Hacker News - Newest: "LLM"

Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware

albinstman — Sat, 17 Oct 2026 04:36:53 +0000

Article URL: https://llmspeed.dev/

Comments URL: https://news.ycombinator.com/item?id=50127979

Points: 39

# Comments: 11

LLM says something, my tool track if it followed its promise on tools

godcreatebugs — Fri, 16 Oct 2026 18:18:14 +0000

Article URL: https://www.raytracer.si/

Comments URL: https://news.ycombinator.com/item?id=50122209

Points: 3

# Comments: 10

A Statistical Analysis of LLM Benchmaxxing

bhu8 — Fri, 16 Oct 2026 17:35:25 +0000

Article URL: https://llemre.com/benchmaxxing/

Comments URL: https://news.ycombinator.com/item?id=50121608

Points: 1

# Comments: 1

Aura v0.1.0: Deterministic behavioral threat-intelligence for LLM safety

kate8382 — Fri, 16 Oct 2026 16:40:48 +0000

Article URL: https://medium.com/@kate8382/aura-v0-1-0-deterministic-trigger-extraction-auditable-math-a-self-healing-analytics-engine-fb96dd64b8a4

Comments URL: https://news.ycombinator.com/item?id=50120707

Points: 2

# Comments: 0

Build LLM Playground (Python, FastAPI, Gemini, React)

yatharth_verma1 — Fri, 16 Oct 2026 13:59:09 +0000

Article URL: https://www.youtube.com/watch?v=73Knur3t4M0

Comments URL: https://news.ycombinator.com/item?id=50118473

Points: 2

# Comments: 0

The evolution of LLM tool-use from API calls to agentic applications (2025)

peter_d_sherman — Fri, 16 Oct 2026 13:42:59 +0000

Article URL: https://bdtechtalks.com/2025/12/29/llm-tool-use-agentic-ai/

Comments URL: https://news.ycombinator.com/item?id=50118314

Points: 2

# Comments: 0

Your LLM is billing you for whitespace

Mojah — Fri, 16 Oct 2026 13:21:05 +0000

Article URL: https://getsnapkin.app/en/engineering/your-llm-is-billing-you-for-whitespace

Comments URL: https://news.ycombinator.com/item?id=50118078

Points: 1

# Comments: 0

Ruby classes powered by LLM batteries (Squishling)

mikecarroll — Fri, 16 Oct 2026 13:13:41 +0000

Article URL: https://coolhand-labs.github.io/squishling/

Comments URL: https://news.ycombinator.com/item?id=50117994

Points: 1

# Comments: 1

A 4B LLM learns to write tools that other LLMs can use

blackcat201 — Fri, 16 Oct 2026 08:05:22 +0000

Article URL: https://tool-use-smith.github.io/

Comments URL: https://news.ycombinator.com/item?id=50115527

Points: 2

# Comments: 0

Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio

vinhnx — Fri, 16 Oct 2026 03:34:45 +0000

Article URL: https://machinelearning.apple.com/research/mlx-distributed-inference

Comments URL: https://news.ycombinator.com/item?id=50113743

Points: 7

# Comments: 1

A tool to compare LLM benchmarks

7777777phil — Thu, 15 Oct 2026 23:09:07 +0000

Article URL: https://philippdubach.com/posts/model-atlas-capability-weights/

Comments URL: https://news.ycombinator.com/item?id=50111618

Points: 1

# Comments: 1

Show HN: Guess the LLM – read an answer and guess which model wrote it

aravindnatch — Thu, 15 Oct 2026 21:53:54 +0000

Hi HN, I made a game to test if people can really tell AI models apart.

Models from all the frontier labs answer the same question. You read one answer and guess who wrote it. You can also pick just the models you want to compare.

I made it and still only get 5/10 lol. Curious how you all do.

Comments URL: https://news.ycombinator.com/item?id=50110907

Points: 2

# Comments: 1

Show HN: Asked LLM to show the most stereotypical man/woman for each country

anvaka — Thu, 15 Oct 2026 21:42:12 +0000

Article URL: https://anvaka.github.io/imaginary-faces/#

Comments URL: https://news.ycombinator.com/item?id=50110735

Points: 2

# Comments: 2

Same LLM, same input tokens, different answers on a MacBook and a Jetson

carrieremaxime9 — Thu, 15 Oct 2026 20:09:27 +0000

Article URL: https://kernwerk.org/blog/same-model-different-board/

Comments URL: https://news.ycombinator.com/item?id=50109547

Points: 1

# Comments: 0

SGLang – High-performance serving framework for LLM's and multimodal models

peter_d_sherman — Thu, 15 Oct 2026 19:08:28 +0000

Article URL: https://github.com/sgl-project/sglang

Comments URL: https://news.ycombinator.com/item?id=50108701

Points: 1

# Comments: 0

Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio

ingve — Thu, 15 Oct 2026 17:12:48 +0000

Article URL: https://machinelearning.apple.com/research/mlx-distributed-inference

Comments URL: https://news.ycombinator.com/item?id=50106858

Points: 6

# Comments: 1

Datadog trained their own cheap SOTA SRE LLM [pdf]

ersiees — Thu, 15 Oct 2026 15:05:02 +0000

Article URL: https://web-assets.dd-static.net/42588/1792071077-datadog-scout_technical_report.pdf

Comments URL: https://news.ycombinator.com/item?id=50104758

Points: 5

# Comments: 0

LLM Addiction in Society Is Getting Out of Hand

speckx — Thu, 15 Oct 2026 14:39:37 +0000

Article URL: https://www.pashynskykh.com/blog/09588eaf/

Comments URL: https://news.ycombinator.com/item?id=50104351

Points: 1

# Comments: 0

Choosing a Chunking Strategy for Your LLM Apps: A Decision-Tree Approach

eigenBasis — Thu, 15 Oct 2026 13:19:11 +0000

Article URL: https://machinelearningmastery.com/choosing-a-chunking-strategy-for-your-llm-apps-a-decision-tree-approach/

Hacker News - Newest: "LLM"

Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware

LLM says something, my tool track if it followed its promise on tools

A Statistical Analysis of LLM Benchmaxxing

Aura v0.1.0: Deterministic behavioral threat-intelligence for LLM safety

Build LLM Playground (Python, FastAPI, Gemini, React)

The evolution of LLM tool-use from API calls to agentic applications (2025)

Your LLM is billing you for whitespace

Ruby classes powered by LLM batteries (Squishling)

A 4B LLM learns to write tools that other LLMs can use

Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio

A tool to compare LLM benchmarks

Show HN: Guess the LLM – read an answer and guess which model wrote it

Show HN: Asked LLM to show the most stereotypical man/woman for each country

Same LLM, same input tokens, different answers on a MacBook and a Jetson

SGLang – High-performance serving framework for LLM's and multimodal models

Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio

Datadog trained their own cheap SOTA SRE LLM [pdf]

LLM Addiction in Society Is Getting Out of Hand

Choosing a Chunking Strategy for Your LLM Apps: A Decision-Tree Approach

Hypotheses failures while training an LLM classifier