A talk at SFRuby highlights how Intercom leverages AI to generate 90% of their PRs, showcasing a significant integration of AI in a large Rails monolith. This event could indicate a shift in how engineering teams might adopt AI for real-world applications.
Tomorrow at #SFRuby:
@brian_scanlan
from
@intercom
on turning Claude Code into a full-stack engineering platform. 90% of their PRs are Claude-authored. 2M-line Rails monolith.
Ruby on Rails x AI is a power combo. 195 people signed up. 5:30 PM. sfruby . com
This tweet discusses a new method presented at NLP2026 for resolving notation variations in medical department names using an LLM, achieving a high accuracy rate. Senior engineers may find the approach and results relevant for improving NLP applications in healthcare.
Published a new article on the KAKEHASHI Tech Blog.
We presented at NLP2026 a method that resolves "notation variations" in medical department names using an LLM, achieving a 97.5% accuracy rate with GPT-5. Please take a look.
A developer has created a full LLM inference engine from scratch in C#/.NET, featuring native GGUF loading and an OpenAI-compatible API. This could be of interest to engineers looking for robust, low-level AI infrastructure solutions.
I've built a full LLM inference engine in C#/.NET 10. From scratch. Not a wrapper - native GGUF loading, BPE tokenizer, attention, KV-cache, SIMD-vectorized CPU kernels, CUDA GPU backend, OpenAI-compatible API. Solo dev, ~2 months, AI-assisted (not vibe-coded!). First preview is
Gemma 4 31B achieves a notable ELO ranking among open models, indicating strong performance relative to larger models. This ranking could inform decisions on model selection for production systems.
Gemma 4 31B. 1451 ELO on
@arena
.
#4 among open models. Preliminary ranking.
Above it? GLM 5.1, GLM 5, and Kimi K2.5 thinking. All significantly larger models.
At 31B parameters this is the best intelligence per parameter ratio on the open leaderboard right now.
Anthropic's new research explores using a weak AI model to supervise the training of a stronger one, potentially accelerating alignment research. This could have implications for how AI systems are developed and aligned in the future.
New Anthropic Fellows research: developing an Automated Alignment Researcher.
We ran an experiment to learn whether Claude Opus 4.6 could accelerate research on a key alignment problem: using a weak AI model to supervise the training of a stronger one.
👁 11,980 views❤ 252🔁 47💬 21🔖 882.7% eng
AI alignmentresearchAnthropicClaude Opusmachine learning
This tweet discusses architectural patterns for building production-grade AI agents, emphasizing the importance of architecture over prompts. Senior engineers may find value in the insights derived from the Google AI Bake-Off, particularly regarding multi-agent systems and deterministic execution.
Building production-grade AI agents? It's not about better prompts, it's about better architecture.
Learn five patterns from the Google AI Bake-Off, from multi-agent systems to deterministic execution.
Read the blog:
👁 2,054 views❤ 7🔁 3💬 0🔖 50.5% eng
AI agentsarchitectureGoogle AI Bake-Offmulti-agent systemsdeterministic execution
Microsoft has released Skala, a neural network exchange-correlation functional that achieves chemical accuracy comparable to hybrid functionals at a semi-local cost. This could be relevant for engineers working on computational chemistry applications.
Microsoft just released Skala on Hugging Face
A neural network exchange-correlation functional for density functional theory
that achieves chemical accuracy on par with hybrid functionals at semi-local cost.