Search: “gpt”

tl;dr: running Qwen3.8FN Q4 locally is cheaper for me than every cloud model except Luna and the newer Haiku at mid-peak and peak electricity pricing where I live, and becomes the absolute cheapest mo

arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ

arXiv:2610.13632v1 Announce Type: new Abstract: Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized re

arXiv:2610.12610v1 Announce Type: cross Abstract: Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communiti

arXiv:2506.09956v2 Announce Type: replace-cross Abstract: Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the pra

arXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still

We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud

AI solved open mathematical problems. But the biggest surprise came afterwards. A team at Google DeepMind has used AI to resolve 9 open Erdős problems, including questions that had remained unsolved f

We see a control gap between what artificial intelligence can do and what the evidence supports trusting it to do. A great demo doesn’t prove that a system will stay within the limits of an intended d

Banger paper from Meta Superintelligence Labs on user simulators for agent training. Agent RL setups usually let an assistant LLM play the user, so the simulated user is too cooperative and too explic

arXiv:2603.23406v3 Announce Type: replace Abstract: Generative agent societies simulate people with assigned roles, preferences and relationships. As agents exchange arguments and choose partners, the

arXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair s

arXiv:2610.10827v1 Announce Type: cross Abstract: Corrective feedback is among the best-evidenced drivers of second-language acquisition, yet corrections delivered during lessons rarely accumulate int

arXiv:2610.11402v1 Announce Type: new Abstract: GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making p

Anthropic: Anthropic launches OSS Scanner, a free opt-in vulnerability scanner for critical open-source projects; its AI-generated reports are sent without human review — We're launching OSS Scanner,

AI costs don’t always scale predictably with traffic. A retry loop, oversized context window, or unnecessarily expensive model can make a small number of traces disproportionately expensive. The post

arXiv:2610.09344v1 Announce Type: new Abstract: General image editors are asked to make a photo look as if it were taken at f/1.4, yet it is rarely checked whether the blur they add follows thin-lens

arXiv:2609.35308v2 Announce Type: replace Abstract: Large language models treat conversation history as unverified context, so false premises injected into prior turns can be adopted as fact, a failur

arXiv:2610.10092v1 Announce Type: new Abstract: For better or worse, LLMs are by now used routinely for scientific writing.footnote{This paper is no exception; we did use AI to assist with writing som

The other week I posted about Jev vs. Kev compared and since then, OpenAI released the decisions endpoint, Cloudflare released Clef and many here asked about Laya as well. This time we compared six po

arXiv:2610.09079v1 Announce Type: cross Abstract: Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete re

arXiv:2505.12224v5 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations

arXiv:2610.04188v2 Announce Type: replace Abstract: Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In t

arXiv:2610.07518v1 Announce Type: cross Abstract: Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of a

As previously promised, here's Anthropic's new fast, low cost model: Introducing Claude Haiku 5.5. The previous Haiku, 4.5, was very much showing its age. It came out almost a year ago, and was priced

Introducing River Recipes: our open-source initiative for turning promising research into vetted, reproducible training recipes. Our first recipe tackles text-to-SQL, where our trained open models bea

arXiv:2610.08095v1 Announce Type: new Abstract: Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfam

Some early first-hand accounts of encountering a narrow superhuman intelligence as mathematicians grapple with the hundreds of big AI proofs released by OpenAI. Problems solved in inhuman ways that ma

arXiv:2412.10510v5 Announce Type: replace Abstract: The proliferation of disinformation demands reliable and scalable fact-checking solutions. We present Dynamic Evidence-based FAct-checking with Mult

arXiv:2312.01886v4 Announce Type: replace Abstract: Large vision-language models (LVLMs) have demonstrated their incredible capability in visual question answering. However, this rich visual interacti

Introducing GeoGuess Bench! A benchmark to measure how good AI models are at playing GeoGuessr. We gave each model 210 photos from around the world, asked it to predict where each photo was taken, and

Like Jev, I believe RL will unlock several more like this, slashing the cost of critical agent operations. flow-1 is competitive in performance, but a huge cost-saver for finding failures in agent tra

Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I

arXiv:2610.04976v1 Announce Type: new Abstract: We evaluate language models' capability to generate novel research ideas through the lens of compression. We aim to lower-bound the potentially tiny pro

For the last few weeks most of my coding has been done locally with Qwen3.8-Flash-Next, so I gave it and Opus 5.5 the same high complexity feature to build on LlamaStash (a complex and large Rust proj

arXiv:2610.04128v1 Announce Type: cross Abstract: Split learning lets a client train a language model on a server without sending its text. The client runs the first layers itself and sends the server

arXiv:2610.05492v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong potential as generalist robot policies, but adapting them to unseen tasks often requires costly pa

arXiv:2610.02664v1 Announce Type: new Abstract: Long-horizon agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their exte

arXiv:2610.03226v1 Announce Type: cross Abstract: GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but runtime alone does not reveal ho

arXiv:2610.02455v1 Announce Type: cross Abstract: Multi-party financial chatrooms are vital for sales-and-trading professionals, but their complexity makes manual recovery of missed trades infeasible:

See how Arize uses Harbor and Phoenix to benchmark AI agents, MCP servers, skills, and CLIs in reproducible sandboxes, then inspect traces and annotations. The post How we benchmark AI agents and tool

arXiv:2610.02788v1 Announce Type: new Abstract: Transferring robotic skills from simulation to reality requires task knowledge that remains usable across differences in perception, dynamics, and embod

Automated lint: 19 errors, 64915 warnings, 3 info

I've come up with a meta-prompt for generating YuE2 prompts that seems to work pretty well. Copy-paste into an LLM (it should have internet searching capabilities, I mostly just use ChatGPT). Just to

Hey everyone, I’ve been working on a game called Anyworld. It’s a browser-based multiplayer (single player also supported) text adventure inspired by the early days of AI Dungeon, especially its brows

arXiv:2610.01564v1 Announce Type: cross Abstract: LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowin