Viewing profile — h-bradio
h-bradio
HN member- Joined
- Fri, Apr 21, 2023, 2:10 PM UTC
- HN karma
- 19
- Public activity
- 9 items
- HN profile
- View on Hacker News ↗
About h-bradio
No profile information was provided.
Recent public activity
-
comment
Comment #45375002
Here's a great piece from Ian Bogost in The Atlantic on this topic (gift link): https://www.theatlantic.com/technology/archive/2015/11/progr... (Please focus on his discussion of P…
-
comment
Comment #44977153
This is a fun little set of commands to run live-captioning on my Macbook! Nothing serious. A tutorial and demo video are in the link. I saw a post on HN that introduced me to Whis…
- story
-
comment
Comment #44739924
Here is how my prompt ended up! https://gist.github.com/hbradio/2f504c3fdb6f7113181b2d8c6862... I just asked an LLM to make it similar to a working Qwen prompt. To make the LLMs ab…
-
comment
Comment #44725090
Thanks so much for this! I updated LM Studio, and it picked up the mlx-lm update required. After a small tweak to tool-calling in the prompt, it works great with Zed!
-
comment
Comment #44605129
OP here! Going into it, I definitely agreed and thought that easily fact-checkable claims would be the minority. But as I worked, I found that many of his claims were "this paper s…
-
comment
Comment #44605118
OP here! Thanks for calling out this important point. As I fact-checked each claim, I was surprised at how many of the checks were "does the paper he's citing say what he says it d…
-
comment
Comment #44604984
OP here -- thanks for your reply! You're exactly right! I included the NYT/PolitiFact graph at the top as an example of that problem. In the second half of the post, I propose what…
- story