Building Moon Bot: A Slack-Native Coding Agent Backed by HuggingFace Buckets
• 46
AI & ML interests
The AI community building the future.
Recent Activity
View all activity
Papers
Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
Qualixar OS: A Universal Operating System for AI Agent Orchestration
Articles
tarekziade
updated a
bucket about 10 hours ago
alvarobartt
updated a
dataset about 11 hours ago
glutamatt
updated a
bucket about 13 hours ago
glutamatt
published a
bucket about 13 hours ago
glutamatt
updated a
bucket about 15 hours ago
glutamatt
published a
bucket about 15 hours ago
sayakpaul
updated a
dataset 2 days ago
eustlb
updated a
bucket 2 days ago
sayakpaul
authored 3
papers 2 days ago
sayakpaul
submitted a
paper to Daily Papers 2 days ago
jeffboudier
posted an update 9 days ago
Post
131
@alvarobartt published a step-by-step guide to deploy zai-org/GLM-5.2 on AMD GPUs, using newly released features in Microsoft Foundry. The FP8 model fits on a single node of MI300X GPUs, which cuts the bill in half vs. H100.
https://alvarobartt.com/goal-glm-5.2-on-foundry/
https://alvarobartt.com/goal-glm-5.2-on-foundry/
AdinaY
submitted a
paper to Daily Papers 11 days ago
evijit
authored a
paper 12 days ago
Post
142
We have recently added Torch Stable ABI support to kernels and kernel-builder. This allows kernel developers to target a particular Torch version and the kernel will be supported on that Torch version and later Torch versions (up to ~2 years).
This makes it much easier to write kernels with long-term support and not just the last two Torch releases.
We have also started rolling out Stable ABI support to kernels in kernels-community, starting with Flash Attention 3, supporting Torch 2.9 and later as well as CUDA versions starting at 12.6:
https://huggingface.co/kernels/kernels-community/flash-attn3/tree/v1/build
This makes it much easier to write kernels with long-term support and not just the last two Torch releases.
We have also started rolling out Stable ABI support to kernels in kernels-community, starting with Flash Attention 3, supporting Torch 2.9 and later as well as CUDA versions starting at 12.6:
https://huggingface.co/kernels/kernels-community/flash-attn3/tree/v1/build
- 1 reply
irenesolaiman
authored a
paper 12 days ago
Post
376
Uhh did Opus 4.8 cheat on PostTrainBench??
it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913
Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace
it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913
Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace
- 1 reply
AdinaY
submitted 2
papers to Daily Papers 26 days ago