Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-09-17 · source-backed
alibaba/open-code-review topped both the all-language and Go trending boards, sitting at 33,568 stars four months after its May 18 creation, and cut v1.12.4 yesterday. It's a Go tool pairing deterministic analysis pipelines with an LLM agent, shipping a built-in multi-language ruleset for NPE, thread-safety, XSS and SQL injection. The hybrid structure is the design to copy: the deterministic pass bounds what the model is allowed to be wrong about, instead of asking a model to find everything and hoping.
Each link below shares sources, entities, or timing with this story.
alibaba/open-code-review cut v1.12.1 at 11:23 UTC this morning. It's a Go CLI that ran as Alibaba's internal review assistant for two years before the May 2026 open-source release, and it's at 24,596 stars with 443 added today. The architecture explains the claimed numbers. It...
Fortune's exclusive reveals the architecture: Claude is placed inside a virtual machine with access to debuggers, fuzzers, and standard security utilities, then autonomously maps component interactions and traces data flow. Every finding goes through multi-stage self-verificat...
Willison launched datasette-apps (0.1a2) on June 18, hosting self-contained HTML+JS apps in a sandboxed iframe that run SQL against your data, read-only by default. He frames it as "Claude Artifacts reimagined for Datasette," artifacts backed by a JSON API to a relational data...
His conclusion is DuckDB matches or beats SQLite's safety for untrusted queries, but only with enable_external_access=false, lock_configuration=true, and a watchdog thread, since DuckDB lacks SQLite's opcode-based query timeouts. He ships a safe_duckdb.py helper and a Datasett...
Forrest Chang's andrej-karpathy-skills repo is a single CLAUDE.md file distilling Karpathy's observations on LLM coding pitfalls. It topped GitHub trending with +44K weekly stars. Then the ecosystem detonated. Ten-plus related repos trended simultaneously with 70K+ combined st...
GLM-5.1 from Zhipu AI scored 58.4% on SWE-bench Pro. GPT-5.4 scored 57.7%. Claude Opus 4.6 scored 57.3%. That's the first time an open-weight model has ever topped a major coding benchmark against the best proprietary models. The specs matter. GLM-5.1 is a 754B-parameter mixtu...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.