StealthEval: A Probe-Rewrite-Evaluate Workflow for Reliable Benchmarks
arxiv.org·1d
🌿Minimalism
💡 What's new in txtai 9.0
dev.to·6d·
Discuss: DEV
🎨Drawing
Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts
bilawal.net·2d·
Discuss: Hacker News
🎨Drawing
Image Encoding Using AutoGrad
aschrein.github.io·4d·
Discuss: Hacker News
🎨Drawing
Incremental query updating in adhesive categories
topos.institute·3d
🛋Interior Design
Compilation vs. vectorization, search engine edition
jpountz.github.io·6d·
Discuss: Hacker News
📵Digital Detox
Song recommendations with C# free monads
blog.ploeh.dk·3d
🎨Drawing
Effective learning: Twenty rules of formulating knowledge (1999)
supermemo.com·2d·
Discuss: Hacker News
🎨Drawing
Thrifty wide-context models of B cell receptor somatic hypermutation
elifesciences.org·6d
📵Digital Detox
Polynomial Chaos Expansion for Operator Learning
arxiv.org·6d
🎨Drawing
Convolutional Denoising Autoencoders for Diagnostic Images
haydenramm.bearblog.dev·21h
🎨Drawing
LongCat-Flash, a language model with 560B total parameters, MoE architecture
github.com·4d·
Discuss: Hacker News
🎨Drawing
I’ve been working on something new:
threadreaderapp.com·6d
🎨Drawing
LLMs are Bayesian, in Expectation, not in Realization
researchgate.net·1d·
Discuss: Hacker News
🎨Drawing
The use of Claude Code in SciML repos
discourse.julialang.org·5d·
Discuss: Hacker News
🎨Drawing
Forcing ChatGPT to Obey: Minimal and Deterministic Rules
dev.to·4d·
Discuss: DEV
🌿Minimalism
Your LLM is too large: How I generate production-ready failure analysis on a toaster
developers.redhat.com·2d
🌿Minimalism
Postit 2025-09-04 09:03:07
dinandmentink.nl·1h
🎨Drawing
The Missing Error Bars in AI Research That Nobody Talks About.
lesswrong.com·9h
🎨Drawing
Minimalist Model for Impossible Differentials
eprint.iacr.org·5d
🎨Drawing