← back NO. #f1011faf

NO.: #f1011faf
Topic: AGENTS & TOOLS
Source: Google AI Forum
Published: 2026-05-20 18:29:59
Importance: ★ 6/10 — radar 60
Original: discuss.ai.google.dev/t/google-antigravity-has-come-to-an-end/146501

`Google Antigravity` shifts toward weekly quotas, hurting long coding sessions

Short-reset Flash access is gone, pushing heavy use into 7-day quotas. The tool now fits burst work better than daily agentic coding.

[ KEY POINTS ]

Gemini 3.0 Flash with roughly 5-hour resets was the practical daily driver; its removal breaks predictable iteration loops.
Paid Ultra users are also hitting tighter limits, so this is not just a free-tier downgrade.
Weekly cooldowns turn debugging, refactoring, review, and test loops into prompt budgeting. Keep a fallback agent ready.

Originaldiscuss.ai.google.dev/t/google-antigravity-has-come-to-an-end/146501Read original →

// related

#0001
#0001Agents & tools Simon Willison5 hours ago
`Gemini Spark`, Google’s hosted agent tied to Workspace apps
60radar
Gemini SparkHosted AI agent — native Google app connections
Google is packaging app-connected agents around Workspace, but much is still coming soon. Security and credential handling decide whether it becomes useful or risky.
- Gemini Spark connects natively to Gmail, Calendar, Drive, Docs, Sheets, Slides, YouTube, and Maps. That makes it closer to a work agent than a chat UI.
- FAQ says it runs on Gemini 3.5 Flash and Antigravity. The Antigravity stack spans a desktop app, CLI, SDK, and VS Code fork.
- Enterprise notes mention fresh isolated ephemeral VMs, Agent Gateway DLP, and encrypted credentials. That is the right threat model, not proof it is solved.
- Since the product is not broadly testable yet, treat it as a roadmap signal. Do not build critical automations around it until GA behavior is clear.
Source: simonwillison.net/2026/May/20/google-io/#atom-everythingRead original →
60radar
PHOTO
FIG-0011:1
#0002
#0002Agents & tools GitHub Changelog5 hours ago
`GitHub Copilot` in VS Code gets task-based auto model routing
70radar
Model choice moves from manual picking to routing by task, utilization, and health. Useful for lower-friction coding, but less control over exact model behavior.
- GitHub Copilot now selects a model using task fit, utilization, and model health metrics, aiming for reliable and token-efficient runs.
- The change matters most in VS Code, where model switching interrupts small coding loops; default auto mode should reduce that friction.
- Tradeoff: less explicit model control. Keep manual model selection for debugging, refactors, or prompts where output variance matters.
Source: github.blog/changelog/2026-05-20-auto-model-selection-noRead original →
FIG-0021:1
70radar
FIG-0021:1
#0003
#0003Agents & tools GitHub Changelog6 hours ago
`GitHub Copilot Chat` Adds Semantic Issue Search
80radar
Natural-language issue triage now works inside web chat. It reduces manual filtering across noisy repos and is worth trying for backlog cleanup.
- Queries can find, group, and analyze issues with a semantic issue index, so exact-label hygiene matters less.
- The feature is available in GitHub Copilot Chat on the web, keeping triage inside the existing GitHub workflow.
- Best fit: duplicate detection, bug clustering, and release-scope checks before planning a small sprint.
Source: github.blog/changelog/2026-05-20-semantic-issue-search-iRead original →
FIG-0031:1
80radar
FIG-0031:1

`Google Antigravity` shifts toward weekly quotas, hurting long coding sessions

// related

`Gemini Spark`, Google’s hosted agent tied to Workspace apps

`GitHub Copilot` in VS Code gets task-based auto model routing

`GitHub Copilot Chat` Adds Semantic Issue Search