Analysis

Authorial takes on the day's AI-engineering news: the conclusion the source itself does not state, grounded in the primary source and the New Runtime archive.

340 analyses54 topicsJSON indexForecast ledger

1-12 of 340 analyses

  1. 4 sources

    The model router is becoming the product

    Gemini 4 Hydrogen matters less as another fast model than as part of a workflow that can assign routine execution and harder reasoning to different models. That makes routing quality—not any single benchmark—the bet builders should test.

    • google
    • routing
    • gemini
  2. 19 sources

    Agent memory: mem0, Zep, Letta

    mem0, Zep, and Letta are third-party agent memory layers, unlike Claude/ChatGPT built-in memory which is product-scoped personalization inside those chat apps. mem0 extracts facts into SQL + vector embeddings (+ Platform Graph Memory entity linking), with Platform cloud or OSS self-host (pip/npm Mem

    • tools
    • developer_tools
  3. 4 sources

    Nvidia’s real succession test is keeping the machine moving

    The board has installed an interim CEO but named no deadline or successor. For customers, the key risk is not the title change itself; it is whether Nvidia can sustain execution while infrastructure financing and data-center access are already under pressure.

    • trends
  4. 4 sources

    Sonnet’s savings proved conditional as Haiku took the cheapest-task slot

    Six weeks after New Runtime’s earlier coverage, the case for Sonnet 5.5 on bounded everyday work still holds, but “new baseline” is too broad. Anthropic’s cheaper Haiku option and evidence that stale instructions add tool calls make workflow design part of the cost equation.

    • anthropic
    • claude
    • benchmarks
  5. 2 sources

    Marin 535B-A23B finished pretraining on 18T tokens and beat its loss forecast; downstream evals are pending

    Open Athena's architecture write-up gives the full recipe for a 535B-total, 23B-active MoE trained on 768 GB200s: a 3:1 local/global attention mix, 8-of-384 latent MoE, MuonH, and a switch to dropless expert parallelism mid-run. The final Paloma loss was 1.982 against a forecast of 2.039, though some of that gain comes from a contaminated eval subset.

    • moe
    • github
    • architecture

Every analysis, by month

The whole archive on one page, newest first: 340 titles with their dates.

November 2026 88

October 2026 232

September 2026 20

Machine routesPublic and cache-friendly
GET /analysis.jsonGET /sitemap-analysis.xml GET /rss.xml
Who read this page?Machine requests, hidden until opened

Loading the privacy-safe route aggregate…

Open the JSON contract