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

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I gave an AI agent a production rollback button — then spent the hackathon trying to trick it into pressing it

Unannotated tools silently bypass approval gates
prince_panchani_f971a20ec profile

I gave an AI agent a production rollback button — then spent the hackathon trying to trick it into pressing it

#wemakedevs #truefoundry #qodo #ai
28
Comments 17
17 min read
I Built an AI Name Generator Because Naming Is Harder Than It Looks
zhe_li_cb865666e61edba79d profile
zhe li

I Built an AI Name Generator Because Naming Is Harder Than It Looks

#ai #programming #tutorial #beginners
Comments
2 min read
A 7.5B model beat a 24B on my coding benchmark.
mrdushidush profile
david

A 7.5B model beat a 24B on my coding benchmark.

#showdev #ai #rust
Comments
21 min read
Google Gemini Expands Connected Apps With Dropbox, Zillow and Viator
alifar profile

Google Gemini Expands Connected Apps With Dropbox, Zillow and Viator

#ai #automation #tools #gemini
Comments
5 min read
When AI Agents Start Moving Money: Who Controls the Wallet?
azaleakuts profile
Azalea

When AI Agents Start Moving Money: Who Controls the Wallet?

#ai #cryptocurrency #agents #fintech
6
Comments 2
3 min read
One API Key for OpenAI, Claude, and Gemini LLM Classification Routing
dawnli2026 profile

One API Key for OpenAI, Claude, and Gemini LLM Classification Routing

#ai #python #architecture
Comments
5 min read
I built CleanSlate, an open-source coding agent for the IDE, CLI, and SDK
maaaz7 profile
maaaz

I built CleanSlate, an open-source coding agent for the IDE, CLI, and SDK

#ai #programming #opensource #automation
Comments
1 min read
I Ran 3 Open-Weight LLMs Head-to-Head on a 24GB Mac — One Was 3x Faster
pitambarmahato profile

I Ran 3 Open-Weight LLMs Head-to-Head on a 24GB Mac — One Was 3x Faster

#llm #benchmark #opensource #ai
2
Comments 6
5 min read
Spec-driven development with AI agents: constitutions, checkpoints, and handoffs
hannody profile

Spec-driven development with AI agents: constitutions, checkpoints, and handoffs

#agents #ai #softwaredevelopment #softwareengineering
Comments
5 min read
Benchmarking GPT-4o, Claude 3.5 Sonnet, and Llama 3 for Automated Code Auditing & Vulnerability Detection
saranyo profile

Benchmarking GPT-4o, Claude 3.5 Sonnet, and Llama 3 for Automated Code Auditing & Vulnerability Detection

#ai #cybersecurity #llm #vulnerabilities
Comments
2 min read
Nobody has shipped an LLM that grades its own draft without a human in the loop
unmannedops profile

Nobody has shipped an LLM that grades its own draft without a human in the loop

#ai #agents #devops #automation
2
Comments
2 min read
My Repo's Riskiest Regex Has Regressed Three Times on Record. It Never Got the Test Pattern I Gave Everything Else.
enjoy_kumawat profile

My Repo's Riskiest Regex Has Regressed Three Times on Record. It Never Got the Test Pattern I Gave Everything Else.

#python #debugging #ai #devtools
Comments 1
5 min read
I Thought This Was a Classification Problem. It Wasn't.
debashish_ghosal profile

I Thought This Was a Classification Problem. It Wasn't.

#healthydebate #ai #llm #testing
12
Comments
6 min read
False Completion Is the Real Failure Mode of Coding Agents
giladha profile

False Completion Is the Real Failure Mode of Coding Agents

#ai #programming #softwaredevelopment #agents
1
Comments 11
7 min read
Open Knowledge Format vs RAG: Why Your Agent Should Read a Wiki
designly profile

Open Knowledge Format vs RAG: Why Your Agent Should Read a Wiki

#ai #agents
3
Comments 2
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.