Live data from Hacker News

Viewing profile — mark_undoio

mark_undoio

HN member
Joined
Fri, Jan 28, 2022, 7:49 PM UTC
HN karma
664
Public activity
249 items

About mark_undoio

I'm the CTO at Undo - https://undo.io

We make software that can record/replay other software (including running it backwards). It's cool, please try it.

Sometimes I share things on Twitter - https://twitter.com/mark_undoio Sometimes I write articles (along with my colleages) about GDB - https://undo.io/resources/gdb-watchpoint/

Recent public activity

  1. comment
    Comment #48449659

    Speaking as a Brit, our national trait is generally too understate things. So even saying what you mean, directly, comes off as a bit immodest and hyping it up in sales pitches sou…

  2. comment
    Comment #48172204

    There was a quote somewhere about Mercurial having a mental model small enough you can fit in your head - and that was the big win for me. It was also fast and had very clean, easy…

  3. comment
    Comment #46767129

    I've recently been thinking how AI agents could affect this. If you're lucky enough to be able to code significant amounts with a modern agent (someone's paying, your task is amena…

  4. comment
    Comment #46669232

    Maybe this? https://sites.google.com/site/616cellnet/ct2

  5. comment
    Comment #46669201

    Whilst I have seen the Rabbit fittings others have mentioned I do remember mention of a "zone phone" and suspect we're recalling the same thing...

  6. comment
    Comment #46370017

    Very excited to see this come out - though coding agents are impressive their UIs are a bit of a mixed bag. Textual offers incredibly impressive terminal experiences so I'm very mu…

  7. comment
    Comment #45412094

    I love the Patagonian Welsh. BBC Wales, which often has great comedy, has a sitcom based around the original emigration to Patagonia: https://www.bbc.co.uk/programmes/b060cd20 The …

  8. comment
    Comment #45137449

    In Cambridge we've got a clock called the Chronophage which is intended to be a sinister "eater of time" - the designer has done a good job of making it feel uncomfortable to look …

  9. comment
    Comment #44933593

    Acorn was doing stuff in Cambridge UK until more recently than I'd realised - it effectively incubated a load of talent that went on to find other companies. Famously ARM span out …

  10. comment
    Comment #44886542

    This demo was so cool. There were lots of alternative OSes out there back then that felt very impressive. Linux at the time was cool too but less polished than now. Lots of people …

  11. comment
    Comment #44876420

    Encarta 95 had it - I remember thinking how cool it was that it looked like Win 95.

  12. comment
    Comment #44834738

    I'm pretty comfortable with the agent scaffolding just restricting directory access but I can see places it might not be enough... If you were being really paranoid then I guess th…

  13. comment
    Comment #44805537

    Amp (ampcode.com) uses Sonnet as its main model and has GPT o3 as a special purpose tool / subagent. It can call into that when it needs particularly advanced reasoning. Interestin…

  14. comment
    Comment #44656880

    I've heard various online stories, over the years, about how nobody nails the ergonomics quite like Maltron does. Which is amazing given how long they've been about. I have an old …

  15. comment
    Comment #44623755

    It's quite weird having local footpaths and paved roads that turn out to have been constructed by the Romans originally - around here that also applies to canals, drainage ditches,…

  16. comment
    Comment #44490726

    > I don't understand this. Developer time is so much more expensive than machine time. Do companies not just double their CI workers after hearing people complain? It's just a thro…

  17. comment
    Comment #44488520

    Process recording by time travel debug seems like a good fit for this problem - then you can capture 100% of process execution and then go back and investigate further. We (Undo.io…

  18. comment
    Comment #44468454

    That's the thing though - they're using logs. My theory is that LLMs are intrinsically quite good at that because they're good at sifting text. Getting then to drive something like…

  19. comment
    Comment #44466462

    I'm fascinated by this paper because it feels like it could be a good analogue for "can LLMs handle a stateful, text-based tool". A debugger is my particular interest but there's n…

  20. comment
    Comment #44466389

    > It will be interesting to know what challenges came up in nudging the model to work better with time travel debug data, since this data is novel and the models today might not be…

  21. comment
    Comment #44466045

    I am appalled and delighted by this. It feels like an AI cousin to the Python error steamroller ( https://github.com/ajalt/fuckitpy ). Whenever I see this sort of thing I think tha…

  22. story
  23. comment
    Comment #44350823

    Always fun to see what izabera has come up with - every single time I'm somewhere between delighted and terrified to see what she's made the computer do this time!

  24. comment
    Comment #44346491

    I assume you're aware but there are some open source assistants that can get you this (at least to some extent). E.g. Codename Goose https://block.github.io/goose/docs/quickstart/ …

  25. comment
    Comment #44346425

    Thanks for this - I've been using the MCP Inspector https://modelcontextprotocol.io/docs/tools/inspector but find it doesn't really fit my workflow. I like the fact this mcp-debug …