My obituary for programming Jeremy Scheff poignantly captures the key loss caused by coding agents for career programmers who enjoyed the puzzle of developing code: Programming turned into one of the greatest jobs you could imagine. You got paid to work on tricky little logic puzzles. The trickier the puzzle, the more you got paid.
Learn how to move an agent session from the GitHub Copilot app into VS Code without losing the conversation, code changes, or working context.
A new benchmark called Taste-Bench tests how well AI agents make strategic choices during long-running tasks. Even the best model, GPT-5.6 Sol, picks the right path on just under 60 percent of simple binary questions. Thinking longer doesn't help.
Deepseek has released V4.1-Flash-1017 as an open-weight model that posts better benchmarks, finishes tasks faster, and produces shorter outputs than its predecessor. The company is also opening up its internal search engine through new Search and Fetch APIs at $0.75 per 1,000 calls. API users in tools like Claude Code and Codex get free access for now.
Anant Kumar builds tools to compare loan valuations and analyze credit agreements, using Codex for code review and faster follow-ups.
Addy Osmani, Morgan Westlee Lunt and Qing Wang describe how the Claude Code team does code review: instead of treating "did a human read the code?" as the test, they ask "what could go wrong with this change, and which check should catch it". Review has thus moved from a gate at the end of a PR to something continuous, with most changes reviewed and fixed by Claude at least once before a human looks.
Two engineers shipped Stack Overflow for Agents in a few weeks with Codex, and its ChatGPT plugin helped drive up to 10× growth in agent creation.
Reflection AI's Beam is an open-weight model for agentic coding and long-horizon tasks. This post shows how to deploy Beam on AWS: start with an Amazon SageMaker JumpStart real-time endpoint, or use Amazon SageMaker HyperPod Inference with JumpStart, SGLang, or vLLM for Kubernetes-native control over distributed GPU infrastructure.
Beam by Reflection is out on Hugging Face! It is the first model from the new US lab, Reflection, and it’s open! It's a mixture-of-experts (MoEs) model with 501B parameters (23B active per token), supports text as input, has a context window of 1M tokens, and is released under the Apache 2.0 license.
Replit CEO Amjad Masad envisions a future of “self-driving companies,” where AI agents handle day-to-day tasks and people focus on higher-level decisions.
Research: sparqlite: SPARQL 1.1 inside SQLite, written in Rust This research task is really an experiment in running Claude Code for web in "Ultracode" mode, as described in Orchestrate subagents at scale with dynamic workflows in the Claude Code documentation.
Tool: Chirp Pong Another game experiment - I wanted to see if it was feasible to have a two player game on two separate phones running in static HTML where the networking code uses chirps sent via the microphone. It seems to work!
Meta and Apple have teamed up for the launch of the social media giant's newest model, Muse Spark Open, which will run locally on Apple silicon.
Muse Spark Open, Meta's coding-optimized open-weight model, is now available in Amazon SageMaker JumpStart. Deploy it to a SageMaker AI endpoint in your own AWS account using SageMaker Studio or the SageMaker Python SDK, and run your first inference request.
Tool: Tree Appreciator Another game experiment with Claude. This one used the default Claude iPhone app (chat mode, not Claude Code mode) where I prompted Claude Opus 5.5 Max with: Build a three js game called "Tree appreciator" - it shows you two algorithmically generated trees and the game mechanics is about appreciating the differences between them.
But the new "Preview" app "will have some bugs," Epic warns.
Redesigning source control at Anthropic Interesting piece from Anthropic describing why and how they built their own custom alternative to Git, based on the dramatic increase in rate of changes to their code after the past six months. In May 2026, Anthropic averaged around 2,500 code changes merged per day; as of September, we merged over 30,000 per day.
Google is making Gemini 4 Argon available worldwide through its API, the Gemini app, and Google Antigravity. The frontier model is aggressively priced but trails Anthropic's Claude Opus 5.5 and Meta's Muse Wonder Full in independent benchmarks. Internally, Google says Argon already cut coding tasks from months to weeks.
Gemini 4 Argon is now globally available today for developers and enterprises via the API in AI Studio and Gemini platform, for Google AI Ultra subscribers in Google Antigravity, and Google AI Ultra and Pro subscribers in the Gemini app and AI Mode in Search.
Epic Games plans to use AI to generate code and art for an unannounced Disney game, which is now delayed from its original March release window, according to a report from Bloomberg. The project's developers have been given an "AI-first" mandate directing them to use tools like Anthropic's Claude more to finish the game.
Release: web-edit 0.1a0 I was working on a project from my phone using Codex Remote when I found myself wanting to edit a credentials file without round-tripping those credentials through the LLM itself. So... I had Codex and GPT-6 Astra Extra High build this Python web app which provides a web UI for viewing and editing files in a folder.
Geoffrey Huntley proposes using a pre-commit hook to inspect the git diff, reject commits that call observability modules directly and bypass the diagnostics module, and inject a prompt telling the AI agent to use the diagnostics library instead. He argues that updating AGENTS.md alone still leaves a delta and will drift, whereas this approach made the agent's performance instantly ten out of ten.
Meta's new Muse Wonder models rank in the top three on six out of ten benchmarks, with the biggest gains in agentic tasks. But the cost per task has nearly tripled.
Learn how to add custom instructions and skills to your repository, use custom agents, and connect MCP servers like Playwright.
Andrej Karpathy, co-founder of OpenAI and now at Anthropic, sees a widening knowledge gap in AI. About 75 percent of the world's population has barely touched LLMs. Roughly 5,000 people, meanwhile, have access to internal frontier systems whose agent swarms do work that would take top experts years. The public, at best, sees a weird chatbot.
Gemini 4 Argon isn't even widely available yet, and rumors about a more powerful version codenamed Carbon are already making the rounds. According to Business Insider, one employee compared Carbon's coding abilities to Anthropic's Opus 5.5. Meanwhile, new modes are showing up in the Gemini app and AI Studio, suggesting Google is gearing up for the broader Gemini 4 launch.
Study finds coding efficiency gains get "absorbed" by human review "bottleneck."
Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.
I shipped a new feature for my blog today: the Newsletters page, which offers an index of all of the newsletters I've sent out, both my free weekly Substack and my monthly sponsors-only updates. I built the feature almost entirely using my voice, chatting away to my laptop while I cooked dinner.
LegalOn cut estimated daily Codex costs by 65% while maintaining development speed. It matched Astra, Sol, and Luna to tasks and managed budgets strategically.
Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.
Anthropic shipped Claude Haiku 5.5, its first Haiku-tier update in about a year. It is priced to match OpenAI’s GPT-6 Luna, and Anthropic cut prices on Sonnet 5.5 and its subscription plans the same day.
Anthropic's new Claude Haiku 5.5 crushes its predecessor in benchmarks, jumping from 15.7 to 72.4 percent on the OSWorld computer use test. Token prices drop by up to 90 percent, though a new tokenizer eats into some of those savings by consuming more tokens per task.
Developers aren’t becoming more careless; they’re being outpaced. The tools that let developers create more software should also take on more of the work of protecting it.
Reflection has released Beam, its first open-weight model. The mixture-of-experts system activates just 23 billion of its 501 billion parameters per token and aims to match GLM 5.2 on coding and reasoning while using three to four times less compute. The strategy against Chinese open-weight rivals like Deepseek and Qwen is efficiency over raw performance.
Today, we're launching a public preview of Mistral Large 4. Unofficially ML4, very officially: le Chonk. ML4 pushes the frontier of open-weight performance. You can try the preview API today on Mistral Studio. Weights drop end of this month.
Reflection announced Beam, a text-only 501B-total / 23B-active MoE for coding, agentic and scientific work. It was trained from scratch, and full weights under Apache 2.0 are due this month.
GLM 5.3 from Z.ai is now available on Amazon Bedrock: a 753B-parameter mixture-of-experts model built for coding and long-horizon agentic tasks. Learn how to invoke it with the OpenAI-compatible APIs, cut cost and latency with prompt caching, and run an authorized security test with the open-source Strix agent.
Amazon SageMaker optimized generative AI inference introduces the aws-ai-ml skill through the Agent Toolkit for AWS, giving coding agents like Kiro, Claude Code, and Codex deep expertise in inference optimization and benchmarking. Describe what you want, and your agent generates executable SageMaker Python SDK v3 code to benchmark, recommend, and compare deployments.
Anthropic Claude Opus 5.5 and Claude Sonnet 5.5 are available on Amazon Bedrock in the AWS GovCloud (US) Regions. Learn how to use them with Claude Code, Anthropic's agentic coding tool, for compliance-aligned, AI-assisted development on regulated and ITAR workloads.