Issue 14 · Nov 2–8, 2026Agent Age News magazine · Other editions · Method · HU / ENG

The impact of AI on software development and developers' work, curated weekly

Issue 14

Nov 2–8, 2026 · 47 stories · 1 of which from Hungary
Viewpoint

case · global

Ethan Mollick publishes Portals, a browser-based 3D experience of 471 generated worlds built by agent teams

Ethan Mollick, a professor at Wharton, has made public a project called Portals: an endless, hands-off flight through 471 machine-generated 3D worlds, running in the browser with no server. According to the project description, AI agents designed and wrote the whole thing, with a lead agent coordinating the teams; the figure of "about 25,000 agents" is Claude's estimate, not a measured number. The code carries a non-commercial licence, and the authors note that the licence of some borrowed shader snippets differs from the one stated.

Nov 9, 2026 · 1 source

Who is affected and how

senior developer
Look at the repo's structure (engine, building blocks, world files): it is a good example of how a large job can be split among many agents.
tech lead
The project shows that an agent team can build a large codebase, but licence checking remains a human task: borrowed code can slip in with the wrong label.
DevOps, security
When code is machine-written, build licence and provenance checks into the pipeline; here the authors themselves found borrowed snippets under a different licence.
startup founder
It cannot be carried into a commercial product: the licence (CC BY-NC-SA) permits only non-commercial use.
incident · global

Malicious Claude Code extension in Cursor marketplace reportedly reaches 5,000 users

A trojanized Claude Code extension appeared in Cursor's marketplace and reportedly reached 5,000 users, with the malicious versions attempting to install an SSH backdoor. Cursor has removed the…

senior developerCheck the publisher of your installed Claude Code extension and, on any affected machine, rotate tokens and keys.tech leadSet rules on which IDE marketplaces and publishers the team may install extensions from.tool change · global

Anthropic restricts Claude Code from cloning video games

Anthropic added two sentences to Claude Code's instructions so that it does not copy existing video games. Indie developers say the restriction also blocks legitimate projects, and reports say Opus…

senior developerIf you give the agent game or reverse engineering work, expect a refusal, and keep an alternative tool or a manual approach at hand.tech leadCheck whether the new restriction affects your team's game, compatibility or reverse engineering tasks before you build a process on them.startup founderIf your product idea relies on recreating existing games or software, a provider rule change is a business risk.security · global

Claude Code's 'Don't Ask Again' file exposes passwords and keys in 1,122 public copies

A Claude Code file that exposes passwords and keys was found in 1,122 public copies on GitHub. The news is dated November 7, 2026.

senior developerBefore committing, check that the agent's permission or settings file is not going into the repo.case · European Union

Revolut switches from Claude Code to Chinese open-weight model, cutting costs by 90%

Revolut has reportedly replaced Claude Code with a Chinese open-weight model, cutting its AI coding costs by 90%. The news appeared on 3 November 2026.

CTOAssess how much an open-weight alternative could save compared with expensive closed models, and what it means for data protection and compliance.tech leadRun a comparison pilot on your own codebase to measure cost and quality.

Hungary

job marketAI and Hungarian graduates: junior positions are shrinkingjunior developerAs a domestic entrant, build skills in checking and testing with AI tools rather than in pure coding tasks.tech leadWhen planning junior hires in Hungarian teams, onboarding capacity must also be counted.

More key stories of the week

case · United States

Apple, Microsoft and Meta tighten internal AI usage limits

Apple is limiting engineers' daily AI spending, Microsoft has reportedly cut some of its AI caps by 90%, and Meta's Claude Code user numbers have halved. The reports appeared between 5 and 8 November…

CTOEven large companies are keeping token costs in check, so plan how you will measure return on investment.senior developerExpect agent usage to be capped, and expect efficient prompting and context management to matter.tool change · global

OpenAI may stop supplying models to Cursor from 12 November

According to an excerpt, OpenAI will stop supplying models to Cursor from 12 November, changing the choice between Codex and Cursor. A decision that used to rest on workflow has become one that…

senior developerIf you use OpenAI models in Cursor, check which model you can switch to before 12 November.tech leadAssess which team workflows depend on the Cursor–OpenAI relationship, and prepare a switchover plan.security · global

Attackers use agentic tooling to find exposed secrets in public GitHub repos

Microsoft Threat Intelligence has observed threat actors using an agentic AI attack framework to search public GitHub repositories for exposed secrets and abuse them. The report was published on…

senior developerIf a key has landed in a public repo, treat it as compromised immediately, and do not just delete the commit.security · European Union

Lovable-built apps left passport and payment data open to anyone

A German security firm examined more than 159,000 apps built with Lovable and found passport numbers and payment data accessible. The news was published on 4 November 2026.

startup founderBefore launching a vibe-coded app, have its data-access rules checked, because sensitive data is a GDPR risk.senior developerCheck the generated app's access control before it handles live data.case · United States

Goldman Sachs bars bankers from using Claude Code and GitHub

Under guidance issued in October, Goldman Sachs has limited access to AI coding tools to engineers, and non-engineering staff cannot use Claude Code or GitHub. The news was reported on 2 and 6…

CTOIn a regulated environment, define clearly who may use a coding agent.case · United States

OpenAI to acquire Pierre Computer to strengthen Codex

OpenAI is acquiring the startup Pierre Computer to strengthen Codex. Analysts say the move targets Microsoft's GitHub in the race for AI coding.

CTOReassess vendor risk in tool choice, because code hosting and the agent market are converging.tech leadWatch how the acquired technology is built into Codex before you reorganize GitHub-based workflows.open source · Asia

DeepSeek's open-source Super-Agent prototype positioned as an alternative to Claude Code

DeepSeek's open-source Super-Agent prototype coordinates several AI workers in an always-on system instead of isolated coding sessions. Hungarian media also reported on the experimental architecture.

senior developerWorth trying as an open alternative, but it is a prototype, so do not build production workflows on it.tech leadAssess whether the always-on, multi-agent model can replace today's session-based agents.tool change · global

OpenAI to pool ChatGPT and Codex usage allowance from December

According to OpenAI's help center, from December the usage allowance on Plus, Pro and Business plans will be shared between ChatGPT and Codex. The Chat and Work tabs in the desktop app are merging…

senior developerCodex and chat draw on one allowance, so schedule heavy agent tasks deliberately.tech leadRecalculate the team's subscription allowance, because Codex use will crowd out other ChatGPT use.case · United States

Meta acquires AI coding startup Conductor

Meta has acquired Conductor, which lets engineers manage several coding agents at once, according to Axios sources. The news appeared on 4 November 2026.

tech leadRunning multiple agents in parallel has become a tool category of its own; assess how your team handles it today.startup founderThe agent-orchestration layer is an acquisition target, which affects vendor dependence and exit options.tool change · global

Coding agents get spending limits as Cognition adds hierarchical budgets to Devin

Cognition has introduced hierarchical budgets for Devin, and The New Stack reports that a coding agent can be cut off mid-task when its budget runs out. The news is dated 2 November 2026.

tech leadSet budgets at team and task level, and define what happens to an interrupted agent task.case · global

AI code review is the next bottleneck: more code, fewer lines read

A Sourcegraph executive says AI code review is the new bottleneck, and that it also costs SREs. The New Stack and an engineer at WorkOS also write about how to cope with the flood of code.

tech leadThe review process needs redesigning, because the volume of code from agents exceeds human review capacity.senior developerYou have to decide what to review line by line and what to leave to automated checks.case · United States

OpenAI builds new Git backend Pando after Codex agents drive commit surge

Codex agents caused a 2,442% increase in commits in OpenAI's monorepo, so the company developed a new Git backend, Pando. According to the announcement, push latency fell by 80% and merge reliability…

CTOAdopting agents can mean investment in storage and CI, not just tool licences.

In brief

researchClaude writes 80% of Anthropic's code; METR publishes independent assessment of its AI R&D accelerationtech leadIf your own team also relies on AI-written code, set up independent review and control processes in advance.incidentClaude Code deleted customer data and notes while given a clean-up tasksenior developerMake destructive commands subject to approval, and keep the agent's environment separate from production data.tech leadSet rules for the environments in which agents may run deletion and clean-up tasks.tool changeAndroid Studio opens to any AI coding agent, ending Gemini exclusivitysenior developerIn Android Studio you can use your preferred agent, so it is worth comparing them on your own project.tech leadThe ACP standard reduces vendor lock-in, so choosing an agent can be more flexible at team level.caseCopilot Cowork generated 1,211 pull requests in a single daytech leadThe flood of agent-generated PRs strains the team's review capacity, so plan filters and limits.senior developerExpect to review more machine-made PRs; without review prioritisation this quickly becomes a bottleneck.securityOpenAI's GPT-6 Cyber finds 81 Firefox and 948 Linux flawssenior developerMaintainers of open-source projects can expect a larger flood of bug reports.securityAI coding agents are installing MCP servers that will never be patchedsenior developerDon't let the agent install an MCP server without asking; check the source and the maintainer.incidentPostman added itself to Claude Code and Codex without asking permissionsenior developerReview your agents' MCP and extension lists and remove anything you did not add yourself.job marketAI coding tools disrupt junior developers' career path, Alasdair Allan saysjunior developerDeliberately practise without agent assistance as well, and ask for reviews, so that debugging and design fundamentals develop.senior developerWhen mentoring, assign tasks where the junior explains the AI-generated code.tech leadPlan a learning path for juniors, because agents are taking over some entry-level tasks.tool changeGoogle is shutting down one of its AI coding toolssenior developerIf you build on Google's tool, find out the shutdown date and switch to another tool in good time.tech leadKeep vendor attrition risk in mind when choosing tools.surveyAI writes 75% of Google's new code as developer distrust risestech leadAs the share of AI-generated code grows, code review culture and test coverage need to be strengthened in advance.senior developerReview has become your main job, so it is worth developing methods for checking AI-generated code.researchAI coding agents still need human rework on three-quarters of taskstech leadDo not treat agents' output as finished; build rework time into your estimates.senior developerTaking over and fixing agents' work is the main part of the daily job, so review skills are valuable.incidentWorkOS, Northflank and Trigger.dev breached in attacks involving stolen AI access tokenstool changeQodo builds context into AI code review with Codextech leadAssess whether context-based review produces fewer false alarms than your current tool.releaseGitHub Copilot impact dashboard adds chat and VS Code agent usage, code review gets API controlstech leadUse the new dashboard data to measure how much your team actually uses Copilot's agent and chat features.tool changeAnthropic adds message threads to its API, but the token bill stays the samesenior developerIf you build your own agent on the Claude API, threads may speed up response times, but do not expect lower costs.startup founderToken costs have to be optimized another way, because threads help with latency, not with the bill.releaseAWS launches Kiro bots to coordinate AI coding agentstech leadDivision of work between agents is gaining tool-level support; factor this in when planning orchestration.releaseXcode 27.3 adds GitHub Copilot to its built-in assistantsenior developerApple-platform developers can now use Copilot in Xcode too, so it is worth comparing it with the built-in assistant.tool changeGitHub Copilot Fusion picks models automatically; local preview runs only partly on-devicesenior developerDo not assume your code stays entirely local, because other stages of the process do not run on your machine.open sourceOccupySaaS open-source project uses AI to clone costly servicesstartup founderOpen clones could put pressure on SaaS pricing, so it is worth factoring in a self-hosted alternative.CTOIn build-versus-buy decisions, open, AI-built clones are a new option, but maintenance and security are your responsibility.caseOpenAI and JPMorgan Chase to deploy Codex and cybersecurity modelsCTOA large-bank deployment can offer a template for using Codex in a regulated environment.caseCat Wu, one of the faces of Claude Code, leaves Anthropictech leadIf your team builds on Claude Code, keep an eye on how the product's direction develops.releaseCognition launches SWE-2 Flash to make coding agents cheaper and fastertech leadThe cheaper, faster model is worth piloting on routine tasks, given budget constraints.securityBug report alleges Claude Code writes user's email address into User-Agent headerreleaseGoogle Cloud adds OpenAI models and Codex agents to Model GardenCTOOpenAI models can also be used within Google Cloud, which may reduce vendor fragmentation.surveySurvey: 67% of developers use AI for code generation, 61% for debugging, only 20% in productiontech leadAgents are mainly used for code generation and debugging; treat rollout in operations as a separate pilot.releaseGitLab 19.5 makes agentic development a governed part of its DevOps platformtech leadPlatform-level agent support could standardise how the team uses agents.open sourceAI is speeding up open source as its maintainer base agessenior developerIf you run an open-source project, consider bringing in agents to offset the lack of new contributors.job marketBanks and healthcare firms outbid tech companies for software talentsenior developerEngineers with AI skills can get better offers in non-tech sectors too, so it is worth surveying the market.CTOFor retention, banks and other industries have to be counted in the pay competition.job marketAmazon memo warns engineers about AI productivity trapssenior developerLarge companies are setting expectations for AI use, so you need to take clear ownership of your own responsibility.tech leadDefine what counts as real productivity, and do not measure only the volume of generated code.

← Issue 13