AI FrontTrack the AI frontier. Discover what comes next.
EnglishEN

// Topic signal

Foundation Models

Frontier research, releases, and benchmarks for LLMs, multimodal models, and diffusion models.

Unknown source

Make CLI commands ~20x faster and halve the package: split the server build, drop gpt-tokenizer

Sorry @looptroop-ai, you've used your own review budget of 250,000 diff characters for the last 7 days. You can request another review in 23 hours and 40 minutes by commenting `@sourcery-ai review`. [Upgrade](https://app.sourcery.ai/login?connection=github&git_namespace_id=257343580&from_surface=gi... <!-- codex-pull-request-review-summary --> ## Codex Review Summary This comment shows the latest Codex review activity on this pull request. | Review | Status | Commit | Review trigger | | --- | --- | --- | --- | | 📝 **Code Review** | ✅ **Completed** <relative-time datetime="2026-10-13T09:34:40.9... <h2><picture><source media="(prefers-color-scheme: dark)" srcset="https://static.deepsource.com/comment_artifacts/dark/grade_a.svg"/><source media="(prefers-color-scheme: light)" srcset="https://static.deepsource.com/comment_artifacts/light/grade_a.svg"/><img src="https://static.deepsource.com/comme...

Foundation ModelsOpen Source
Unknown source

fix: handle Claude Code verbose results and improve summary errors

<!-- codex-pull-request-review-summary --> ## Codex Review Summary This comment shows the latest Codex review activity on this pull request. | Review | Status | Commit | Review trigger | | --- | --- | --- | --- | | 📝 **Code Review** | ✅ **Completed** <relative-time datetime="2026-10-12T11:40:47.3... <!-- This is an auto-generated comment: summarize by coderabbit.ai --> <!-- review_stack_entry_start --> <a href="https://app.coderabbit.ai/change-stack/Muesli-HQ/muesli/pull/609?scope=ghh_OusAJGA4HG8ljoOV0wJvVx8NmnZIjc2DdjmxOu0xZWA&amp;cs_source=review_comment"><picture><source media="(prefers-col... **Claude finished @pHequals7's task in 22s** —— [View job](https://github.com/Muesli-HQ/muesli/actions/runs/38243981655) --- ### Code review of PR #609 The automated `/code-review` skill failed to run, so this is a manual read of the diff. I didn't build or run the tests. **No blocking issues.** ...

AI AgentsFoundation Models
Unknown source

feat(alerts): run the llm detector on claude haiku 5.5

✨ Submitted to Merge by @andrewm4894. It will be added to the merge queue once all branch protection rules pass. See more details [here](https://app.trunk.io/posthog-inc/merge-queue/3921a8a3-abf7-42ff-b9cf-ef4fab8f3649/115139). ### PostHog Review · Standard · reviewed `0e632a9` Nothing to post. | Step | Status | Result | |---|---|---| | Prepare the diff | done | 1 file | | Main review and lenses | done | 0 issues | | Merge and cap | done | 0 → 0 | | Publish | done | Nothing to post | <!-- reviewhog:status:01a12cb1-1431-... <!-- posthog-ci-report --> ## 🤖 CI report <!-- ci-report:section:trunk-lane:eyJzdGF0dXMiOiJ3YXJuIiwic3VtbWFyeSI6ImJhY2tlbmQgUHl0aG9uIGxhbmUifQ== --> <details> <summary>⚠️ <b>Trunk lane</b> — backend Python lane</summary> This PR is assigned to the backend Python lane. It runs backend Python tests ...

Foundation ModelsOpen Source
Unknown source

Add Claude Code GitHub Workflow

## 🤖 Installing Claude Code GitHub App This PR adds a GitHub Actions workflow that enables Claude Code integration in our repository. ### What is Claude Code? [Claude Code](https://claude.com/claude-code) is an AI coding agent that can help with: - Bug fixes and improvements - Documentation upd

AI AgentsFoundation Models
Unknown source

Guides for Claude code usage in writing comments and PR descriptions

I would strongly suggest broadening this discussion to all of NumericalEarth, not just Oceananigans! I think we should allow bots to open PRs directly. I think the downsides are huge. It's not just the time taken to open a PR, but we can potentially miss out on bug fixes, performance optimizations, etc. I would rather see that code, if it helps, even if there is no PR description. And I think that ... Also a provisional description that requires rewriting is a good option, it keeps within the scope of the human developer revising and understanding the AI-generated implementations

AI AgentsFoundation Models
Unknown source

✨ feat(model-bank): add Claude Haiku 5.5

### Summary Contribution source: AI-assisted Adds **Claude Haiku 5.5** (`claude-haiku-5-5`, released 2026-10-07) using data from Anthropic's official docs ([models overview](https://platform.claude.com/docs/en/about-claude/models/overview), [Haiku 5.5 overview](https://platform.claude.com/docs/en/

Foundation ModelsOpen Source
Unknown source

feat(posthog-ai): move the main agent to claude-sonnet-5-5

Sonnet 5.5 rejects `thinking.budget_tokens`, so the agent switches to adaptive thinking and keeps `output_config.effort: medium` as the depth control. `display: "summarized"` keeps reasoning visible in the UI, because Sonnet 5.5 omits thinking text by default. The interleaved thinking beta is droppe

AI AgentsFoundation Models