Search: “codex”

arXiv:2610.04838v2 Announce Type: replace Abstract: As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupl

ik ik 'another harness D:'. so... i spent the last 6 months of my life building and ironing out every single detail and bug through almost every route with extensive testing across 3 machines, daily,

Hey everyone, Jovan from UkisAI (Swift Qwen) here! For those who don't know us, UkisAI is a small lab making tiny frontier LLMs, tools and datasets (+doing it open-source!). I'm one of the guys runnin

True You don't have to wait for Grok Bot to add Claude, OpenAI, etc. You can do it now. I did Just ask your Grok Bot to connect to your AI subscriptions. How it'll do it: • Opens a terminal on its own

OpenAI introduced interactive in‑chat tools that let users play games or run utility calculators—such as an interactive budget planner—directly within a conversation. The demonstration, released on Oc

GPT‑6 with Intelligent UI rolls out globally to Plus, Pro, Business, and Enterprise users today and will expand to Free and Go users starting tomorrow. GPT‑6 in ChatGPT is powered by GPT‑6 Sol for Plu

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

The real news here isn’t the result; it’s what we were not told. 1. AI once tried to be a science. Now we get stuff like the completely vague report from OpenAI below, and a lot of ignorant questions

arXiv:2610.05367v1 Announce Type: cross Abstract: Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verificati

let me introduce you to the langchain stack 1. langgraph gives you this level of control 2. traces give you the complete run lineage 3. version your skills and instructions in context hub 4 & 5. deepa

I built a Pi extension that implements Victor Taelin's OptChat recipe: instead of compacting, every message is logged and summarized into a binary tree. Each turn starts from a fresh context with a bo

A while ago, I posted here getting OSS-120B and GLM-4.6 playing full games of Civilization V. Since then, models have moved pretty far, and we wanted a better understanding about models' capabilities

I actually want personal operating systems optimized for co-working with AIs, including fine-grained ideas of security, easier ways to dynamically see & understand what AIs are doing, and independent

Blind A/B arena where AI agents build things in Blender and you vote on which result is better: https://render-arena.izolight.xyz Each agent gets a prompt that describes its environment and the rules,

arXiv:2610.02569v1 Announce Type: cross Abstract: Coding agents have become increasingly long-horizon, autonomous, reliant on general-purpose shell and maintain their own persistent memory for self-im

The Information: Sources: Meta and Microsoft are working to cut their employees' use of Claude; Meta employees using Claude Code have dropped to ~30K from ~60K earlier this year — Meta Platforms and M

We're expanding our approach to content provenance to include text in response to EU regulatory requirements, while recognizing the significant limitations of current text watermarking technology. Our

A tweet by Kristof (@CoastalFuturist) titled “How it feels to ask the Chinese ai models for help on something Claude won’t agree to” was posted at 1:30 AM on Oct 4, 2026. The post garnered 616.3 k vie

HuggingFace just closed a major gap in harness engineering! (the ultimate guide to multi-harness RL) the same open-weight model can perform well inside one harness, then lose accuracy or produce inval

Research: Qwen3.8 27B addition in words Colin Frasier posted on Bluesky about an experiment he ran over two years ago using GPT-4o to see how well it could 'compute the sum but return the answer in wo

Must-read paper from Meta on reliable auto-research agents. If you let coding agents run ML experiments, one silent bug like leaked eval data or a disconnected gradient can invalidate hours of trainin

arXiv:2610.00917v1 Announce Type: new Abstract: Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing

arXiv:2610.00912v1 Announce Type: new Abstract: Large language models can translate business descriptions into optimization models, but executable code may misrepresent constraints or objectives. A so

Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the

Super interesting paper from Meta Superintelligence Labs on controlling long agent runs. They use the same workers and same budget, and ProgramBench goes from 63.7% to 71.5% with GPT-5.5 when a dedica

The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guide to multi-harness RL, and it's one of

Hey everyone! I’ve been working on ASTRABOX: an arcade interface where you describe a game, the AI builds it, and you can ask for changes by voice while playing. Each game gets its own visuals and gam

babe, wake up. Hugging Face just dropped a new banger article about RL training coding agents on different harnesses. 1/ Excited to release The ultimate guide to multi-harness RL The same model behave

arXiv:2609.38912v1 Announce Type: new Abstract: Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting a

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:2609.38345v1 Announce Type: cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically as

arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compac

arXiv:2609.39551v1 Announce Type: new Abstract: Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experim

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

Madison Mills / Axios: Google rolls out Gemini 4 Argon to a small group of cybersecurity partners and says it outperforms GPT-6 Astra on certain coding and knowledge work benchmarks — Google is unveil

I built Image Studio, a local web app for Qwen-Image 2.1 on Apple Silicon. I had the model running on my Mac, but the only way to use it was the ComfyUI graph, and chaining edits meant wiring loaders,

i kinda wish dots was a standalone app and not part of chatgpt. as it stands, it feels like a product feature (e.g. GPTs) and not a big, exciting new release. i might understand why they did it though

arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that age

OpenAI launched Dots at DevDay. My thoughts. First, the good. Always-on is really really really what the market needed. It's why I find myself reaching for Instinct so often. I don’t have to think abo

arXiv:2609.37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing app

arXiv:2609.38147v1 Announce Type: new Abstract: As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control c

arXiv:2609.33807v1 Announce Type: new Abstract: How well can general-purpose multimodal models turn visual understanding and reasoning into embodied manipulation via executable code? We introduce Code

arXiv:2609.35515v1 Announce Type: cross Abstract: Scientific discovery requires not only recovering mathematical laws that describe observable behavior, but also identifying the mechanisms that genera

arXiv:2512.22318v3 Announce Type: replace Abstract: When do role-specific training counts improve knowledge-graph error ranking? We evaluate fifteen from-scratch predictors, nine development-selected

We've partnered with @OpenAI to bring the new Sign in with ChatGPT experience to Nous Portal. Log into Nous Portal with ChatGPT to use your plan in Hermes Agent, with full visibility and controls in C

Maxwell Zeff / Wall Street Journal: OpenAI scraps plans to publicly launch a model dubbed GPT-6.1 Astra, saying it didn't quite meet its safety bar; it had been targeting an October release — Model du