DEV Community

#llms

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Model That Trained Itself: 56% of Real GitHub Issues at 1/50th the Price

The Model That Trained Itself: 56% of Real GitHub Issues at 1/50th the Price

Comments
6 min read
40 GB to 6.7 GB: The 3-Bit Trick That Shrinks Your KV Cache 6x

40 GB to 6.7 GB: The 3-Bit Trick That Shrinks Your KV Cache 6x

1
Comments 1
5 min read
Linus Torvalds defends the use of artificial intelligence by Linux developers

Linus Torvalds defends the use of artificial intelligence by Linux developers

Comments
2 min read
Why Vector Databases Need Approximate Nearest Neighbor (ANN): HNSW Graphs and the Curse of Dimensionality

Why Vector Databases Need Approximate Nearest Neighbor (ANN): HNSW Graphs and the Curse of Dimensionality

1
Comments
5 min read
Non-Determinism Doesn't Matter

Non-Determinism Doesn't Matter

Comments 3
3 min read
Streamlining Kubernetes Pod Crash Debugging: Overcoming Log Overload and Inefficient Methods

Streamlining Kubernetes Pod Crash Debugging: Overcoming Log Overload and Inefficient Methods

Comments
12 min read
Reflection AI’s Beam Puts Efficiency at the Center of the Open-Model Race

Reflection AI’s Beam Puts Efficiency at the Center of the Open-Model Race

Comments
5 min read
Machine Translation Advances Remain Under-Discussed Despite Near-Perfect Accuracy

Machine Translation Advances Remain Under-Discussed Despite Near-Perfect Accuracy

1
Comments
14 min read
OpenAI Kills GPT-6.1 Astra: When AI Learns to Lie, Even Its Maker Flinches

OpenAI Kills GPT-6.1 Astra: When AI Learns to Lie, Even Its Maker Flinches

Comments
4 min read
78 Billion Parameters, 3.5 Awake: Germany's Sovereign AI Just Shipped

78 Billion Parameters, 3.5 Awake: Germany's Sovereign AI Just Shipped

Comments
6 min read
Self-Hosting vs. API: Evaluating Cost-Effectiveness and Practicality for Large Language Models

Self-Hosting vs. API: Evaluating Cost-Effectiveness and Practicality for Large Language Models

1
Comments
13 min read
Drop-in Django app to serve a decent LLM-ready documentation site

Drop-in Django app to serve a decent LLM-ready documentation site

Comments
2 min read
I made my portfolio readable to AI crawlers: llms.txt, JSON-LD and a 40-method distribution stack

I made my portfolio readable to AI crawlers: llms.txt, JSON-LD and a 40-method distribution stack

Comments
3 min read
75% More Requests, Same GPUs: Why LLM Serving Runs on Two Machines Now

75% More Requests, Same GPUs: Why LLM Serving Runs on Two Machines Now

1
Comments
6 min read
Can You Copyright What AI Makes? Mostly Not — Here's Where the Line Is

Can You Copyright What AI Makes? Mostly Not — Here's Where the Line Is

Comments
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.