AI Coding Assistants

Today's Stories

1. 1

   SCPI test gear users share AI agent setups on HN

   A hobbyist on Hacker News asked whether others use AI coding agents with SCPI-enabled electronics gear and shared his own experiments. He built a desktop voltmeter-chart (slow oscilloscope) with a LABLOOT LB1041 DMM, made a SIGLENT SDS814X scope decode UART, set power-supply voltage on an OWON SPS6051, and loaded waveforms into an OWON DGE2045 signal generator. The post reflects a growing hands-on interest in letting coding agents drive test equipment, not just write software. The author also uses AI agents to evaluate USB devices like UARTs and MCUs, combining signal generation with scope and meter readings—so the question taps into practical workflows for automated hardware testing.

   The thread invites others to share what SCPI they use and which gear they would recommend for a modest home electronics bench. The outcome depends on what other hobbyists post in response.

2. 2

   Snowflake CoCo Boosts Reproducible Data Pipelines

   Snowflake introduced CoCo, an AI coding agent for data engineers, available via CLI, Desktop, and Snowsight. CoCo runs within Snowflake's security perimeter and has built-in skills for Snowflake workflows like dbt and Snowpipe Streaming. CoCo helps data engineers create repeatable, high-quality outcomes by encoding team knowledge into skills and plugins, rather than relying on one-off prompts. Snowflake argues that AI agents should not make direct production changes and that professional tools like dbt and DCM remain essential.

   CoCo supports model choice among top frontier and open-source models. Skills are folders with a SKILL.md file, while plugins bundle skills, hooks, MCP servers, and more into versioned, installable units via the Plugins Catalog.

3. 3

   GitHub unveils HydraFusion, a multi-model AI orchestrator

   GitHub introduced Project HydraFusion, a research preview that automatically chooses and orchestrates models from multiple providers to handle coding tasks. It can draft, critique, and revise, or escalate to stronger models as needed. In tests, HydraFusion delivered frontier-level quality while cutting costs: on TerminalBench 2.1 it improved verified task quality by 4.9 percentage points at 67% lower estimated cost compared to Claude Opus 5. On DeepSWE it came within 1.5 points of Opus 5 while reducing cost by 36%.

   HydraFusion is now in research preview for GitHub Copilot, designed for first-turn, single-prompt tasks. Developers can try it in autopilot mode and share feedback via /feedback in Copilot CLI or the GitHub Community discussion.

4. 4

   GPT-6 Astra launches, under $6 an hour AI engineer

   OpenAI launched GPT-6 Astra, its first Stargate and lightly looped supermodel, which beat Fable 5.1 on many metrics including 97.6% on the hardest FrontierMath and 99.9% on ARC-AGI-3. In early access tests using over 20B tokens, Astra proved capable of full AI engineer tasks—choosing and training models, labeling data, deploying systems, and maintaining coherence over billions of tokens in a single thread—at an effective cost of under $6 per hour.

   At 33 tokens per second and a max $50 per million token rate, Astra's cost-efficiency may make it the best fast-and-smart model available, but heavier use at Ultra settings could exceed that hourly figure.

5. 5

   AI to Sort Trash in Sabae City Starting Sept 1

   Sabae City launched a web app on September 1 that uses AI to identify and sort trash when users photograph it with a smartphone. The app can distinguish multiple items in a single photo and provides sorting instructions within about 10 seconds. Last year, fires caused by improperly disposed lithium-ion batteries in non-burnable trash occurred repeatedly at the city's waste facility. The city hopes the AI tool, accessible via its website, will reduce such sorting errors and improve safety.

   The service is free and available through Sabae City's homepage. It is unclear if the city will expand the app's capabilities or monitor its effectiveness in reducing mis-sorting incidents.

6. 6

   Open-source InsForge boosts AI agent backend accuracy

   Agents fail at backend tasks like auth and database setup. InsForge adds a semantic layer with structured, machine-readable capabilities. It delivers roughly 2x more accuracy than Supabase MCP, and 30% better token efficiency. Backend platforms like Firebase and AWS were built for human clicking, so agents get fragmented context and hallucinate. InsForge fixes this at the infrastructure level, letting agents reason about the backend as one system.

   InsForge works with Cursor, Claude Code, Windsurf, and Codex, and is open-source under Apache 2.0. A test built a full ChatGPT clone with Claude Code with no manual configuration.