Seriora Research
AgentPortalBlog
← Lab

Notes

What we learned from the systems we run.

Our current investigations. From work we are still running.

  • 22 Sep

    Most self-improving agent papers fail the eval traps they should already know

    A methods audit of forty-one peer-visible self-improving LLM-agent papers under a five-trap checklist. Locked primary result: 39/41 (95.1%) fail two or more applicable traps. Seriora Research preprint.

  • 16 Sep

    What is an agent?

    A lab note on the gap between next-token prediction and systems that perceive, act, and revise how they act. Model weights are not scaffolding. Autonomy is not agency.

  • 16 Sep

    When the score is wrong

    Alignment fails quietly when models optimize proxies instead of intent. As reinforcement learning, preference models, and self-improving agents scale, that failure mode stops being a training curiosity and becomes the central reliability problem, because we still lack evaluations that can reliably tell learned-what-we-meant from hacked-the-score.

  • 11 Sep

    Harness-Bench preview

    We ran the base Seri harness on Harness-Bench with GPT-5.6 Luna Pro. This note reports that untreated run.

  • 07 Sep

    How compaction works

    Context is finite. Compaction is how an agent keeps the thread after it has already seen too much.

Seriora Research