AI News, 10 June 2026

Today’s lead item covers AI features in Google Search and Shopping for second-hand shopping, though the source is documented only at headline and summary level. The rest of the issue brings a wave of new version numbers from several AI coding tools plus a very thin OpenAI customer story, none of them accompanied by a published changelog or further detail.
Today’s Stories
Section titled “Today’s Stories”1. OpenAI: How Endava is redesigning software delivery around AI agents
Section titled “1. OpenAI: How Endava is redesigning software delivery around AI agents”What changed: OpenAI published the update on 3 Jun 2026. OpenAI published a customer story describing Endava restructuring its software delivery process around AI agents; the source text supplies only the headline, with no description of what specifically changed.
Why it matters: The story signals that agent-based workflows are spreading to larger IT delivery firms, but without concrete detail it offers no practical guidance for readers’ own setups yet.
How to verify it: Search for the Endava case study on OpenAI’s own site and read it directly to see which tools and processes are actually described.
Uncertainty: There is no information on which AI tools are involved, which part of the delivery chain changed, or whether any outcomes were measured versus described anecdotally.
Source: How Endava is redesigning software delivery around AI agents
2. Google AI: 5 ways Google Search can level up your thrift and vintage shopping
Section titled “2. Google AI: 5 ways Google Search can level up your thrift and vintage shopping”What changed: Google AI published the update on 2 Jun 2026. Google published a guide outlining five ways to use AI features in Search and Shopping to find second-hand and vintage items; the specific five tips themselves are not present in the available excerpt.
Short source excerpt: Uncover second-hand scores with AI tools in Google Search and Shopping. Try these 5 thrifting tips from Google Skip to…
Why it matters: If these features already exist in the standard Google app, they could matter to anyone hunting for used furniture or electronics for the home, but without the actual steps the practical value is hard to judge.
How to verify it: Open Google Search or the Shopping app and try searching for a used item to see whether AI-driven filters or suggestions actually appear.
Uncertainty: It is unclear whether these features are new or pre-existing, which countries and languages they cover, and whether they require a specific Google account or app version.
Source: 5 ways Google Search can level up your thrift and vintage shopping
3. OpenClaw: openclaw 2026.6.5
Section titled “3. OpenClaw: openclaw 2026.6.5”What changed: OpenClaw published the update on 8 Jun 2026. On June 8, the open source OpenClaw project shipped release 2026.6.5, though the GitHub page states only the version number and date with no list of changes.
Short source excerpt: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 - Release openclaw 2026.6.5 · openclaw/openclaw Release…
Why it matters: If you let OpenClaw update automatically, its behavior could shift without warning, since there is nothing to look up before the update lands.
How to verify it: Look up the actual changelog for openclaw 2026.6.5 on GitHub before letting the update roll out to an active installation.
Uncertainty: The scope of the changes in 2026.6.5 is unknown, and the material says nothing about whether the update requires any manual action.
Source: openclaw 2026.6.5
4. Claude Code: v2.1.162
Section titled “4. Claude Code: v2.1.162”What changed: Claude Code published the update on 2 Jun 2026. Claude Code 2.1.162 shipped on June 2 according to Anthropic’s GitHub repo, which does not state what was actually changed in this version.
Short source excerpt: Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster…
Why it matters: Terminal agents like Claude Code operate close to the file system and git, so a version with unknown contents makes it hard to judge whether updating right away is safe.
How to verify it: Run claude —version locally and compare it against the GitHub release so you know whether the update has already landed on your machine.
Uncertainty: There is no indication of whether this is a bug fix, a feature change, or whether it alters anything in existing setups or hooks.
Source: v2.1.162
5. OpenAI Codex: 0.138.0
Section titled “5. OpenAI Codex: 0.138.0”What changed: OpenAI Codex published the update on 7 Jun 2026. OpenAI’s terminal agent Codex reached version 0.138.0 on June 7; the release is logged on GitHub without any description of its contents.
Short source excerpt: Lightweight coding agent that runs in your terminal - Release 0.138.0 · openai/codex Release 0.138.0 · openai/codex · GitHub /…
Why it matters: Scripts and automations built around a specific Codex version can break quietly if the update changes flags or behavior without documentation.
How to verify it: Find the release notes for Codex 0.138.0 on GitHub and read them through before updating an environment you rely on daily.
Uncertainty: Whether version 0.138.0 is a minor maintenance update or contains larger changes cannot be determined from the available material.
Source: 0.138.0
6. Gemini CLI: Release v0.47.0-preview.0
Section titled “6. Gemini CLI: Release v0.47.0-preview.0”What changed: Gemini CLI published the update on 9 Jun 2026. Google tagged its Gemini CLI with a new preview build, v0.47.0-preview.0, on June 9, without publishing what the preview label actually covers in terms of changes.
Short source excerpt: An open-source AI agent that brings the power of Gemini directly into your terminal. - Release Release v0.47.0-preview.0 · google-gemini/gemini-cli…
Why it matters: A preview label usually signals features that are not yet fully tested, so it is worth keeping production use on the stable line until more is known.
How to verify it: Review the release description for v0.47.0-preview.0 on GitHub to see what actually changed before installing the preview build.
Uncertainty: It’s not shown whether the preview build includes breaking changes, how stable it is, or when it might graduate to a stable release.
Source: Release v0.47.0-preview.0
Why It Matters
Section titled “Why It Matters”- The focus is changes that can affect AI products, models, browser experiences, agents, API usage, privacy, pricing, or security.
- A new feature is useful in the home only after access, logging, and rollback have been tested.
- The article separates documented information from editorial judgment and open questions.
Sources and Further Reading
Section titled “Sources and Further Reading”| Publisher | Source | Date |
|---|---|---|
| OpenAI | How Endava is redesigning software delivery around AI agents | 3 Jun 2026 |
| Google AI | 5 ways Google Search can level up your thrift and vintage shopping | 2 Jun 2026 |
| OpenClaw | openclaw 2026.6.5 | 8 Jun 2026 |
| Claude Code | v2.1.162 | 2 Jun 2026 |
| OpenAI Codex | 0.138.0 | 7 Jun 2026 |
| Gemini CLI | Release v0.47.0-preview.0 | 9 Jun 2026 |
Editorial Note
Section titled “Editorial Note”SmartBolig.net used automated research, deduplication, and drafting for this issue. Editorial rules require a primary source, verifiable links, and explicit uncertainty.
Comments
SmartBolig // AI Core
SmartBolig AI
Get help with troubleshooting, architecture and concrete configuration. I use broad AI knowledge and find SmartBolig guides when they improve the answer.
Start with a useful question