Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Silent 1024-Token Ceiling Breaking Your Local Ollama Agents
colonistone_34 profile

The Silent 1024-Token Ceiling Breaking Your Local Ollama Agents

#ollama #ai #llm #agents
Comments
5 min read
DPO vs SimPO: What Your Preference Trainer Is Actually Optimizing
natnael_alemseged profile

DPO vs SimPO: What Your Preference Trainer Is Actually Optimizing

#ai #llm #finetuning #machinelearning
1
Comments
6 min read
The Making of a 10x Engineer in AI Era: Why Big-O Thinking Changes Everything
Cover image for The Making of a 10x Engineer in AI Era: Why Big-O Thinking Changes Everything
titon profile
Tito

The Making of a 10x Engineer in AI Era: Why Big-O Thinking Changes Everything

#llm #algorithms #computerscience #beginners
4
Comments
4 min read
How I added LLM fallback to my OpenAI app in 10 minutes
jayrai profile
Jay

How I added LLM fallback to my OpenAI app in 10 minutes

#python #llm #openai #tutorial
Comments
3 min read
All Data and AI Weekly #240-04 May 2026
Cover image for All Data and AI Weekly #240-04 May 2026
timothy_spann_a41a639e47c profile

All Data and AI Weekly #240-04 May 2026

#llm #ai #mcp #agenticai
5
Comments
13 min read
Mistral Medium 3.5 Review: A 128B Open-Weight Model With a Coding Agent That Opens PRs For You
techsifted profile

Mistral Medium 3.5 Review: A 128B Open-Weight Model With a Coding Agent That Opens PRs For You

#mistral #opensourceai #openweight #llm
Comments
9 min read
LLM Foundry: the boring stack that makes an LLM actually useful
aman_sachan_126d19c4a2773 profile

LLM Foundry: the boring stack that makes an LLM actually useful

#ai #llm #openai #anthropic
5
Comments
3 min read
A Semantic Kernel Alternative for .NET — When and Why You'd Reach for One
Cover image for A Semantic Kernel Alternative for .NET — When and Why You'd Reach for One
logicgriddev profile

A Semantic Kernel Alternative for .NET — When and Why You'd Reach for One

#dotnet #csharp #ai #llm
Comments
5 min read
I wrote a custom CUDA inference engine to run Qwen3.5-27B on $130 mining cards
haru-neo profile

I wrote a custom CUDA inference engine to run Qwen3.5-27B on $130 mining cards

#ai #llm #opensource
1
Comments
5 min read
Building Production-Ready AI Agents in 2026: What Breaks, What Works, and What Nobody Tells You
xidao profile
Xidao

Building Production-Ready AI Agents in 2026: What Breaks, What Works, and What Nobody Tells You

#aiagents #llm #mcp #productionengineering
Comments
6 min read
The Council has Decided
mgbec profile

The Council has Decided

#llm #awscognito #agents #bedrockagentcore
Comments
5 min read
Entrené mi propio LLM desde cero en 2025: lo que el tutorial viral de HN no te dice sobre el costo real
Cover image for Entrené mi propio LLM desde cero en 2025: lo que el tutorial viral de HN no te dice sobre el costo real
jtorchia profile

Entrené mi propio LLM desde cero en 2025: lo que el tutorial viral de HN no te dice sobre el costo real

#spanish #espanol #llm #ia
1
Comments
10 min read
I Built My Own Entropy Coder Because Deflate Doesn't Know What GN Knows
Cover image for I Built My Own Entropy Coder Because Deflate Doesn't Know What GN Knows
atomsrkuul profile

I Built My Own Entropy Coder Because Deflate Doesn't Know What GN Knows

#rust #compression #algorithms #llm
1
Comments
3 min read
Stop Using AI Only to Build—Start Using It to Break Your Systems
swapneswar_sundarray profile

Stop Using AI Only to Build—Start Using It to Break Your Systems

#ai #softwareengineering #llm
1
Comments
4 min read
Stop Starting From Scratch: How Claude Projects Will Change the Way You Work
Cover image for Stop Starting From Scratch: How Claude Projects Will Change the Way You Work
abdlrahmansaberabdo profile

Stop Starting From Scratch: How Claude Projects Will Change the Way You Work

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