DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Who is nondeterministic, the model or the human?
khunjua profile

Who is nondeterministic, the model or the human?

#discuss #ai #computerscience #llm
5
Comments
8 min read
Convert Word (DOCX) to Markdown With Python (Standard Library Only) for LLM Prompts and Chatbot Knowledge
appierun_66 profile

Convert Word (DOCX) to Markdown With Python (Standard Library Only) for LLM Prompts and Chatbot Knowledge

#python #markdown #llm #tutorial
Comments
14 min read
vLLM Fast Start Explained: What Preload and Snapshots Save, What They Cannot, and the Fingerprint Gap
wolfsea2357 profile

vLLM Fast Start Explained: What Preload and Snapshots Save, What They Cannot, and the Fingerprint Gap

#ai #machinelearning #llm #vllm
Comments
14 min read
What our analytics SDK receives from your server, field by field
getmcpulse profile

What our analytics SDK receives from your server, field by field

#ai #llm #mcp #privacy
Comments
5 min read
Building Production Features with the Claude API in Java
said_olano profile

Building Production Features with the Claude API in Java

#java #ai #llm #architecture
Comments
6 min read
What counts as feedback in weight-space programming?
panditshivam profile

What counts as feedback in weight-space programming?

#ai #machinelearning #llm #research
Comments
3 min read
Stop Trusting Vibes: Build a Minimal LLM Eval Harness Before You Claim Your Model Got Better
eme_gug_0821b41b948be6516 profile

Stop Trusting Vibes: Build a Minimal LLM Eval Harness Before You Claim Your Model Got Better

#llm #python #machinelearning #testing
Comments
8 min read
json.dumps Writes NaN by Default: 31 LLM Reports JSON.parse Rejected
ji_ai profile

json.dumps Writes NaN by Default: 31 LLM Reports JSON.parse Rejected

#python #llm #ai
Comments
6 min read
How to Secure a Local LLM Relay Listening on *:4000
orca_forge profile

How to Secure a Local LLM Relay Listening on *:4000

#llm
Comments
5 min read
Enterprise AI spend hits $177B as agents become the biggest consumers of model tokens
delimitter profile
News

Enterprise AI spend hits $177B as agents become the biggest consumers of model tokens

#agents #ai #llm
Comments
2 min read
Anthropic cuts agent request payloads from 800 KB to 1.8 KB with Message Threads in public beta
delimitter profile
News

Anthropic cuts agent request payloads from 800 KB to 1.8 KB with Message Threads in public beta

#agents #api #llm #performance
Comments
2 min read
Turn 10 of a 50K-token chat waits 5 seconds, not 49: the prefix cache on RTX Spark, and whether the code compiles
steefjan_wiggers_34a415b profile

Turn 10 of a 50K-token chat waits 5 seconds, not 49: the prefix cache on RTX Spark, and whether the code compiles

#ai #windows #llm #ollama
Comments
13 min read
A 763B MoE on a 12 GB GPU: Our Speed Ceiling Versus What Strata Reports, and What Closes the Gap
ginigen_ai_010d9180cbbdb1 profile

A 763B MoE on a 12 GB GPU: Our Speed Ceiling Versus What Strata Reports, and What Closes the Gap

#ai #machinelearning #edgeai #llm
Comments
13 min read
How ChatGPT Actually Finds Your Page: A Developer's Walkthrough of RAG
asad_abdullah_zafar profile

How ChatGPT Actually Finds Your Page: A Developer's Walkthrough of RAG

#ai #webdev #seo #llm
Comments
3 min read
Hydrogen-1.0 MIT Open Weights: Gated BF16, NVFP4 262K Context Cliff, and Vendor FSR vs GPT-6 Astra
yong_yu_f98e15562e9b120a0 profile

Hydrogen-1.0 MIT Open Weights: Gated BF16, NVFP4 262K Context Cliff, and Vendor FSR vs GPT-6 Astra

#ai #llm #opensource #machinelearning
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.