Mushroom hunting with LLMs: what can go wrong? (quesma.com)

Screenshot of quesma.com: Mushroom hunting with LLMs: what can go wrong?

First screen, captured 1 month ago.

Looks similar

Screenshot of mrzk.io: Fixed three bugs that made Qwen3.5-122B a daily driver on Mac Studio

Fixed three bugs that made Qwen3.5-122B a daily driver on Mac Studio (mrzk.io)

55 points by marzukia 3 months ago | 22 comments

Screenshot of dylancastillo.co: Honey, I shrunk the embeddings: Matryoshka vs. PCA

Honey, I shrunk the embeddings: Matryoshka vs. PCA (dylancastillo.co)

60 points by dcastm 2 months ago | 12 comments

Screenshot of thariq.io: Detecting when LLMs are uncertain

Detecting when LLMs are uncertain (thariq.io)

257 points by trq_ 2 years ago | 148 comments

Screenshot of ghuntley.com: Unikernels were hard. key word: were

Unikernels were hard. key word: were (ghuntley.com)

177 points by ghuntley 16 days ago | 89 comments

Geoffrey Huntley blog post recounting a conversation with Justin Cormack about why unikernels are becoming practical again and their security benefits.

unikernels mirageos operating-systems security

Screenshot of sebastianraschka.com: Optimizing LLMs from a Dataset Perspective

Optimizing LLMs from a Dataset Perspective (sebastianraschka.com)

126 points by alexmolas 3 years ago | 23 comments

Screenshot of changyi.fun: Attention Through Arithmetic Intensity

Attention Through Arithmetic Intensity (changyi.fun)

13 points by jxmorris12 2 months ago | 0 comments

Looks similar

Fixed three bugs that made Qwen3.5-122B a daily driver on Mac Studio(mrzk.io)

Honey, I shrunk the embeddings: Matryoshka vs. PCA(dylancastillo.co)

Detecting when LLMs are uncertain(thariq.io)

Unikernels were hard. key word: were(ghuntley.com)

Optimizing LLMs from a Dataset Perspective(sebastianraschka.com)

Attention Through Arithmetic Intensity(changyi.fun)