Coding
50 items tagged with this topic
Recent
How Oracle turns days of work into minutes with ChatGPT and Codex
Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.
Older
LegalOn halves Codex costs while maintaining development speed
LegalOn cut estimated daily Codex costs by 65% while maintaining development speed. It matched Astra, Sol, and Luna to tasks and managed budgets strategically.
Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve the…
Together Link: open models in the harness you already use. Start with one command today.
Together Link brings frontier open models like GLM 5.3 and Kimi K3 into the coding agent your team already uses, cutting model spend by over 50%.
[AINews] not much happened today
a quiet day.
[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing
yay small models
Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?
Kubernetes co-creators Craig McLuckie and Joe Beda aim to bring agent harnesses fully into the cloud.
The Spice Trader vs. the Tariffs
a section 301 update from the litigant
China, the FCC, and the Logic of Transceivers
The dependencies that a potential rule on optical transceivers misses
Day 3 (encore)/ We silently re-shipped codex cloud. It’s pretty good now https://t.co/Fau14sCke8
Day 3 (encore)/ We silently re-shipped codex cloud. It’s pretty good now https://t.co/Fau14sCke8
🚨NEW EXPERIMENT 🚨 Playground is an experimental gaming platform that lets you create your own…
🚨NEW EXPERIMENT 🚨 Playground is an experimental gaming platform that lets you create your own games with zero coding experience. If you can think it, you can play it. Go to https://t.co/fRUukpuoqM to learn more! Avail…
The compute needed for the stage of AI we’re about to enter is going to be insane. Personal age…
The compute needed for the stage of AI we’re about to enter is going to be insane. Personal agents, agent swarms defending enterprises, agents that review all of our code for security issues, agents that process nearly…
Remember that coding is a means to an end. The end matters more than the means
Remember that coding is a means to an end. The end matters more than the means
[AINews] Reflection Beam - 501B-A23B American Open Model
A small win for US open source
[AINews] not much happened today
a quiet day.
Building China’s Two Starlinks
is two better than one?
what is your default/workhorse coding agent today, Oct 2026?
what is your default/workhorse coding agent today, Oct 2026?
working at a higher level of abstraction has always required understanding the lower level ones…
working at a higher level of abstraction has always required understanding the lower level ones, I don't think coding agents changes this
Cyber will be one of the most defining domains for AI in the coming years, and a huge area of f…
Cyber will be one of the most defining domains for AI in the coming years, and a huge area of focus for most enterprises. AI is going to now create a whole new level of work for security dealing with the increase of vib…
I hooked up our team claw to X to trigger work faster. Unassigned sessions are for anyone to gr…
I hooked up our team claw to X to trigger work faster. Unassigned sessions are for anyone to grab. Our agent looks who worked on the related code last and pings people on the server. Whole thing was a prompt and team se…
I have had the distinct pleasure of collaborating with @keithmadams for almost 15 years. We wor…
I have had the distinct pleasure of collaborating with @keithmadams for almost 15 years. We worked together at Facebook and now jam on startups together. It is such an interesting time to explore what it truly means to…
Inside-Out AI: Rebuilding Airbnb Behind the Scenes and Across the Guest Experience
After leading Meta’s Llama models, Ahmad Al-Dahle is now transforming Airbnb with AI — from how its teams develop products to how it serves guests.
[AINews] Pi 1.0, Pi Durable, and AIE NYC
the minimalist harness goes stable... and TypeScript!
a big advantage of doing planning like this is that it’s a lot more token efficient compared to…
a big advantage of doing planning like this is that it’s a lot more token efficient compared to raw HTML- the model doesn’t need to remake the components or logic to do common things like state machines, diagrams, code…
Introducing gdp-ts: Ghosts of Departed Proofs for TypeScript. gdp-ts is a library, linter and A…
Introducing gdp-ts: Ghosts of Departed Proofs for TypeScript. gdp-ts is a library, linter and AI skill for safer API design. Under this contract, sensitive functions require 'proofs' that the caller performed an authori…
Harnesses from labs have an incentive to burn tokens, which means harnesses from startups have…
Harnesses from labs have an incentive to burn tokens, which means harnesses from startups have a real utility, like how Grep can automatically swap token burn into deterministic tested code that is repeatable just by ob…
Academia is for Ambition — Alex Zhang, MIT
We catch up with RLM first author Alex Zhang, MIT PhD, on Jev, PhD masxing, and the future of harnesses.
Chatham scales its capital markets expertise with OpenAI
Chatham Financial uses Codex and GPT-5.6 to build technology and redesign workflows, cutting trade validation from 30 minutes to under 4.
Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and rel…
Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and relevant for most codex/work users or ship a full reset. Let the improvements begin. https://t.co/0oFXZ7LY5T
I'm glad OpenAI is focusing on simplifying ChatGPT because it has become a mess (sorry). Here's…
I'm glad OpenAI is focusing on simplifying ChatGPT because it has become a mess (sorry). Here's a clip from my dots review about this. What I'd simplify: 1. Work vs. Codex 2. Spaces vs. Pages vs. Sites 3. The model and…
DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification…
DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification (carcinization, technically 🦀) for a while. One of the first projects we migrated was Turborepo, from Go to Rust¹. The mig…
[AINews] Gemini 4 Argon: GDM’s answer to Astra/Fable, with 1M output
... but you can’t try it yet unless you are “government users and trusted cyber defenders in the Fairwind Program”
Import AI 474: Platonic mindspace; TPUs in space; Zhipu starts an outer RSI loop
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. Subscribe now Are minds patterns from a Platonic space, with bodies and…
Security will become a larger and larger function in software companies. Security is verificati…
Security will become a larger and larger function in software companies. Security is verification engineering (eg: “my code is probably memory-safe”), as well as capital allocation (“what surface should I throw most tok…
AI agent adoption is still very bimodal right now. You have coding and coding adjacent tasks wh…
AI agent adoption is still very bimodal right now. You have coding and coding adjacent tasks which have taken off, and then everything else. And even within coding, you have a very wide continuum of adoption patterns, w…
How will the world change if coding agents get 10x better?
How will the world change if coding agents get 10x better?
Fortunately our future models will be much better at code deletion and simplification. Just in…
Fortunately our future models will be much better at code deletion and simplification. Just in time
Seeing some reports that the Pro 500 didn’t get the reset as expected earlier. Investigating an…
Seeing some reports that the Pro 500 didn’t get the reset as expected earlier. Investigating and will make up for it
"You should know" is a great way of staying on top of what's possible with Claude and also a gr…
"You should know" is a great way of staying on top of what's possible with Claude and also a great example of the kind of things mods enable. You can really make Claude Code yours. https://t.co/En0OhotxQL
If you are a home automation nerd, this is a fun prompt to try on Claude Code / Codex (edit bas…
If you are a home automation nerd, this is a fun prompt to try on Claude Code / Codex (edit based on your own setup): "Can you sniff network packets in our house and see what else can we automate? For context: We have a…
Here's the app. One thing I've been liking is to ask models to 'teach me back' what they did¹ b…
Here's the app. One thing I've been liking is to ask models to 'teach me back' what they did¹ by including "quines". Quines² are programs that output their own source code. So, in this demo you can reveal step by step t…
Frontend code is probably the most expressive medium for storytelling of our times yet many peo…
Frontend code is probably the most expressive medium for storytelling of our times yet many people are just using it to make SaaS landing pages
Why AI Agents Cheat | Eric Ho (Goodfire)
Speaker 1 | 00:00 - 00:20 A lot of people who aren't in the AI field are very surprised to realize that even the, you know, smartest researchers and scientists at the frontier don't understand their creations. It's like, oh, I thought we h…
How we contain Claude across products
Twelve months ago, we'd have rejected out of hand the idea of granting Claude access sufficient to take down an internal Anthropic service. Today that level of access is routine, and Anthropic developers are more productive for it. Th…
An update on recent Claude Code quality reports
Over the past month, we’ve been looking into reports that Claude’s responses have worsened for some users. We’ve traced these reports to three separate changes that affected Claude Code, the Claude Agent SDK, and Claude Cowork. The API was…
Scaling Managed Agents: Decoupling the brain from the hands
Get started with Claude Managed Agents by following our docs . A running topic on the Engineering Blog is how to build effective agents and design harnesses for long-running work . A common thread across this work is that harnesses encode…
Why Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 Week
Our DevDay coverage - the first pod on the DevDay lineup - dives in with the leaders of OpenAI’s CUA team and API platform.
Helping small businesses put AI to work
OpenAI is partnering with America’s SBDC to expand hands-on AI training and local support for small businesses, alongside a new report on how small teams are using AI.