Live data from Hacker News

Viewing profile — jhalloran

jhalloran

HN member
Joined
Wed, Jul 08, 2026, 4:23 PM UTC
HN karma
2
Public activity
8 items

About jhalloran

Researcher working on LLM alignment and preference optimization, focused on agentic/tool-use safety (MCP). Papers: arxiv.org/abs/2505.23634, arxiv.org/abs/2605.11217. Code: github.com/johnhalloran321

Recent public activity

  1. story
  2. comment
    Comment #48955234

    This reminded me about the news cycle last year that we were running out of training data (and how silly that was)

  3. comment
    Comment #48865677

    One thing that's easy to forget is how much of the "everything is a service" idea predates LSP. Emacs had long-running subprocesses, RPC-ish interactions, TRAMP, GUD, REPL integrat…

  4. comment
    Comment #48855395

    Curious how Strix/Shannon/Deepteam all stack up against one another

  5. comment
    Comment #48855355

    Nice, looks good. This would mesh really well with the unified system memory on apple silicon

  6. comment
    Comment #48848491

    wow, addictive

  7. comment
    Comment #48834107

    [flagged]

  8. story