Live data from Hacker News

Viewing profile — andrewmunsell

andrewmunsell

HN member
Joined
Sun, Jul 29, 2012, 12:05 AM UTC
HN karma
2,238
Public activity
566 items

About andrewmunsell

Any content I post on Hacker News is strictly personal opinion and does not reflect the views of my employer or anyone other than myself.

- https://www.andrewmunsell.com/ - https://mastodon.munsell.io/@andrew

[ my public key: https://keybase.io/andrewmunsell; my proof: https://keybase.io/andrewmunsell/sigs/iTG3yiQopPB2Za_q0DZMOVBh_5rxp_aExEVcXVUyDv4 ]

Recent public activity

  1. comment
    Comment #48735115

    My guess is for distillation, they need to forward the prompt to Anthropic to get the real Anthropic model's response so they can train their own models on it

  2. comment
    Comment #48465032

    Improvements in model performance aren't always strictly compute-constrained in a way that makes them reliant on Moore's Law. Open weight models-- in particular, from Chinese labs-…

  3. comment
    Comment #47531323

    This has been a thing for years, and so much so, that there's an entire TV with a dedicated second screen that shows you ads underneath your main screen: https://www.telly.com

  4. comment
    Comment #45870370

    No one rich enough flying what the average person would consider a "private jet" or private plane would be flying VFR from uncontrolled airport to uncontrolled airport. The "ultra …

  5. comment
    Comment #45254142

    Yes, but I had to update the Codex CLI manually via NPM to see it. The VS Code extension auto-updated for me

  6. comment
    Comment #44044119

    > incorrect, its an o3 finetune. This is Open AI's fault (and literally every AI company is guilty of the same horrid naming schemes). Codex was an old model based on GPT-3, but th…

  7. comment
    Comment #43933045

    The reason I have never bothered with Claude Code (or even other agentic tools), is that I still code mostly by hand. When I am using LLMs, I know exactly what the code should be a…

  8. comment
    Comment #43929964

    Given that there's a dozen agentic coding IDEs, I only use Cursor because of the few features they have like auto-identification of the next cursor location (I find myself hitting …

  9. comment
    Comment #43516391

    https://archive.is/okv6M

  10. comment
    Comment #42553581

    On the Apple Edu store, it's $499 for the 16/256 and $1079 for the 32/512

  11. comment
    Comment #42270246

    Another data point: 17.6 tokens/s on an M4 Max 40 core GPU

  12. comment
    Comment #41997276

    Data privacy-- some stuff, like all my personal notes I use with a RAG system, just don't need to be sent to some cloud provider to be data mined and/or have AI trained on them

  13. comment
    Comment #41768007

    Sellers are actually supposed to mark items as AI generated/assisted, where applicable: https://techcrunch.com/2024/07/09/etsy-new-seller-policy-202... Whether they actually do thi…

  14. comment
    Comment #40729957

    If Apple's "Private Cloud Compute" is used even on the latest devices for some tasks that are too computationally complex to be done on-device, then is there some reason (other tha…

  15. comment
    Comment #40636946

    From MacRumors: > Notes can record and transcribe audio. When your recording is finished, Apple Intelligence automatically generates a summary. Recording and summaries coming to ph…

  16. comment
    Comment #40370399

    CarPlay is rendered by the phone itself, so it's not strictly a function of how powerful the car infotainment is. You've been able to talk to Siri since the beginning of CarPlay so…

  17. comment
    Comment #40287047

    My current assumption is that this has to do with whatever "AI" Apple is planning to launch at WWDC. If they launched a new iPad with an M3 that wasn't able to sufficiently run on-…

  18. comment
    Comment #38915316

    You appear to be right, as far as I can tell the standard itself has not been ratified https://www.ieee802.org/11/Reports/tgbe_update.htm https://en.wikipedia.org/wiki/IEEE_802.11b…

  19. comment
    Comment #38875325

    I was very excited by this, but I found that some of my dumber IoT devices would refuse to connect to the network if it used PPSK. If I connect them to a separate SSID I use for Io…

  20. comment
    Comment #38869776

    There's always the option to turn off your phone entirely, leave it at home, or simply buy a dumb phone incapable of using these new satellite features. There's always going to be …

  21. comment
    Comment #38844288

    Honestly no, it's mostly due to inexperience with operators and not really understanding what the "best" way to find operators is. I did also look at the Crunch Data one (I was hav…

  22. comment
    Comment #38843996

    My holiday project was doing another pass at my Homelab Kubernetes cluster, part of which involved switching to a proper operator to manage Postgres. Coincidentally, I setup cloudn…

  23. comment
    Comment #38614479

    The article is essentially an ad for an app that does just this

  24. comment
    Comment #38480183

    Everyone made fun of me for having one, but it was the perfect city car. Great turning radius & it fit basically anywhere. And the plastic body meant that if someone opened their d…

  25. comment
    Comment #38407484

    Since I had the same question as everyone else, it seems like it must be using just the transcript. When asking about one of those "8k HDR" showcase videos (with no speech), Bard r…