NLP

📝 NLPSpecific

Natural Language Processing, Text Analysis, Language Models, Transformers

Feeds to Scour
SubscribedAll
Scoured 504 posts in 6.9 ms

RATrain: A Resource-Aware Training Runtime for Large Language Models on Bandwidth-Constrained Heterogeneous Supercomputing Platforms

 🤖LLMs  Content type: Academic
arxiv.org·
Less-relevant results

Pro Wrestlers Are Fighting in Libraries Now, and It’s Actually for a Good Cause

 🤖LLMs  Content type: News
vice.com·

emollick/concord: Instrument-grade qualitative text analysis: AI-coded corpora, gold calibration, DSL/PPI-corrected statistics, Evidence Ladder

 🤖LLMs  Content type: Code
github.com·

I built a sentiment analyzer for Hacker News (as an MCP server)

 🔄DevOps
mcpize.com··Hacker News

Pathetic pretense

 🟠Svelte  Content type: Blog
freethoughtblogs.com·

Why tokenization is an ETF-style market structure revolution

 ⛓️Blockchain
coindesk.com·

Tokenization Exec Predicts An All-Blockchain Wall Street by 2030

 ⛓️Blockchain
pymnts.com·

What are AI parameters — and why does everyone keep talking about billions of them?

 🤖LLMs  Content type: Blog
medium.com·

NBC Nightly News With Tom Llamas : KNTV : June 4, 2026 4:00pm-4:30pm PDT : Free Borrow & Streaming

 🤖LLMs  Content type: Video
archive.org·

Apples to Apples: MLX vs. Llama.cpp for Gemma 4 12B on an M1 16GB

 🦙Ollama  Content type: Blog
ziraph.com··Hacker News

BeeLlama.cpp DFlash on Strix Halo: 2.7x Gemma 31B, But MTP Is Still Faster

 🤖LLMs
sleepingrobots.com·

The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring

 🤖LLMs  Content type: Academic
arxiv.org·

NVIDIA releases Nemotron 3 Ultra, claiming five times the speed and 30 percent lower costs than prior modelsThe model delivers 300 tokens per second on benchmar...

 🤖Transformers
digg.com·

Apex Group Joins Tokenized Real Estate Fund on Goldman Sachs Platform

 ⛓️Blockchain
cointelegraph.com·

BioMedGraphica: An All-in-One Platform for Joint Textual Biomedical Prior Knowledge and Numeric Graph Generation

 🗂️Data Structures
academic.oup.com
·

Using local LLMs for agentic coding

 🤖LLMs  Content type: Blog
blog.alexewerlof.com·

Wall Street will run entirely on the blockchain by 2030, says Brickken CEO

 ⛓️Blockchain  Content type: News
coindesk.com·

KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

 🤖LLMs  Content type: Code
github.com··Hacker News

Wrestling matches provide an action-packed story time at US libraries, in photos

 🤖LLMs  Content type: News
independent.co.uk·

Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM

 ☕Java
deemwar-products.github.io··Hacker News

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help