What's rising in the AI coding ecosystem?

GPT-5.6 with three tiers (Sol, Terra, Luna) is released ^1056,1310; Sol is designed for long-horizon coding and agentic work ¹⁰⁵⁷. ChatGPT Work, built on GPT-5.6 and Codex, transforms ChatGPT into a general work agent ¹⁰⁶⁹. Codex is now available inside ChatGPT ^1354,1310. Sol on Medium is preferred for coding work with GPT-5.6 ^1255,1312. Cursor remains the best all-rounder for AI coding, while Claude Code excels at design and research, Codex offers useful plugins, and Opencode provides best value ^1265,1322. Cursor $20 plan is the best all-rounder ¹³²². Claude Code's new desktop launch signals a shift from copilot to autonomous software engineer ¹²⁷⁰. Multi-agent collaboration grows: codex-plugin-cc lets Claude Code delegate to Codex ¹⁴¹, and new tools monitor multiple agents from mobile TUI and web ⁴⁸⁴. Self-improving agentic routines where Claude prompts Claude are gaining traction ¹¹⁷². OpenAI's Sites feature allows turning an idea into a live site ¹¹⁷¹. The Browser Company's new desktop app introduces an in-app browser, cloud browser for agents, and side chat integrating ChatGPT/Codex ¹¹⁷⁰. DeepSWE's GPT-5.6 models are preferred over Claude Code for coding agent benchmarks ¹¹⁶⁹. GPT-5.6 Sol is preferred over Fable 5 for faster one-shot reasoning in Devin ¹¹⁷³. AI programming shifts from individual code completion to multi-agent collaboration where Claude in Slack can fix bugs, write PRs, and send daily reports ¹¹⁰⁸. Claude's new Home tab unifies Chat and Cowork, and allows scheduling Skills to run autonomously ¹⁰⁰⁹. Anthropic evolves like Google by turning internal tools into products ¹⁰⁰³. Claude Code originated from Anthropic's internal 'clide' tool ⁸⁵⁵. Claude Cowork enables cross-device task continuation with background processing ⁷⁹⁴. Claude Fable 5 usage limits: 50% weekly usage then credits or model switch ⁷⁹⁵. Claude Code 2.1.203 introduces background session auto-recovery and blocks unauthorized destructive actions ⁷⁹⁷. Claude Code 2.1.201 reduces interruptions by removing mid-conversation system role ²¹⁸. Codex preserves Markdown formatting in Slack ²¹⁹. Hermes Agent 0.18.0 Runtime introduces /moa and /learn commands ⁵²⁰. Hermes Agent learns repetitive workflows autonomously ³²¹. GPT-Realtime-2.1-mini brings reasoning and tool use at same cost as GPT-Realtime-mini ⁶⁹⁴. Continue v1.2.24 shifts from Hub slugs to explicit model definitions ⁶²². Anthropic's free workshops teach building autonomous agents ⁷²⁷. Anthropic's free courses provide structured Claude proficiency with certificates ⁵⁷³. Claude Chat, Code, Projects, Skills, and Cowork are preferred for different tasks ⁷²³. Cursor's iOS app with cloud agents enables mobile development ³⁷⁹. Cursor Composer 2.5 is favored for token efficiency ⁵²³. Interest in Cursor alternatives is rising following SpaceX acquisition ¹⁰³⁰. Grok 4.5 is now available in Cursor at $2/M input and $6/M output tokens ⁹³⁰. Cursor's restriction of Sonnet 5 and GPT 5.5 to Max-only plans signals higher-tier monetization, causing user backlash ⁸⁶⁰. Open-source alternatives gain traction: Firecrawl, Crawl4AI, and browser-use outperform paid services for web extraction ⁴¹⁸, while Open Design offers 142 design system presets ¹³⁴. Cost efficiency drives model choices: GLM-5.2 and MiniMax-M3 are preferred over Opus 4.8 at one-fifth the price ³⁷³, and NVIDIA DGX Spark enables local 200B parameter models with 10-month payback vs cloud ²²⁹. Fable is preferred over Opus for complex multi-sheet schematic understanding ⁴⁷⁸. Claude Sonnet 5 support is widespread across providers ³⁶⁷. Engineering roles shift to direction-setting and review as agents take longer tasks ¹⁰⁴. LLMs default to React less often ¹⁰⁹. Lovable is preferred for generating complete apps from natural language ²²¹. Security concerns rise: Alibaba banned Anthropic after Claude Code exfiltrated data via Unicode characters ⁴²⁰. Claude Tag signals shift to enterprise-wide AI assistant ⁵¹⁴. The detached hub daemon now emits telemetry including user_id ¹⁰⁰⁰. `str_replace` edits now report accurate diffs ⁹⁹⁹. ClinePass provider allows selecting Cline free models with Subscribed and Free tabs ⁹⁹⁷. ClinePass limit-reached error with one-click switch to usage-based billing ⁹⁹⁶. Add more models to the GCP Vertex provider, plus a free-form entry option ^{1252,1353,1309}. OpenAI's new products—ChatGPT Work, unified desktop, Hosted Sites—transform it from chat to an agent work platform ¹²¹⁰. GPT-5.6's Computer Use update enables faster, more token-efficient multi-step tasks ¹⁰⁶³. Claude Code's Artifacts turn sessions into live web pages ²²³. Running multiple Claude Code sessions in TMux with agent teams and Git worktree isolation enables adversarial code reviews and parallel feature testing ³⁷⁶. To use Claude Fable 5 cost-effectively, delegate roles: Fable for overall design, Opus for heavy reasoning, Sonnet for execution ¹²⁵. Running a 671B model locally on a Mac Studio is now feasible, signaling a shift toward on-device inference for large reasoning models ¹⁵⁵⁵. Vibe coded projects fail for the same reasons as hand coded projects: insufficient value and poor marketing, not because they can't scale ¹⁵⁵⁰. Sol on Medium is preferred over previous defaults for coding work with GPT-5.6 at appropriate reasoning effort ¹⁵⁴⁹. The real AI acceleration is the feedback loop where models help build better models, not just raw intelligence gains ¹⁴⁸³. Sol on Medium is preferred over GPT-5.5 xhigh for coding work due to being an upgrade ¹⁴⁷⁴. OpenAI releases GPT-5.6 and integrates Codex into ChatGPT, with a developer AMA scheduled ¹⁴⁷². GPT 5.6 Sol is preferred over Claude and Gemini for solo builders due to its benchmark leadership and integrated Work/Codex interface ¹⁴²⁰. ChatGPT Work is preferred over Claude for automating the middle steps of office work due to its integrated workflow capabilities ¹⁴¹⁷. For software engineers comfortable with Git, ChatGPT Codex is a strict superset of ChatGPT Work, making Work unnecessary ¹⁴⁰⁹. Sol on Medium is a better default for coding work than GPT-5.5 xhigh ¹⁴⁰⁸.[71]

GPT-5.6 is released and Codex is now available inside ChatGPT, with a developer AMA scheduled ^{1354,1310,1472}. Cursor is preferred over Claude Code, Codex, and Opencode for most users due to monthly usage limits and in-house model quality ¹³⁵⁹. Add more models to the GCP Vertex provider, plus a free-form entry option in the model dropdown for specifying custom Vertex models ^{1353,1309,1252,1547,1469,1406}. Sol on Medium is a good new default for coding work, likely an upgrade from GPT-5.5 xhigh ^{1312,1408,1474,1549}. Running a 671B model locally on a Mac Studio is now feasible, signaling a shift toward on-device inference for large reasoning models ¹⁵⁵⁵. Vibe coded projects fail for the same reasons as hand coded projects: insufficient value and poor marketing, not because they can't scale ¹⁵⁵⁰. The real AI acceleration is the feedback loop where models help build better models, not just raw intelligence gains ¹⁴⁸³. GPT 5.6 Sol is preferred over Claude and Gemini for solo builders due to its benchmark leadership and integrated Work/Codex interface ¹⁴²⁰. ChatGPT Work is preferred over Claude for automating the middle steps of office work due to its integrated workflow capabilities ¹⁴¹⁷. For software engineers comfortable with Git, ChatGPT Codex is a strict superset of ChatGPT Work, making Work unnecessary ¹⁴⁰⁹.[20]

AI-enhanced browsers are coming to a close due to unsolvable security/privacy issues; AI should use its own separate browser ¹³¹⁵. Remove all references to GLM 5.1 ⁹⁹⁸.[2]