Viewing profile — krschacht
krschacht
HN member- Joined
- Wed, Oct 14, 2009, 5:51 PM UTC
- HN karma
- 53
- Public activity
- 74 items
- HN profile
- View on Hacker News ↗
About krschacht
Recent public activity
-
comment
Comment #48337933
In the last 18 months I tried a Framework twice and both times ended up returning it. I was running Arch both times and had too many low level issues. I couldn’t get hibernation or…
-
comment
Comment #48337844
Which god are you asking about? People have come up with so many different ones. Do they all count?
-
comment
Comment #48337803
I’ve been starting companies my whole career. My first real one was a software dev shop while in college, I sold it my senior year and dropped out. It wasn’t much of a financial su…
-
comment
Comment #47752304
At the end of this article it states, "Our tests gave models the vulnerable function directly, often with contextual hints (e.g., "consider wraparound behavior"). A real autonomous…
-
story
Show HN: Clippy – screen-aware voice AI in the browser
A friend and I built a browser prototype that answers questions about whatever’s on your screen using getDisplayMedia, client-side wake-word detection, and server-side multimodal i…
-
comment
Comment #47249572
Dang, that would be unfortunate if this is driven by ads.
-
story
Ask HN: Why has ChatGPT disabled links to websites?
I was just using ChatGPT to help me pick an SDK library. It mentions a few options by name (e.g. Baileys, whatsapp-web.js), but when I click those names rather than opening a brows…
-
comment
Comment #46914298
I think I see the problem… and a possible solution. I think the main problem with attempting to document this is that the system would not be running off of it. Your infrastructure…
-
comment
Comment #46810159
For something like tests, where I have very specific opinions on how I want them written, I have a simple doc (tests.md) and I’ll regularly tag Claude with it. Claude writes a bunc…
-
comment
Comment #46747936
antirez — how do you reliably get Claude to re-read the file after compaction? It's easy to let Claude run for awhile, it compacts and starts getting much worse after compaction, a…
-
comment
Comment #46654754
Run your own server for GitHub Actions. There is a simple library they have you install so your runner gets registered with your repo. Then you can SSH in whenever a job fails. Thi…
-
comment
Comment #46518757
Here are two of mine: Volumetric displays: https://youtu.be/na7pvihXhYs?si=cIWIk2yrv-WVbe4x Physically adaptive desktop: https://tangible.media.mit.edu/project/transform-as-dynamic…
-
comment
Comment #46518656
I don’t lock down my kids computer use. I know risks exist, but I think their unrestricted access to computers and the internet is far more beneficial than harmful. I know I’m high…
-
story
Ask HN: What are the most futuristic computing interfaces you've seen?
What are the most futuristic computing interfaces you can think of, that just aren’t widespread yet? (In line with Gibson’s famous quote that, "The future is already here—it's just…
-
comment
Comment #46502520
(1) and (2) are good points. Particularly 2 because movies may intentionally add steps / slow things down so that a viewer can follow along but this would be at odds to daily use. …
-
comment
Comment #46502481
My assumption is a bit different: the UIs in science fiction are intended to communicate information, now typically that's to advance the storyline but there's a lot of overlap wit…
-
comment
Comment #46500996
I've been keeping an eye on the SDKs for Meta glasses and Even Realities, but they don't yet support much access.
-
story
Ask HN: Why don't sci-fi interfaces ever turn into real products?
Is there a good reason why the UI we see in sci-fi don't make it into actual products? Maybe there is some true limitation inherent in this style UI which causes them to stay as me…
-
comment
Comment #46405010
What does it say about moving to cash now? :)
-
story
Show HN: Voice-first todo list that updates live as you talk
I built a demo of a voice AI task manager. You speak naturally and it updates your visible task list in real time. Try it here, no sign up: https://taskmaster.keithschacht.com I fi…
-
comment
Comment #46016548
I find most human agents can only produce high quality tests if you give them detailed guidance and good starting examples. :)
-
comment
Comment #45520030
Since you are convinced you’re using the tools to their full potential, the quality problem you experience is 100% the tools fault. This means there is no possible change in your o…
-
comment
Comment #45515690
Yes, most days I’m 2x as productive. I’m using Claude Code to produce extremely high quality code that closely follows my coding standards and the architecture of my app.
-
comment
Comment #45515646
You aren’t entertaining the possibility that some experienced engineerings are using these tools to produce incredibly high quality code, while still massively increasing productiv…
-
comment
Comment #45515621
Simon, I think this is a good distinction. Another possible term could be: “agent engineering management” or simply “agent managing.” I am deep in this and one important way in whi…