» Tag
ai
1156 postsAgent-Native Software Engineering: Why Specs Alone Aren't Enough
Coding agents fail less at writing code than at holding architectural context. A look at spec-driven development's limits and what comes next.
Are AI Labs Gaming the Pelican-on-a-Bicycle Benchmark?
A statistical study generates 1,008 SVGs across 7 LLMs to test whether AI labs are secretly optimizing for the famous pelican-on-a-bicycle benchmark.
Emem: A Signed Memory Layer for Multi-Agent AI Systems
Emem gives AI agents a signed, verifiable memory layer for physical-world facts that survives context compaction across models and vendors.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comGPT-5.6 vs Claude Fable 5: Benchmarking Physical AI Simulation
JuliaHub compares GPT-5.6 and Claude Fable 5 in its Dyad agent on five physical modeling problems, revealing cost, speed, and validation trade-offs.
Fable 5 vs GPT-5.6 Sol on an NP-Hard Problem: Does /goal Help?
Claude Fable 5 and GPT-5.6 Sol tackle an NP-hard fiber-network problem, testing whether the /goal persistence feature actually improves results.
NVIDIA's Nemotron 3 Super Beats GPT-OSS-120B on Coding Benchmarks
NVIDIA's open Nemotron 3 Super model beats GPT-OSS-120B by 20 points on SWE-Bench and delivers 2.2x faster inference throughput.
Three Years of AI Disclosures on Steam: A 53,600-Game Census
Steam census of 53,600 games (2023-2026) shows AI disclosures rising to ~33% of releases, but AI titles still underperform non-AI games commercially.
Open-source AI skill set turns LinkedIn posting into a pipeline
linkedin-skills is an open-source, ten-skill toolkit for Claude Code and Codex that automates LinkedIn writing, publishing, and analytics safely.
Engrava: A Deterministic Memory Library for AI Agents Built on SQLite
Engrava is an MIT-licensed Python library storing agent memory as a typed graph in SQLite, with deterministic consolidation instead of LLM rewrites.
"Hallucination" Isn't One Bug. It's Three, and Only One Is Fixable
Hallucination isn't one failure mode — it's three. A test to tell them apart, why benchmarks reward bluffing, and what a 2026 prediction experiment showed.