Skip to content

Topic · Themes

Code and developers: all our articles

All 22 Alyriaz articles on the “Code and developers” topic: news, analysis and explainers, newest first. To stay up to date, you can get an alert as soon as a new article on this topic is published.

Filter in the library

  1. · Models

    It starts today: weekly quotas come into force

    The weekly usage limits announced for an agentic coding tool take effect today. We explain the mechanism and what to check.
  2. · Explainers

    What is an agent "harness"? The wrapper that does half the work

    Agent evaluations now measure a model + harness pairing. We explain what this software wrapper is, why it weighs as heavily as the model, and what it changes when choosing.
  3. · Models

    Three providers restructure their usage limits within two weeks

    In two weeks, three major providers have changed the structure of their usage limits. We explain these mechanisms, why they are multiplying, and how to measure what you are actually paying.
  4. · Society

    A third of companies abandon buying software because they can build it themselves

    A McKinsey survey indicates that 32% of organisations have abandoned purchasing a software product because they could build it in-house. We analyse this shift and the growing gap between large and small organisations.
  5. · Models

    Meta bets on cheaper rather than better

    Meta is churning out code-focused models, betting on price rather than cutting-edge performance. We analyse this positioning and what it reveals about real-world usage.
  6. · Explainers

    How does an AI find a security flaw?

    Understanding how a model identifies a software vulnerability sheds light on both its capabilities and its limitations. The mechanism is explained without providing any exploitable details.
  7. · Models

    OX Alpha: a state-of-the-art model appeared out of nowhere, free, and no one says who built it

    An anonymous model named OX Alpha appeared on OpenRouter on 20 August, free of charge, with a million-token context window and multimodal support. No lab has claimed it. Here's a rundown of what we know, what's speculation, and the question no one is asking.
  8. · Models

    AI agents are leaving the demo stage and entering production.

    Several recent announcements point in the same direction: AI agents are moving from prototype to real-world deployment, complete with the supervision and security tools that entails. We analyse what this wave of announcements reveals.
  9. · Models

    Alibaba releases Qwen 3.8-Max, 2.4 trillion parameters, and promises to publish its weights

    Alibaba launched Qwen 3.8-Max on 3 August 2026, a 2.4-trillion-parameter model aimed at code and collaborative work, with a weights release announced for the following week. We analyse what this release means in the race for openness.
  10. · Society

    AI agents speed up scientific code by 60x. The problem is, they seem to be right even when they're wrong.

    A field report conducted by OpenAI and academic partners shows that coding agents can modernise neglected research software, with speed-ups of up to 60 times. The same report warns that these systems produce convincing and sometimes false results. We explain this tension.
  11. · Business

    Today at 5:59 PM, thousands of DeepSeek integrations will stop working.

    On 24 July 2026 at 15:59 UTC, DeepSeek permanently removes the deepseek-chat and deepseek-reasoner identifiers from its API. Any request using these names will fail, with no grace period. We explain what needs to change, the hidden pitfall in the migration, and what this deadline says about the growing weight of Chinese models.
  12. · Vision

    Do we still need to learn to code in 2026?

    AI models now write professional-grade code and top certain rankings ahead of the best closed models. Does that mean learning to program is no longer worth it? We honestly examine both sides, and explain why the real question isn't whether to learn, but what to learn.
  13. · Explainers

    What is an "AI agent"? The word everyone uses without really explaining it

    The word "agent" is everywhere in AI news in 2026, but rarely explained. We break down what sets an agent apart from a simple chatbot, how it works in a loop, and why this capability changes the way we should trust it.
  14. · Models

    Claude Sonnet 5: Anthropic sells (almost) Opus-level power at a standard model price

    Anthropic launched Claude Sonnet 5 on 30 June 2026, the default model for Free and Pro. It comes close to Opus 4.8 on agentic tasks while costing 60% less during the launch period. We break down the figures, the strategy, and what to expect from it day to day.
  15. · Society

    Agentjacking: the flaw that turns your code assistant against you

    An attack dubbed Agentjacking, disclosed in June 2026, traps AI coding agents by injecting fake instructions into error reports. 85% success rate, 2,388 organisations affected. We explain how it works and how to protect against it.
  16. · Applications

    Antigravity 2.0: Google takes on Claude Code and Cursor on their own turf

    Antigravity 1.0, launched in November 2025, was a simple editor. Antigravity 2.0, launched on 19 May 2026, is a complete ecosystem for agentic programming: desktop, terminal, SDK, managed API, enterprise. And everything runs on Gemini 3.5 Flash, 4x faster than the competition. Analysis.
  17. · Society

    The AI startups quietly outperforming while the giants collapse

    In our article on the great AI failures, we showed how Sora, the Humane Pin, Microsoft Designer and Apple Siri crashed and burned in 2026. At the other end of the scale, some startups are posting growth curves never seen before in the history of software. Here is who is really winning, and why.
  18. · Applications

    Claude Code: Your terminal gets smart

    Where Antigravity offers a rich visual interface, Claude Code opts for the purist philosophy: everything happens in text mode, invisible but ultra-efficient.
  19. · Models

    DeepSeek V4: The ultra-fast software architect

    DeepSeek's new model reshuffles the global AI deck. Multimodal, open-weight, and conceived as a genuine "senior architect" rather than a mere assistant.
  20. · Applications

    OpenClaw: the AI that takes control of your computer

    This is no longer a simple chatbot that answers questions. OpenClaw is an 'Agent', an AI capable of clicking, typing on the keyboard and organising your files.

Other topics in “Themes”

All the other topics

Every article, month by month →