LoginSign Up
← Back to all sparks
J

Jan

AI-ASSISTANTS
Velocity2.5

Open-source offline AI assistant that runs language models locally on your device.

jan.ai ↗

Jan ships sparse, low-level fixes — CSP and context-length defaults in a thin crawl window

local-llmbug-fixesllama-cppsparse-feed
◆Current state
Only two changelog entries are crawled for Jan, both small engineering fixes: a CSP change to let video uploads load and a llama.cpp default change disabling context auto-fit. The thin feed limits what can be inferred — these are maintenance commits, not feature direction. The sparse window may itself reflect a crawl-coverage gap rather than a genuinely quiet product.
◆Where it's heading
On the visible evidence, work is at the plumbing layer: content-security policy correctness and local-inference defaults. Whether Jan is shipping larger features that aren't being captured can't be determined from two entries; the crawl coverage is worth checking.
◆Prediction
Hard to predict from two low-level fixes; the safe read is continued llama.cpp default-tuning and bug fixes unless richer release notes surface.

◆Recent moves

  1. 20d ago

    Fix CSP to allow video uploads (v0.8.3)

    A CSP fix adding a media-src directive so video uploads load — a correctness bug fix with narrow user-visible impact.

    View source ↗
  2. 1mo ago

    Disable context auto-fit; default context length to 8192 (v0.8.1)

    Disabling context auto-fit by default and setting ctx_len to 8192 changes default local-inference behavior — a small but user-visible default that affects how models run out of the box.

    View source ↗