Also they cache food they don't eat, they hide it, cover with leaves and make sure nobody is watching them, they act very casual. I am not sure if they remember the locations though.

Compared to ravens they have smaller head but I believe it is because they spend so much time near people (at least here in Europe you don't see ravens in cities, they are afraid,for historical reasons, of people and low in numbers) they get smarter and more crafty.

I can recommend a great book about corvids with beautiful illustrations: https://yalebooks.yale.edu/book/9780300122558/in-the-company...

⎿ API Error: 400 messages.1.content.17: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response.

From /code-review max.

Example: https://github.com/rkuska/carn/blob/main/VOCABULARY.md

``` # Development Workflow

*Always use `bun`, not `npm`.*

# 1. Make changes

# 2. Typecheck (fast)

bun run typecheck

# 3. Run tests

bun run test -- -t "test name" # Single suite bun run test:file -- "glob" # Specific files

# 4. Lint before committing

bun run lint:file -- "file1.ts" bun run lint

# 5. Before creating PR

bun run lint:claude && bun run test ```

I have these things in pre-commit, this way the targets are always ran and the agent is forced to fix them (I ask claude to commit changes). The agents are erratic and very often skip these steps. Anything that can be deterministic I keep as scripts.

Regarding commits; both codex and claude are terrible at writing them. I have in my user CLAUDE.md:

``` Pattern: `type(scope): message` where type is `fix`, `feat`, `chore`, `docs`, `refactor`, or `style`; scope marks what is affected; message is a short lowercased description.

Keep subject and body lines under 72 characters. Always write a body explaining what, how, and why in continuous human-readable text. For fixes include the error message being fixed. No first-person speech. Re-read the actual git diff before writing — the message must describe what changed, not what was planned.

Use following command to create commit:

```bash git commit -F - <<'EOF' type(scope): subject line

Body paragraph explaining what, how, and why. EOF ```

```

Without it would write the body as a single long sentence; when asked to fix lines it would just insert \n (newlines), which were not respected and were instead just rendered as characters.

Another thing I find helpful is VOCABULARY.md. Very often the agent would assume (connect?) a different thing than what I had in mind, with VOCABULARY I make sure when I say "thing" claude and I have both the same "understading" (connection?) what "thing" is.

`claude --thinking-display summarized`

The thinking is then visible with ctrl+o in the claude cli (shortcut available at least on mac).

Well you can't really trust the documentation I guess. I can't edit my original comment anymore.

> Claude Opus 4.7 (claude-opus-4-7), adaptive thinking is the only supported thinking mode. Thinking is off unless you explicitly set thinking: {type: "adaptive"} in your request; manual thinking: {type: "enabled"} is rejected with a 400 error.

https://platform.claude.com/docs/en/build-with-claude/adapti...

For my claude code I went with following config:

* /effort xhigh (in the terminal cli) - To avoid lazying

* "env": {"CLAUDE_CODE_DISABLE_1M_CONTEXT": "1"} (settings.json) - It seems like opus is just worse with larger context

* "display": "summarized" (settings.json) - To bring back summaries.

* "showThinkingSummaries": true (settings.json) - Should show extended thinking summaries in interactive sessions

Freaking wizardry.

https://github.com/rkuska/carn

https://www.muzeumprahy.cz/en/visit-langweils-model-of-pragu...

It parses the conversations and shows them in uniform view with toggles to enrich the view with more data and provides an easy way to search/resume and copy relevant parts of conversation.

I put the TUI together with claude and codex without reading any of the code - it was an experiment for me. I tried to put as much guardrails as possible to steer the agents and not let them go wild. Each commit is more or less a single conversation.

It's written in Go and inspired by TIG.

Comments URL: https://news.ycombinator.com/item?id=47411792

Points: 1

# Comments: 0

> Like I said, America's a third world country as it is and... and we're just basically in a hopeless situation as it stands

https://www.youtube.com/watch?v=pP8XBJc2p_g

I keep GY!BE playing on repeat for the past several months.