Type: new Abstract: Ambivalence and hesitancy (A/H) are subtle behavioural states that may be expressed through language, voice, facial activity, and other non-verbal cues.

arXiv:2607.28636v1 Announce Type: new Abstract: LLMs increasingly serve as automated judges, but their judgments remain vulnerable to cognitive biases. Existing mitigations mostly rely on prompt-drive

arXiv:2607.19338v2 Announce Type: replace Abstract: Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect an

arXiv:2607.28750v1 Announce Type: cross Abstract: As mobile applications grow in complexity, traditional End-to-End (E2E) testing frameworks struggle with UI volatility, maintenance overhead, and cros

even within math, frontier models are far from being general intelligences. and we still need people to assess which of their output are trustworthy and which are not. All frontier AI models (includin

arXiv:2607.29087v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitat

arXiv:2607.29196v1 Announce Type: new Abstract: Long-running multi-turn interactions with chatbots and agents are now common, and a correct response often depends on remembering earlier details, track

arXiv:2607.29274v1 Announce Type: cross Abstract: Claims that language models homogenise are usually measured against human judgements collected for the study, which makes the human side an artifact o

arXiv:2607.28979v1 Announce Type: new Abstract: Heterogeneous Large Language Model (LLM) systems increasingly rely on shared contexts, retrieved evidence, and multi-agent dialogue histories, yet their

arXiv:2607.29431v1 Announce Type: new Abstract: Large language models increasingly generate optimization models from natural language, but existing evaluation often reduces a generated model and its g

arXiv:2508.13187v5 Announce Type: replace-cross Abstract: Homelessness is a persistent social challenge, impacting millions worldwide. Over 876,000 people experiencing homelessness (PEH) were recorded

Has anyone followed nousresearch work on Hermes? I mean we are Q3 2026. We have some crazy models trickling down from HGX territory to multi gpu workstation. And we have nousresearch deploying the 0.2

arXiv:2607.29334v1 Announce Type: cross Abstract: Conversational AI developed by geopolitical rivals reaches citizens worldwide, raising concerns that it could sway public opinion or be rejected as fo

arXiv:2607.28887v1 Announce Type: cross Abstract: Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder t

arXiv:2607.29678v1 Announce Type: new Abstract: LLM serving systems cache prompt KV state, yet most front ends still re-tokenize the full request text on every call. The cost lands on coding agents, w

arXiv:2607.29287v1 Announce Type: cross Abstract: Multi-domain machine translation (MDMT) poses a unique challenge due to varying levels of linguistic complexity across domains. Inspired by human tran

arXiv:2607.28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect. We measure how often that treatment is

The June edition of my sponsors-only monthly newsletter is out. If you are a sponsor (or if you start a sponsorship now) you can access it here. This month: Accidental cyberattacks by OpenAl and Anthr

2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de

An internal version of Astra, @OpenAI’s next major model family, solved 10 major open problems in mathematics, quantum complexity, and theoretical computer science. We believe it will be a major step

**Kimi K3 is Moonshot AI’s 2.8‑trillion‑parameter open‑weight language model—the largest ever released—designed for frontier tasks such as long‑horizon coding and deep reasoning.** Its architecture us

Ten advances in mathematics and theoretical computer science A few days ago it was Anthropic discovering cryptographic weaknesses with Claude using Mythos Preview, spending 100,000 on tokens and with