Alibaba tests how far an autonomous AI developer can go
Alibaba claims to have reached a new milestone in agentic software development with Qwen3.8-Max, its new flagship model launched in early August 2026. In an internal test, the model reportedly worked fully autonomously for around 16 days on a real software engineering project, without human intervention during its execution.¹ The experiment was not simply about generating a few functions from a prompt: Qwen3.8-Max had to start from an empty environment, organise its work, develop the project, run its own tests, detect problems and keep iterating over an exceptionally long period for an AI agent. Alibaba presents this demonstration as an illustration of the model’s ability to carry out so-called “long-horizon” tasks, which require keeping hold of an objective and coordinating numerous actions over several days.
265 commits and 127 pull requests produced by the agent
The announced result gives an idea of the scale of the experiment. As of 30 July 2026, after around 16 days of autonomous operation, the repository used for the test had 265 commits, 127 pull requests and 151 issues.² The model was working on “oh-my-cli”, an agentic framework able to evolve based on requests received, community feedback and its own tests. Its workflow included turning requirements into issues, assigning tasks, generating code, running unit and end-to-end tests, then fixing the defects detected. Alibaba has made the project publicly available on GitHub, allowing part of the traces produced during the experiment to be examined.
The real feat lies in the duration
Coding assistants have been able to generate code, explain a function or fix an error for several years, but sustaining a task over several days is a far more complex problem. An agent must keep the original objective in mind, understand the state of the project after hundreds of actions, detect its own mistakes and resume its work without constantly starting from scratch. Qwen3.8-Max relies in particular on a Mixture-of-Experts architecture with 2.4 trillion parameters, 95 billion of which are activated, as well as a context window of up to one million tokens.³ Above all, Alibaba highlights a closed-loop process in which the agent plans, executes, checks and then corrects its work, a mechanism that is gradually bringing these systems closer to a genuine autonomous software engineering process.
Qwen no longer just wants to write code
This demonstration is part of a broader market trend. Cursor, Claude Code, Codex and GitHub Copilot have gradually moved AI tools from simple autocompletion towards agents capable of exploring a repository, editing several files and running commands. Alibaba now wants to push this logic much further by making the length of autonomy a performance criterion. Qwen3.8-Max was also tested on reproducing a research paper: according to the Qwen team, the model worked for around five days, produced nearly 7,600 lines of code and ran 33 GPU training runs before proposing its own improvements.² These results come from Alibaba’s own evaluations and should therefore be distinguished from independent benchmarks, but they clearly show the direction AI labs are taking.
The developer becomes the supervisor of long-running agents
If agents genuinely become capable of working for several days on the same project, Web Programming and Management could undergo a major transformation. Developers do not disappear from the process: their role shifts towards defining the architecture, setting objectives, reviewing code, testing, security and validating the decisions taken by the agent. Knowing how to program will remain essential to spot a poor implementation or understand the consequences of a change, but a new skill is gradually being added: knowing how to delegate complex tasks to agents, monitor their progress and take back control when their decisions stray from the project’s requirements. A developer’s value could thus depend less and less on the number of lines written by hand and more on their ability to orchestrate and control systems capable of producing code at scale.
The 16 days still have to stand up to real-world conditions
Alibaba’s demonstration should nevertheless be treated with caution. The 16 days correspond to an experiment organised and documented by the model’s provider, and this duration is not enough to prove that an agent can replace a development team on any professional project. Key questions remain about the quality of the code produced, its maintainability, security, the real cost of such a long run and the system’s ability to work in far more complex environments. Industry observers point out that performance deserves to be assessed beyond the number of days of autonomy alone.⁴ The real breakthrough will come when these agents can maintain this level of autonomy in enterprise projects subject to production, security and human collaboration constraints.
From copilot to agentic developer
Above all, Qwen3.8-Max shows how fast AI-assisted development is evolving. After copilots able to suggest the next line, then agents able to modify an entire project, the industry is now experimenting with systems that can pursue an objective for several days. If this autonomy becomes reliable enough for production use, the change will be profound: the challenge will no longer simply be asking an AI to code a feature, but entrusting it with a complete assignment, letting it work and then evaluating the result. The 16 days claimed by Alibaba are therefore less a definitive proof of autonomy than a particularly strong signal of the direction software development is taking.
360° IT News — decoding technology to understand the jobs of tomorrow.
Further reading
Programming environments are also evolving towards agents able to take on a growing share of development. Read our article “ZCode wants to challenge Cursor and Claude Code: China enters the AI coding battle”, on Z.ai’s arrival in the market for agentic development environments.
References
1. Alibaba Group. (2026). Alibaba Unveils Qwen3.8-Max: Its Largest and Most Capable Flagship Model to Date.
https://www.alibabagroup.com
2. Qwen Team. (2026). Qwen3.8-Max: A New Bar for Coding and Cowork.
https://qwen.ai
3. Alibaba Cloud. (2026). Qwen3.8-Max Model Information.
https://www.alibabacloud.com
4. Computerworld. (2026). Alibaba takes aim at OpenAI and Anthropic with Qwen3.8-Max launch.
https://www.computerworld.com
Data centre boom: Legrand goes on the offensive in China and the UK
Data centres are becoming the heart of the global digital economy Legrand is stepping up its investments in China and the United Kingdom to strengthen its presence in the data centre sector, which has become critical infrastructure for the digital economy. This...
GPT-5.4-Cyber: OpenAI responds to Claude Mythos in the AI cybersecurity battle
A new front line in the artificial intelligence war On 14 April 2026, OpenAI launched GPT-5.4-Cyber, a model specialising in cybersecurity, just days after Anthropic announced Claude Mythos. This timing is no coincidence: it marks an acceleration in the competition...
Claude Mythos: beyond the buzz, what are the real stakes for IT security?
An AI that promises to transform cybersecurity With Claude Mythos, Anthropic is showcasing a new generation of artificial intelligence able to analyse, detect and anticipate cybersecurity threats. At a time when cyberattacks are soaring, with more than 2,200 attacks a...
Microsoft reinvents development with AI agents in VS Code
Software development enters the age of agents Microsoft is taking a new step by integrating artificial intelligence agents into Visual Studio Code, with a beta version available via the Insiders channel. This development comes at a time when VS Code is used by more...
In the cloud era, enterprise networks are changing standards
The network is no longer just support: it is becoming a driver of performance For a long time, the enterprise network was regarded as a simple technical infrastructure, often invisible as long as it worked. But with the explosion of the cloud, SaaS applications and...
Windows 11: Microsoft wants to speed up user testing with Insider
Software testing becomes a lever for innovation Microsoft is overhauling its Windows Insider programme, which now brings together more than 10 million testers worldwide, to simplify access to experimental versions of Windows 11 and speed up user feedback. In an...
51,600 satellites: Jeff Bezos steps up the battle for the global internet
News in brief With Project Kuiper, Jeff Bezos is committing Amazon to a major transformation of the world’s internet infrastructure by deploying tens of thousands of satellites in low Earth orbit. The goal is not limited to connecting isolated areas, but to building a...
PepsiCo automates its logistics: a turning point for smart warehouses
News in brief PepsiCo France is investing in an automated, multimodal warehouse that combines robotics, digital systems and intelligent management of logistics flows. The aim is no longer simply to store and distribute products, but to turn the warehouse into a...
Windows 11: Microsoft finally relaxes forced updates
News in brief Microsoft is preparing to overhaul the way updates are managed in Windows 11, giving users greater control over their installation, notably by making it easier to postpone them or avoid certain enforced interruptions. This change responds to a...
WeChat goes autonomous AI: Tencent steps up with OpenClaw
News in brief Tencent has just integrated OpenClaw into WeChat, turning the app into far more than a simple communication tool. This development introduces agents capable of carrying out tasks directly from the interface, without going through several applications or...
