Viewing profile — tkellogg
tkellogg
HN member- Joined
- Tue, Nov 15, 2011, 1:18 AM UTC
- HN karma
- 1,127
- Public activity
- 245 items
- HN profile
- View on Hacker News ↗
About tkellogg
No profile information was provided.
Recent public activity
- story
-
comment
Comment #45412678
how is this self promotion? What am I promoting? This post is literally rooted in curiosity, to the core.
-
comment
Comment #45412568
Whelp, it took an hour for this to quickly rise on the front page and then get shadow banned. I guess that says something.
- story
- story
- story
- story
- story
- story
-
comment
Comment #44017816
FYI https://mcp.so/ is the exact same thing as was posted. Not sure why they directed to the github instead of the actual site..
-
comment
Comment #43958626
Somewhere in 2024 I noticed that "AI" shifted to no longer include "machine learning" and is now closer to "GenAI" but still bigger than that. It was never a strict definition, and…
- story
- story
- story
- story
- story
- story
- story
-
comment
Comment #43007291
The R1 paper did it as well. Agreed, it's always very interesting.
- story
-
comment
Comment #42937954
it's just an example, but it's great to see smolagents in practice. I wonder how well the import whitelist approach works for code interpreter security.
-
comment
Comment #42841904
Additionally, in the following days, I've seen evidence suggesting that the SFT part might not even be necessary. I'd argue that work wouldn't have happened if R1 wasn't released i…
-
comment
Comment #42830841
Ah! My bad, I edited the article to simply quote Francois. Thanks for catching this, Simon.
-
comment
Comment #42829777
Author here. I do believe it's going to be exponential (not yet), but that's out of scope for the article. However, if someone has a good explainer link for that, please put it her…
-
comment
Comment #42785100
I think their thought process is unconvincing, although I think they're probably correct. A much better paper is, "Procedural Knowledge in Pretraining Drives Reasoning in Large Lan…