DEV Community

Open Source

May The Source Be With You! Articles about Open Source and Free Software as a philosophy, and its application to software development and project management.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Asked 'Do You Trust an Agent That Says the Tests Passed?' — 68 Comments Later, Here's What I Learned

I Asked 'Do You Trust an Agent That Says the Tests Passed?' — 68 Comments Later, Here's What I Learned

3
Comments 3
3 min read
Why ngx-runtime-i18n treats the active language as a signal, not an Observable

Why ngx-runtime-i18n treats the active language as a signal, not an Observable

Comments
2 min read
Fine-tuning an LLM on a Mac is easy to start and hard to evaluate

Fine-tuning an LLM on a Mac is easy to start and hard to evaluate

Comments 1
3 min read
I fixed a clip-split bug in Hyperframes with 89 lines (and it was about where time starts)

I fixed a clip-split bug in Hyperframes with 89 lines (and it was about where time starts)

Comments
2 min read
Build a Tiny Model Ledger Before Spending Free Tokens

Build a Tiny Model Ledger Before Spending Free Tokens

Comments
5 min read
I built a tool to catch AI agents getting stuck in loops

I built a tool to catch AI agents getting stuck in loops

2
Comments
1 min read
Wiring an AI Voicebot to Your CRM Without Adding Latency: A FreeSWITCH ESL Deep Dive

Wiring an AI Voicebot to Your CRM Without Adding Latency: A FreeSWITCH ESL Deep Dive

Comments
4 min read
Titan: Real-time message dispatch, made lightweight

Titan: Real-time message dispatch, made lightweight

Comments
1 min read
The "1 Million Token" Trap: Why I Built a Bi-Temporal Memory Engine for AI Agents

The "1 Million Token" Trap: Why I Built a Bi-Temporal Memory Engine for AI Agents

5
Comments
3 min read
I open-sourced the other half of agent observability: reading beliefs, not just traces

I open-sourced the other half of agent observability: reading beliefs, not just traces

Comments
2 min read
Don't Trust a New Model's Benchmarks Until You Run Your Own 30-Minute Smoke Test

Don't Trust a New Model's Benchmarks Until You Run Your Own 30-Minute Smoke Test

Comments
5 min read
I kept committing to client repos with the wrong email, cause switching git config is a pain

I kept committing to client repos with the wrong email, cause switching git config is a pain

Comments
1 min read
Benchmarks Don't Build Great Products. Engineers Do.

Benchmarks Don't Build Great Products. Engineers Do.

4
Comments
5 min read
Zhipu va ouvrir les poids du meilleur chasseur de failles

Zhipu va ouvrir les poids du meilleur chasseur de failles

Comments
5 min read
I built MEVA to check whether AI actually uses the evidence it retrieves

I built MEVA to check whether AI actually uses the evidence it retrieves

Comments
1 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.