nutanc
Joined 16 years ago
Karma
1,078
Submissions
525
Member since
Sep 17
Chief Innovation Officer of Ozonetel Systems. Currently working on AI and ML stuff.
View on Hacker NewsRecent submissions
Comment · 9 hours ago
I don't think weight space interpretability is the only thing. I think it's the fact that Astra(and apparently Opus 5.5) can directly read the weights and find patterns and make changes. Writing code for interpretability is one thing. I think this approach shows models now understand weights directly without tools.
Comment · 1 month ago
Would this means remotion etc are not needed?
Comment · 3 months ago
This is awesome. I am trying to build a full scale ASR system within 20-25MB. Now that we have Claude code to run experiments, I have started running some experiments. Promising results so far. First realization is that you can capture the nuances of speech in just 3300 embedding vectors(786d). This sequence can be decoded with a small CTC system to get text. Next experiments are on reducing the 768 dimension space into a 64D space. Thats also show some promising results. Hooking up my system so that the agent blogs the results everyday[1]. So my research "claw" setup does the experiments and posts results which I check in the morning and adjust the experiment direction as needed. Its not fully automated yet, but almost there.
[1] https://blog.trulm.com/posts/speech-as-independent-parts/
Comment · 5 months ago
You can get very close to a working version by reverse engineering the javascript with Claude. I got a good version almost an year back. With Opus it might do a better job.
Comment · 5 months ago
Most of the problems happen because we want to simulate human conversations. While thats a good goal to have, another approach is to let the user know clearly they are talking to a bot. You will be surprised at how accomodating users can be when they know they are talking to a bot and want their queries resolved.