TylerHilbert/PyTorchConference2025_GithubRepos
Viewer • Updated • 117 • 144 • 1
Tyler Hilbert
TylerHilbert
AI & ML interests
Performance Testing
Recent Activity
updated a dataset 5 days ago
TylerHilbert/PyTorchConference2025_GithubRepos liked a dataset 14 days ago
blanchon/EuroSAT_RGB liked a dataset 17 days ago
lc-col/bigearthnetOrganizations
None yet
updated a
dataset 5 days ago
liked a
dataset 14 days ago
liked 2
datasets 17 days ago
liked a
dataset 21 days ago
updated a
dataset 27 days ago
published a
dataset 27 days ago
updated a
dataset 29 days ago
updated a
dataset about 2 months ago
published a
dataset about 2 months ago
Advice for OpenCL
1
#3 opened 3 months ago
by TylerHilbert
commented a
paper 3 months ago
upvoted an article 3 months ago
Article
OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments
- +3
christian-washington, ajasuja, santosh-iima, lewtun, burtenshaw
• • 32 commented a
paper 3 months ago
upvoted 2
papers 3 months ago
liked a
dataset 3 months ago
upvoted an article 3 months ago
Article
We Got Claude to Build CUDA Kernels and teach open models!
- +2
burtenshaw, evalstate, merve, pcuenq
• • 156 commented on From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output 3 months ago
Thanks for sharing.
It makes sense the constrained decoding would create the best results for generating valid json.
I was wondering if you have any thoughts on using constrained decoding for generating code for compiled languages, such as C++. Could you utilize a compiler as feedback for the constrained decoder, and if so, would the generated code likely be correct?
liked a
dataset 3 months ago