Insiders: DeepSeek is forming a Harness team to compete with Claude Code
Author｜Wang Bo, Jiazi Light Year
"Jiazi Light Year" has learned from sources close to DeepSeek that the company is organizing a new Harness team focused on code intelligent agent products, internally benchmarking against Claude Code from Anthropic.
DeepSeek's senior researcher Chen Deli recently confirmed this on social media, stating, "DeepSeek is organizing a new Harness team to work on products and research in the Harness direction," and bluntly said, "In simple terms, it is benchmarking Claude Code to create DeepSeek Code Harness."
This is not an ordinary recruitment.
The job postings indicate that DeepSeek is opening two key positions: Harness Product Manager and Harness R&D Engineer, with the work location currently limited to Beijing. DeepSeek's office in Beijing is located in the Haidian District Rongke Information Center, very close to Peking University and Tsinghua University. Officially, it is located in the "Centennial Beijing-Zhang AI Innovation Belt," while informally, it is also in the recently popular "Wang Huiwen Area."
Core Definition: Model + Harness = Agent
In the job description, a core formula is prominently displayed:
Model + Harness = Agent.
This phrase can almost be seen as DeepSeek's internal definition of the productization path for the next stage: the model itself is merely the foundation of the Agent, while context management, tool invocation, task planning, file reading and writing, code modification, terminal execution, feedback collection, and evaluation loops outside the model are the key parts that allow the Agent to truly enter the workflow.
The job posting further states, "We are transforming DeepSeek's cutting-edge model capabilities into leading Agent products. All work outside of the model itself falls under the scope of Harness." Additionally, this position will participate in the entire process of "DeepSeek desktop Agent product" and "define DeepSeek's understanding of Harness."
"Jiazi Light Year" analyzes that DeepSeek is not simply trying to create a code assistant plugin, but is filling in the intermediate layer that connects the model to the real workflow.
Over the past year, the industry has proven that strong coding capabilities do not equate to developers actually using them; a model that can write code does not mean it can continuously complete an engineering task.
What truly changes the way developers work is not a standalone Claude model, but Claude Code; not a standalone GPT model, but Codex; not a code answer in a chat box, but an engineering intelligent agent that can enter the terminal, understand projects, read and write files, run commands, fix errors, manage Git, and invoke tools.
DeepSeek's greatest strength in the past was the model. Now, it is starting to add that layer of "hands" above the model.
I. Why DeepSeek Emphasizes Harness
In the context of traditional AI products, "code assistant" usually refers to two types of products: one is a completion plugin in an IDE, and the other is code Q&A in a chat box.
However, the term that repeatedly appears in DeepSeek's recruitment is not Code Assistant, but Harness.
Harness originally refers to "test harness" or "execution framework" in the engineering context, and in the Agent context, it is closer to a system that truly enables the model to take action. The model is responsible for understanding, reasoning, and generating, while Harness is responsible for integrating these capabilities into the real environment.
The job description mentions that this role needs to plan the DeepSeek Harness product roadmap, connect researchers, engineers, open-source communities, and end-users, and communicate deeply with researchers from the model training team to achieve the co-evolution of the model and Harness.
This statement is crucial.
It indicates that what DeepSeek wants to do is not just to wrap the existing model in a shell, but to make the Agent product itself a part of the model's evolution. In the past, the common product logic for large model companies was: the research team first trains a model, and then the product team creates applications based on the model's capabilities. However, in the Agent era, this order is being disrupted. Products are no longer just an outlet for model capabilities, but a training ground for those capabilities.
A code Agent failing in a real project may not be due to product interaction issues, but rather the model's incorrect compression of long contexts; it may not be a problem with the tool invocation chain, but rather the model's unstable strategy for task decomposition; or it may not be a lack of coding ability, but rather its failure to maintain a continuous understanding of engineering constraints, testing feedback, and user intent.
Therefore, the value of the Harness team is not just to "make products," but to turn real development tasks into a feedback source for the model's continuous evolution.
II. Why DeepSeek Must Fill the Code Harness Gap
DeepSeek has long bet on coding capabilities. From DeepSeek-Coder to DeepSeek-Coder-V2, DeepSeek's investment in code models has continued to increase, supporting improvements in language, context length, and complex task capabilities. Its issue is not the lack of coding ability, but rather that this capability has largely remained at the model level and has not yet become a high-frequency product in developers' daily workflows.
The popularity of Claude Code proves one thing: The competition in AI coding is shifting from competition in model capabilities to competition for entry points into developers' workflows.
This is also a lesson that DeepSeek must learn now. More subtly, before DeepSeek officially took action, the developer community had already created a version of "DeepSeek's Claude Code."
An open-source project named DeepSeek-TUI previously became popular in the developer community. It is a coding agent running in the terminal that can read and write files, execute shell commands, search the web, manage Git, and coordinate sub-agents through a TUI interface.
The rise of DeepSeek-TUI indicates two issues:
Basic Mentality Maturity: The DeepSeek model has already established a foundation in developers' minds for becoming a code Agent. Otherwise, the community would not have naturally grown around it to create Claude Code-like products.
Official Level Absence: What DeepSeek lacks is not model attention, but official Harness.
In the eyes of developers, the appeal of DeepSeek-TUI is straightforward: low cost, available domestically, long context, and relatively low deployment barriers. Many domestic developers do not want to use Claude Code, but are limited by price, access stability, account systems, and corporate compliance.
However, community projects also have inherent boundaries:
No matter how active a third-party open-source project is, it is difficult to truly grasp the evolutionary rhythm of the model's internal capabilities;
It can adapt around the API, but cannot reverse-decide how the model is trained;
It can optimize prompts, toolchains, and interactions, but it is challenging to systematically inject massive real task feedback into model improvements.
The significance of official Harness lies precisely here.
DeepSeek's own Code Harness has several advantages that community projects do not possess: collaboration with the model team, interface design authority, training data feedback loops, internal real task scenarios, and long-term operational capabilities for the developer ecosystem.
The open-source community has already paved the way: developers indeed need a DeepSeek version of Claude Code. Now, DeepSeek needs to reclaim this path and turn it into its core product.
The fact that DeepSeek is now starting to recruit means it is finally ready to step into the arena itself.
Chen Deli mentioned at the 2025 World Internet Conference in Wuzhen last November: "One of our core advantages is long-termism, insisting on making breakthroughs in cutting-edge intelligence as the main line. In this process, we have also abandoned many side projects and do not engage in those short-term, quick-return side endeavors."
After the model wars, the real Agent wars have begun. What DeepSeek needs to fill this time is the most critical layer between the model and action—Harness.
DeepSeek is equipping its model with a pair of hands.
You may also like
ZachXBT: Humanity private key leak and abnormal surge in H token should be viewed separately
On June 9, according to related disclosures, on-chain investigator ZachXBT posted an update on Humanity’s roughly $31 million security incident, saying that after further analyzing fund flows, he currently tends to believe the project team was not involved in an “inside job” or a self-staged attack. According to him, the official explanation about the private key leak was broadly accurate, but before the token unlock, the price of H had been artificially pushed higher, and the hacker later took advantage of that market environment; therefore, the private key leak and the earlier abnormal price pumping should be regarded as two separate and independent events. This reframing has shifted the market’s understanding of the nature of the incident. Earlier discussion around Humanity had focused on whether the team directly participated in the attack or used the security incident to cover up internal operations. ZachXBT’s latest remarks shift the focus from “whether it was self-theft” to “whether there were pre-unlock market structure issues.” He also questioned whether the team may have.
Morning Report | OpenAI has submitted an S-1 registration statement draft to the U.S. SEC; Morpho completes $175 million financing
Morning Report | BitMine increased its holdings by 126,971 ETH last week; trader Eugene announced his exit from the crypto market
Wang Chuan: How can one not feel anxious after the neighbor Old Wang made thirty times profit by investing in storage stocks? (Seven) - A quarter-century cycle
Cryptocurrency CEXs are flocking to sell US stocks, and traditional brokerages are facing an "uninvited guest."
$75 billion in foreign capital has fled, and South Korean retail investors have absorbed it all using leverage
Japan’s Three Megabanks Plan Joint Stablecoin Issuance in Fiscal 2026
MUFG, SMBC, and Mizuho reportedly plan to jointly issue fiat-pegged stablecoins in fiscal 2026, signaling Japan’s growing push into bank-led digital payment infrastructure.
Humanity Discloses H Token Dual-Chain Attack Details, With Losses on Ethereum and BSC Exceeding $36 Million
Humanity said the H token attack across Ethereum and BSC caused more than $36 million in losses after leaked ProxyAdmin keys enabled malicious contract upgrades and token minting.
White House Discusses CLARITY Act With Law Enforcement Ahead of Senate Vote
The White House discussed the CLARITY Act with law enforcement ahead of a Senate vote, focusing on illicit finance risks and developer protections.
Bitcoin Trading Guide 2026: Strategies for Experienced Traders
What Is XAUT and PAXG? Why Tokenized Gold Is Booming in 2026
Will the SpaceX IPO Hurt Bitcoin? Here's What Traders Are Watching
Foreign selling in the South Korean stock market accelerates, with cumulative net sales reportedly reaching $75 billion this year
On June 9, The Kobeissi Letter, citing Goldman Sachs data, reported that global investors are selling South Korean stocks at an unusually rapid pace. In the latest trading session, foreign investors sold about $801 million worth of Kospi constituent stocks again; total foreign outflows last week reached about $10 billion, and the market has been in net foreign selling on nearly every trading day over the past month. According to the data cited in the report, foreign investors have sold about $75 billion worth of South Korean stocks so far this year. Meanwhile, South Korean retail and institutional investors together recorded roughly $69 billion in net buying over the same period, suggesting that the market’s main buying support has come from domestic capital rather than returning overseas funds. The information currently disclosed still mainly comes from The Kobeissi Letter’s retelling and Goldman Sachs data summaries, while public details on the statistical period and the specific definition of “selling” remain relatively limited.
Fortune Warns of Strategy’s Financing Structure Risks as Bitcoin Premium Narrows
Fortune warned that Strategy’s Bitcoin treasury model faces growing financing risks as MSTR’s net asset premium narrows and preferred stock dividend pressure increases.
Ferrari Challenge Le Mans: Carl Moon to Dominate in WEEX Livery
Sahara AI Responds to SAHARA’s Sharp Drop: No Contract or Product Security Issues Found, Internal Investigation Underway
Sahara AI responded to SAHARA’s 60% price drop, saying no token contract or product security issues have been found and an internal investigation is underway.
WEEX Deposit/Withdrawal Dynamic Island: Your Asset Status, Always in Sight
Scaling Crypto Derivatives: The Digital Asset Infrastructure Behind High-Volume Trading
In the fast-moving digital asset ecosystem, derivatives platforms face an extreme architectural test. High-leverage futures markets demand more than just standard security—they require absolute operational precision, zero-latency matching engines, and ironclad structural scalability, all while navigating intense market volatility.
As global platforms scale to meet these demands, the industry is shifting away from rigid, monolithic setups toward a more agile, "decoupled" infrastructure philosophy.
The Blueprint for High-Volume Copy TradingFor elite global exchanges like WEEX (founded in 2018), this architectural choice becomes critical when scaling high-volume retail features like social copy trading. When thousands of users automatically mirror the real-time strategies of elite traders simultaneously, it triggers sudden, monumental spikes in concurrent transactional volume.
To prevent execution latency or settlement bottlenecks during these peak volatility events, a platform's primary engine must remain entirely dedicated to risk management, copy-trade synchronization, and order matching.
The Architectural Rule: New-generation platforms must separate front-end user execution engines from heavy backend infrastructural overhead to eliminate operational friction.
By separating these layers, platforms can maintain complete sovereignty over their trading environments and user experiences while strategically aligning with institutional-grade infrastructure ecosystems. This strategic framework allows modern exchanges to leverage advanced Digital Asset Custody infrastructure such as Cobo’s behind the scenes, ensuring that backend wallet management scales elastically alongside trading spikes.
Capitalizing on Market Momentum and 400× LeverageIn a derivatives arena where platforms offer up to 400× leverage on perpetual contracts, capital efficiency and market agility are core business metrics. To capture market momentum, an exchange needs the ability to rapidly expand its asset offerings, supporting everything from legacy crypto assets to sudden, trending altcoins across a massive library of trading pairs.
Adopting a flexible, scalable Wallet-as-a-Service (WaaS) solution such as Cobo’s could completely rewrite the development timeline for high-growth exchanges. Instead of spending months of engineering capital building out custom backend wallet architectures for every new blockchain network, platforms can deploy localized infrastructure in days.
This agility allows platforms to instantly scale their listings to over a thousand trading pairs without compromising security or delaying time-to-market. It mirrors the exact operational advantages seen during high-velocity market events, similar to how advanced wallet infrastructure empowers platforms during sudden asset surges; allowing exchanges to pass that speed and liquidity directly to their global user base.
A Mature Foundation for GrowthThe synergy between trusted infrastructure ecosystems and global trading platforms represents the natural evolution of a maturing crypto market. As WEEX continues to scale its global spot and derivatives offerings for over 6 million users, adopting robust backend paradigms proves that platforms no longer have to compromise between cutting-edge trading velocity and uncompromised structural security.
ZachXBT: Humanity private key leak and abnormal surge in H token should be viewed separately
On June 9, according to related disclosures, on-chain investigator ZachXBT posted an update on Humanity’s roughly $31 million security incident, saying that after further analyzing fund flows, he currently tends to believe the project team was not involved in an “inside job” or a self-staged attack. According to him, the official explanation about the private key leak was broadly accurate, but before the token unlock, the price of H had been artificially pushed higher, and the hacker later took advantage of that market environment; therefore, the private key leak and the earlier abnormal price pumping should be regarded as two separate and independent events. This reframing has shifted the market’s understanding of the nature of the incident. Earlier discussion around Humanity had focused on whether the team directly participated in the attack or used the security incident to cover up internal operations. ZachXBT’s latest remarks shift the focus from “whether it was self-theft” to “whether there were pre-unlock market structure issues.” He also questioned whether the team may have.
Morning Report | OpenAI has submitted an S-1 registration statement draft to the U.S. SEC; Morpho completes $175 million financing
Morning Report | BitMine increased its holdings by 126,971 ETH last week; trader Eugene announced his exit from the crypto market
Wang Chuan: How can one not feel anxious after the neighbor Old Wang made thirty times profit by investing in storage stocks? (Seven) - A quarter-century cycle
Cryptocurrency CEXs are flocking to sell US stocks, and traditional brokerages are facing an "uninvited guest."
$75 billion in foreign capital has fled, and South Korean retail investors have absorbed it all using leverage
