88

Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal help? (charlesazam.com)

10 hours ago couAUIA charlesazam.com

1

Gemini 3.5 Pro delays due to coding performance, upgraded Flash model in testing (9to5google.com)

a day ago couAUIA 9to5google.com

8

Kimi K3 is ranked 3rd on artificial analysis, only 2 points behind Sol (artificialanalysis.ai)

2 days ago couAUIA artificialanalysis.ai

1

I ran an AI nuclear engineering department for a week (charlesazam.com)

2 weeks ago couAUIA charlesazam.com

3

White House lifts ban on Anthropic models (ft.com)

2 weeks ago couAUIA ft.com

1

Hardware Engineering as Code (github.com/charles-azam)

3 weeks ago couAUIA github.com

1

Scientific documents should be written in Python (2022) (github.com/charles-azam)

3 weeks ago couAUIA github.com

5

Mistral Compute? I hear Mistral Cloud (mistral.ai)

a month ago couAUIA mistral.ai

1

Proton Pass for AI Agents (proton.me)

a month ago couAUIA proton.me

2

Ask HN: Should I continue this project ? (Being able to change AI harness) (github.com/charles-azam)

2 months ago couAUIA github.com

1

Evaluate Your Own RAG: Why Best Practices Failed Us (charlesazam.com)

5 months ago couAUIA charlesazam.com

3

GLM-5 topped the coding benchmarks. Then I used it (charlesazam.com)

5 months ago couAUIA charlesazam.com

4

I benchmarked 4 coding agents on an NP-hard problem I solved 8 years ago (charlesazam.com)

5 months ago couAUIA charlesazam.com

2

I Accidentally Rebuilt OpenHands from Scratch – Here's What I Learned (huggingface.co)

6 months ago couAUIA huggingface.co

3

Evaluate Your Own RAG, Why Best Practices Failed Us (huggingface.co)

8 months ago couAUIA huggingface.co