DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Told My LLM Critic to Be Adversarial. It Started Blocking Plans for Being 'Not Thorough Enough.'

Code-enforced allowlists fix prompt drift
debashish_ghosal profile

I Told My LLM Critic to Be Adversarial. It Started Blocking Plans for Being 'Not Thorough Enough.'

#ai #adversarial #llm #promptengineering
7
Comments 9
4 min read
My first website said "Don't commit without context." I never committed it at all.
earlgreyhot1701d profile

My first website said "Don't commit without context." I never committed it at all.

#buildinpublic #ai #webdev #beginners
7
Comments 2
7 min read
I Built a Personal AI That Actually Knows My Projects (RAG + Ollama, Zero Cloud)
samhartley_dev profile

I Built a Personal AI That Actually Knows My Projects (RAG + Ollama, Zero Cloud)

#ai #rag #ollama #selfhosted
Comments
5 min read
The best argument against my MCP server came from Anthropic
heinrichneb profile

The best argument against my MCP server came from Anthropic

#ai #mcp #career #programming
Comments 2
9 min read
Pi Agent vs OpenCode after 100+ Hours of Real Use ✌️
shricodev profile

Pi Agent vs OpenCode after 100+ Hours of Real Use ✌️

#ai #productivity #opensource #architecture
14
Comments 5
15 min read
Knowledge and Intelligence ARE Mutually Exclusive.
wiseai profile

Knowledge and Intelligence ARE Mutually Exclusive.

#ai #llm #lmm
Comments
42 min read
Intelligence at Rest
wiseai profile

Intelligence at Rest

#ai #lmm #llm
Comments 2
34 min read
The Proxy I Added to Measure Tokens Tripled Them
hexisteme profile
John

The Proxy I Added to Measure Tokens Tripled Them

#agents #ai #llm #tooling
Comments
8 min read
The cheapest model on my plan loses every benchmark. It still beats models charging 14x more.
dev_michael profile

The cheapest model on my plan loses every benchmark. It still beats models charging 14x more.

#discuss #ai #programming #webdev
2
Comments 2
5 min read
Leveling up OpenCode... and not in the way you would expect.
searay_11_254650fe8d2b6b6 profile

Leveling up OpenCode... and not in the way you would expect.

#ai #productivity #opensource #agents
2
Comments
2 min read
I Ran 157 Agent Plans Against a Real LLM. The Problem Wasn't Execution. It Was Planning.

Explores why self-review fails agents
debashish_ghosal profile

I Ran 157 Agent Plans Against a Real LLM. The Problem Wasn't Execution. It Was Planning.

#ai #agentskills #fieldtest #development
20
Comments 12
8 min read
I translated DOOM from C to Rust in 23 seconds, then used AI for what it is good at
efraingaray profile

I translated DOOM from C to Rust in 23 seconds, then used AI for what it is good at

#showdev #rust #programming #ai
Comments
3 min read
Your CLAUDE.md is full of wishes: 7 rungs that make a rule stick
michael_rakutko profile

Your CLAUDE.md is full of wishes: 7 rungs that make a rule stick

#ai #claude #agents #testing
Comments 2
6 min read
We put an AI helper in our course and spent weeks teaching it to say I don't know
academy_agineai profile

We put an AI helper in our course and spent weeks teaching it to say I don't know

#ai #machinelearning #programming
Comments 1
4 min read
Your Voice Agent Needs Three Exits, Not One
nabeelbaghoor profile

Your Voice Agent Needs Three Exits, Not One

#ai #architecture #automation #devjournal
Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.