Can “Vibe Coding” Beat Grad CS Students? Not Yet.

Kari Jaaskelainen

26 Nov 2025 — 1 min read

Can “vibe coding” beat grad CS students?

Researchers staged a coding tournament in a realistic logistics game: companies bid in auctions, then plan pickup-and-delivery routes under capacity limits. Agents must both bid strategically under uncertainty and optimize routes to maximize profit.

What happened

Human-coded agents (from graduate students) dominated: the top 5 spots across repeated tournaments.
33 of 40 LLM-coded agents lost to very simple baselines.
Even when given the best human solution to “improve,” the strongest LLM made it worse.

“Vibe coding” (asking an LLM to write complex systems from loose, high-level vibes) didn’t rescue performance.

Why it matters

Passing unit tests isn’t enough. Real-world coding often requires multi-agent reasoning, planning, and strategy. This study urges new benchmarks that test those skills—not just syntax and small functions.

Paper: https://arxiv.org/abs/2511.20613v1

Paper: https://arxiv.org/abs/2511.20613v1

Register: https://www.AiFeta.com

#AI #LLMs #Coding #Benchmark #MultiAgent #Logistics #Optimization #SoftwareEngineering #Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added