vibehacker
News
TechGig (via The Information) ·

Anthropic is reportedly testing a model that infers what you meant from incomplete coding instructions

Per The Information, a tester said the unreleased model spotted broader related problems when asked for a simple bug fix, but it's unclear whether it can tell an incomplete request from work you deliberately left out. That gap matters: the Overeager Coding Agents study found Claude Code, Codex CLI, and Gemini CLI took out-of-scope actions in 5.4% to 27.7% of runs, versus 0.2% to 4.5% for ask-first OpenHands.

Read at techgig.com
Claude
AI assistant for research, coding, writing, and everyday work

More news

View all

Cursor's pstack adds a skill that has your agent formally verify the riskiest invariant in your repo

Calling /create formal verification skill makes the agent pick a high stakes property (races, retries, parsers, unsafe code), choose a tool such as TLA+, CBMC, or Kani, show the check failing on a deliberately broken variant, then leave a project local skill so the next agent can rerun it with one command. pstack also ships into Claude Code's plugin marketplace from the same repo, and Cursor's own eval behind the skill is small (one run per repo on six open source projects)…

GitHub (cursor/plugins)

OpenAI's MultiLangBench has models build SQLite from scratch in 20 languages, COBOL included

The open eval (GitHub) checks a from scratch SQLite 3.40.1 engine against 272 tests adapted from SQLite's own suite and scores pass rate alongside API cost; OpenAI says GPT 6 Astra averages 87.4% (COBOL hardest at 72.1%) vs 26.8% for GPT 5.6 Sol, while cheaper GPT 6 Luna hits 40.3% at about 78% lower cost. A separate COBOL migration eval has GPT 6.1 Sol at 97.9% on high reasoning, though all figures are OpenAI's own runs…

OpenAI

SIwithin runs Claude Code unattended inside a folder fence and a hard dollar budget

The single file, stdlib only Python tool (macOS only) confines a run to the folders you grant, blocks your home folder, and routes every API call through a loopback proxy that holds the real key, prices each response, and kills the run once the budget is spent. Its Codex CLI adapter is weaker: per the README it hasn't been tested against a live CLI and needs the key in the run's environment (write up)…

GitHub (metahumansworld/SIwithin)

Respan open-sources a Rust AI gateway where every provider, protocol, and feature is a plugin

The YC W24 team rebuilt its LiteLLM based gateway as a tiny event dispatch core, so providers (Mistral's is 22 lines), MCP, realtime voice, fallbacks, and PII redaction are all plugins, and an OpenAI, Anthropic, or Gemini client can call any model with tools and reasoning translated. It's pre alpha, MIT/Apache 2.0, and runs locally from source (GitHub), with a paid hosted version for observability and evals…

Hacker News (Launch HN)

Spotted something we missed? Start a thread.