Trending

LLMs replacing human participants harmfully misportray, flatten identity groups

Show HN: I compressed 10k PDFs into a 1.4GB video for LLM memory

The Trackers and SDKs in ChatGPT, Claude, Grok and Perplexity

Cerebras achieves 2,500T/s on Llama 4 Maverick (400B)

Claude 4 vs. Gemini 2.5 Pro: A Developer's Deep Dive Comparison

Tokenization for language modeling: BPE vs. Unigram Language Modeling (2020)

What is currently the best LLM model for consumer grade hardware? Is it phi-4?

I let Claude Code write an entire book

Human coders are still better than LLMs

[D] LLM Generated Research Paper

[R] System Prompt Learning: A Third Paradigm for LLM Learning Beyond Pretraining and Fine-tuning

Request for AI agent

Allowing LLM to ponder in Open WebUI

25L Portable NV-linked Dual 3090 LLM Rig

Consuming 1 billion tokens every 3 days | Here's what we have learnt

Let's build a production level Small Language Model (SLM) from scratch | 3 hour workshop

104k-Token Prompt in a 110k-Token Context with DeepSeek-R1-0528-UD-IQ1_S – Benchmark & Impressive Results

Views on recent acceptance of LLM written paper at ACL main [D]

DeepSeek

Save item

DeepSeek-R1-0528-Qwen3-8B

Task: text-generation

ByteDance Seed

Save item

BAGEL-7B-MoT

Fractal AI Research

Save item

Fathom-R1-14B

Task: text-generation

osmosis

Save item

Osmosis-Structure-0.6B

Mistral AI_

Save item

Devstral-Small-2505

Task: text2text-generation

Tongyi-Zhiwen

Save item

QwenLong-L1-32B

Unsloth AI

Save item

DeepSeek-R1-0528-GGUF

Task: text-generation

Unsloth AI

Save item

DeepSeek-R1-0528-Qwen3-8B-GGUF

Task: text-generation

Nari Labs

Save item

Dia-1.6B