AI Coding Assistants

Today's Stories

1. 1

   Harness launches agent-ready code repository and AI review

   Harness Inc. today announced Agent-Ready Harness Code Repository and AI Code Review. These tools are designed for teams using AI coding agents that produce code faster than humans can review and deploy. CEO Jyoti Bansal says today's code management expects humans to write and review code, a model overwhelmed by AI agents that generate volumes in minutes. Harness aims to rebuild this layer to handle thousands of pull requests at once, with each agent inheriting permissions from its human trigger.

   Internal testing over the last month saved an estimated 10,000 hours. The system uses Model Context Protocol and command-line interfaces, enabling programmatic control and lower AI token costs.

2. 2

   MCA final-year student seeks real-world AI project ideas

   An MCA student with experience in Python, LangChain, Chroma, HuggingFace, and FastAPI is asking for real-world AI project ideas that companies like IBM or Google would actually need solved, not generic tutorials. The student's project guide wants a problem with genuine business value, enough depth to defend under tough viva questioning, and something realistic for one person to build in a few months without being trivial.

   The student is looking for projects that impressed committees or recruiters, seeking ideas that stand out from typical final-year submissions like sentiment analysis or spam classifiers.

3. 3

   Visa ships security AI that auto-patches code

   Visa's open-source security harness now finds vulnerabilities, writes fixes, and runs an adversarial panel on its own patch before any human review. The full loop ships on by default, running all 11 stages and editing source files unless capped at detection. The default is the opposite of what Steve Wilson, Exabeam's Chief AI and Product Officer and OWASP Top 10 for LLM Applications co-lead, advised two days earlier: 'put an authorization gate outside the model.' This could raise concerns about AI autonomy in security.

   The release follows Tenet Security's GhostJacking demo at DEF CON 34, where an agent read a payload from a log file and rewrote DNS with a valid credential—illustrating risks that Visa's harness aims to counter.

4. 4

   AI inference power demand to hit 46GW by 2035

   ABI Research projects that AI inference data center power demand will grow from 2GW in 2026 to 46GW by 2035, with code generation becoming the largest workload. Code generation workloads are expected to grow at a 52% CAGR, reaching 23.6GW by 2035—over half of all AI inference power. This shift highlights the rapid expansion of inference-specific infrastructure.

   The market is consolidating, with players like CoreWeave and Qualcomm acquiring companies such as Weights & Biases and Modular. Open-source model adoption is projected to rise from 35% in 2025 to 55% by 2026.

5. 5

   DHH talks AI programming, Linux desktop on Lex Fridman

   DHH, creator of Ruby on Rails and CTO of 37signals, appeared on the Lex Fridman podcast to discuss programming with AI agents, vibe coding, and the future of software development. He argues AI agents will end manual programming and that Linux will win the desktop, touching on how software creation and open source will change for businesses and developers.

   The episode includes specific advice for programmers, a look at his Omarchy Linux distro, and his views on the best AI coding models and harnesses.

6. 6

   Vibe-coded apps seen challenging SaaS giants like Salesforce

   A Spiceworks article explores whether 'vibe-coded' applications—AI-generated software built through natural-language prompts—could replace established SaaS products such as Salesforce and ServiceNow. The question matters because these tools are staples for business operations; if AI can generate similar apps on demand, it may disrupt how companies purchase and use software.

   Whether the trend gains traction in enterprise settings, as the article does not offer a definitive verdict on adoption timelines or market impact.