Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
1.
Context is essential for AI agents, but I think shared state is the next problem (github.com/Abloatai)
2 points
lukasanderss
3 days ago
1 comment
2.
Time Ablation Experiments on tau2-bench (github.com/sshh12)
3 points
sshh12
5 months ago
discuss
3.
Show HN: Toolkit for LLM Fine-Tuning, Ablating and Testing (github.com/georgian-io)
14 points
rsaha7
2 years ago
21 comments
4.
Show HN: Implementation and ablation of the Hierarchical Reasoning Model (HRM) (github.com/krychu)
2 points
krychu
9 months ago
discuss
5.
Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (github.com/antoinezambelli)
687 points
zambelli
16 days ago
252 comments
6.
Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs (github.com/Tsadoq)
140 points
tsadoq
a year ago
52 comments
7.
Show HN: Desbordante 2.0 – A high-performance data profiler (github.com/Desbordante)
67 points
chernishev
2 years ago
14 comments
8.
Show HN: Chonky – a neural text semantic chunking goes multilingual (huggingface.co)
43 points
hessdalenlight
7 months ago
6 comments
9.
Show HN: A tiny reasoning layer that steadies LLM outputs (MIT; +22.4% accuracy) (github.com/onestardao)
6 points
TXTOS
10 months ago
discuss
10.
HRNet; the most powerful new vision CNN architecture to come out since AlexNet!
3 points
timscarfe
7 years ago
discuss
11.
Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs
2 points
dnosoz
a month ago
4 comments
12.
Show HN: SoMatic – Vision-based OS automation framework for AI agents (github.com/Smyan1909)
2 points
smyansondur
14 days ago
discuss
13.
Show HN: FT-Lab – Lightweight TinyLlama Fine-Tuning (Full FT / LoRA / QLoRA) (github.com/REICHIYAN)
2 points
Sai-HN
6 months ago
discuss
14.
MiRAGE: Open-source framework for multimodal RAG evaluation
1 point
mmhetric
4 months ago
discuss
15.
Show HN: WLM – A 70B model trained to decode "I'm fine" with 94.7% accuracy (github.com/gabewillen)
1 point
gwillen85
4 months ago
discuss
16.
Show HN: FT-Lab – Lightweight TinyLlama Fine-Tuning (Full FT / LoRA / QLoRA) (github.com/REICHIYAN)
1 point
Sai-HN
6 months ago
discuss
17.
New QA system released open source with reviews (github.com/bernhard2202)
2 points
ablation125
7 years ago
discuss