Viewing profile — thomashop
thomashop
HN member- Joined
- Mon, Sep 19, 2016, 12:10 PM UTC
- HN karma
- 382
- Public activity
- 227 items
- HN profile
- View on Hacker News ↗
About thomashop
Recent public activity
-
comment
Comment #48843954
I'm also a fan of the Yamanote Line. I made a psychedelic AI audio-visual collage inspired by it. https://www.youtube.com/watch?v=xwUSzUvShqcaa I made field recordings during my la…
-
comment
Comment #48049363
i thought the agent can execute real ffmpeg to compare
- story
-
comment
Comment #47567213
I don't think it's correct that we destroyed everything that isn't us. If we take all living beings, we have destroyed only a small percentage.
-
comment
Comment #45840224
Ah understood i misread
-
comment
Comment #45839338
Why is privacy a concern? You can run them in your own infrastructure
-
comment
Comment #45047316
I'm also a fan of the Yamanote Line. I made a psychedelic AI audio-visual collage inspired by it. https://www.youtube.com/watch?v=xwUSzUvShqcaa I made field recordings during my la…
-
comment
Comment #44917489
I have done quite a bit of game dev with LLMs and have very rarely run into the problem you mention. I've been surprised by how easily LLMs will create even harmful narratives if I…
-
comment
Comment #44706274
The rest was fine without citations, but the part you disagree with needs them?
-
comment
Comment #44458973
I have the impression that the thinking helps even if the actual content of the thinking output is nonsense. It awards more cycles to the model to think about the problem.
-
comment
Comment #44387113
I use AI to simplify code. My manifesto has always been code is debt. Works really well too.
-
comment
Comment #44268414
I don't care that much. This level of knowledge about me can also be easily found on the internet. I'm also working almost entirely on open-source software so I'm happy if the AIs …
-
comment
Comment #44267925
Interesting { "assistant_response_preferences": { "1": "User prefers concise responses for direct factual queries but detailed, iterative explanations when exploring complex topics…
-
comment
Comment #44172624
[flagged]
-
comment
Comment #44052889
Who runs python code on mobile?
-
comment
Comment #44049803
The AI is not paying for watching videos yet
-
comment
Comment #43914709
But aren't they getting this data already at a much larger scale? GPT is still one of the backbones in many coding assistants, even Windsurf.
-
comment
Comment #43914573
I'm pretty sure the model is cached with the system prompt already processed. So you should only pay extra tokens.
-
comment
Comment #43451810
"I cannot emphasize this enough: ChatGPT is not generating meaning. It is arranging word patterns. I could tell GPT to add in an anomaly for the 1970s - like the girl looking at Bi…
-
comment
Comment #43089482
It always feels like people are irrationally critical of AI assisted stuff. Does the typical Hacker News comment have more substance? - Informally benchmarked against 4 specific co…
-
comment
Comment #43089339
Why sorry? So what? I often write things I want to post in bullets and then have it formulated better than I could by an LLM. But its just applying a style. The content comes from …
-
comment
Comment #42838569
It feels like we've been moving in the opposite direction, where more and more models from various countries are state-of-the-art. The idea that there will be one model to rule the…
-
comment
Comment #42522920
Sure. You can always write more tests. That's not a problem specific to AI. I'd also do code reviews on the code AI produces.
-
comment
Comment #42522803
Why not write tests with AI, too? Since using LLMs as coding assistants, my codebases have much more thorough documentation, testing and code coverage. Don't start when you're alre…
-
comment
Comment #42507019
> And that's just hooey. Well, I mean Google animism. It's hooey from your point of view.