DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
We benchmarked 10 LLMs on 10 real agent coding tasks — here are the results
vystartasv profile
Vilius

We benchmarked 10 LLMs on 10 real agent coding tasks — here are the results

#ai #llm #benchmark #agents
Comments
2 min read
How we almost wrote off 3 models as broken — the thinking-mode tax
vystartasv profile
Vilius

How we almost wrote off 3 models as broken — the thinking-mode tax

#ai #llm #benchmark #postmortem
1
Comments
2 min read
Why Your AI Character Keeps Breaking Under Pressure (And What I Built Instead of Yet Another System Prompt)
kiro0x profile
Kiro

Why Your AI Character Keeps Breaking Under Pressure (And What I Built Instead of Yet Another System Prompt)

#ai #llm #mcp #opensource
Comments
8 min read
What 16 Parallel Claude Agents Built Around Themselves: Deconstructing Anthropic's C Compiler Experiment
vbcherepanov profile

What 16 Parallel Claude Agents Built Around Themselves: Deconstructing Anthropic's C Compiler Experiment

#agents #claude #llm #rust
Comments
12 min read
The right of an AI agent to stay silent
vbcherepanov profile

The right of an AI agent to stay silent

#llm #ai #software
Comments
8 min read
1-bit, 545 megabytes, zero API keys — local AI that beats GPT-5.4
vystartasv profile
Vilius

1-bit, 545 megabytes, zero API keys — local AI that beats GPT-5.4

#ai #llm #local #quantization
Comments
2 min read
I Built a Local AI Coding Agent on M5 Max 128GB — It Failed 164 Times Before Passing 35 Tests
josephyeo profile

I Built a Local AI Coding Agent on M5 Max 128GB — It Failed 164 Times Before Passing 35 Tests

#llm #agents #tdd #ollama
Comments
7 min read
How Stripe, Shopify, and Airbnb Build AI Harnesses
eleonorarocchi profile

How Stripe, Shopify, and Airbnb Build AI Harnesses

#ai #llm #agents
Comments
3 min read
Anthropic plugs into SpaceX's 220,000-GPU Colossus — and doubles Claude's rate limits
thegatewayguy profile

Anthropic plugs into SpaceX's 220,000-GPU Colossus — and doubles Claude's rate limits

#ai #anthropic #llm #api
1
Comments
3 min read
I Trained an LLM on 75K of My Own Messages So It Would Stop Writing Like a Chatbot
niclydon profile

I Trained an LLM on 75K of My Own Messages So It Would Stop Writing Like a Chatbot

#ai #machinelearning #llm #python
Comments
8 min read
What 11 big tech companies actually do with AI in 2026
kanywst profile
kt

What 11 big tech companies actually do with AI in 2026

#ai #productivity #engineering #llm
Comments
23 min read
tierKV: A Distributed KV Cache That Makes Evicted Blocks Faster to Restore Than GPU Cache Hits
prasanna_kanagasabai_4ae7 profile

tierKV: A Distributed KV Cache That Makes Evicted Blocks Faster to Restore Than GPU Cache Hits

#llm #rust #machinelearning #opensource
1
Comments
3 min read
Why AI Coding Agents Waste 30% of Their Tokens — And How to Fix It
kyoma_1234 profile

Why AI Coding Agents Waste 30% of Their Tokens — And How to Fix It

#agents #ai #llm #softwareengineering
Comments
6 min read
How a $0.02/Call Model Scored 78.2% on SWE-bench Verified — Beating Every Model on the Leaderboard
kyoma_1234 profile

How a $0.02/Call Model Scored 78.2% on SWE-bench Verified — Beating Every Model on the Leaderboard

#ai #llm #claude #minimax
Comments
7 min read
Stop Guessing Your RAG Quality: Automating Faithfulness Metrics with Spring AI and LLM-as-a-Judge
machinecodingmaster profile

Stop Guessing Your RAG Quality: Automating Faithfulness Metrics with Spring AI and LLM-as-a-Judge

#java #ai #llm #systemdesign
Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.