Viewing profile — bconsta
bconsta
HN member- Joined
- Wed, Dec 06, 2023, 2:54 AM UTC
- HN karma
- 29
- Public activity
- 11 items
- HN profile
- View on Hacker News ↗
About bconsta
No profile information was provided.
Recent public activity
-
comment
Comment #48839958
Kind of ironic considering Anthropic hasn't even been around for 7 years.
-
comment
Comment #48700216
Too similar to Goldfinger cheating at cards and golf to not make me chuckle.
-
comment
Comment #48405105
Seems ironic that Claude isn't listed as a contributor to this article. If was used in writing the article, why not list it? If it wasn't used, that seems to go against Anthropic's…
-
comment
Comment #46170080
David Graeber in three lines
-
comment
Comment #45477945
I had no idea about this. Thanks for sharing
-
comment
Comment #45476557
There is a study that gives a rule of thumb of ~2 bits per param for a model's memorization capacity: https://arxiv.org/abs/2404.05405
-
comment
Comment #45188428
Pixel 9a is probably the closest to what you're describing on the market today.
-
comment
Comment #44242741
If I'm not mistaken, the idea is use MCP to let a user-facing LLM make tool calls to a VLA model with actions the user prescribes. He mentions using the LeRobot library in another …
-
comment
Comment #44011168
pareto adequate
-
comment
Comment #43500444
Following along these lines, I asked chatgpt to come up with a term for 'haboginking a habogink'. It understood this concept of a 'gorbink' and even 'haboginking a gorbink', but fa…
- comment