Dariusz Kuśnierek

Raczkujący tata · Alternatywny kawosz (V60, AeroPress, Chemex) · Służbowo Excel, SQL, Power BI · Po godzinach seriale, retro gaming, no-code/low-code

[Dariusz Kuśnierek @dkodr]

No i co się okazało... not great, not terrible 🙂 To na razie tylko jeden dzień monitoringu, więc będę się sprawie jeszcze przez jakiś czas przyglądać. Przy okazji sprawdzę też kwestię opóźnień w raportowanje pozycji względem rzeczywistej.

[Dariusz Kuśnierek @dkodr]

Przedczoraj wdrożyłem możliwość śledzenia lokalizacji busów na żywo na https://t.co/uDYTumwBPM. *Ponownie* wdrożyłem 😉 ale tym razem z innego źródła. Po... ekhm... drobnych problemach z poprzednim źródłem, z pomocą przyszły otwarte dane https://t.co/aLt8PBUe1v.

[Dariusz Kuśnierek @dkodr]

Chciałem sprawdzić na ile poważnym może się to okazać problemem; zaimplementowałem więc logowanie przy okazji pobierania danych z API, podpiąłem Better Stack i dodatkową analizę po swojej stronie (bo Better Stack próbkuje co 3 minuty, a wolałem nieco bardziej szczegółowo).

[ClaudeDevs @ClaudeDevs]

We've updated /fork in Claude Code

/fork now runs a background agent with your exact context (system prompt, tools, history, model) and prompt cache. The result gets returned to your session.

/branch (the old /fork) still copies the transcript to a new session you drive.

[Google Gemma @googlegemma]

Meet Gemma 4 12B!

A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.

Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇

[Matt Van Horn @mvanhorn]

TL;DR of my new article: every Agentic Engineering hack I know.

This used to be vibe coding. Around last Thanksgiving it got good enough to become something real.

📝 The moment you have an idea → /ce-plan a plan.md, with Compound Engineering by @kieranklaassen + @trevin. Fuzzy? /ce-brainstorm first
🙈 Make the plan, don't read it. Plans are for agents
🧠 Use /ce-plan for your deepest NON-code work too (strategy, specs, research)
🎙️ Get voice-pilled. Talk, don't type (@usemonologue or @WisprFlow)
🪟 Run 4-6 tabs in cmux (@manaflowai), one task each
⌨️ New tabs open straight into Claude or Codex
📱 Remote-control every session + give your agent its own email address on @agentmail
☠️ Dangerously skip permissions. YOLO. It's my computer
🔀 /ce-work --codex: route the build to @OpenAI Codex without leaving Claude
🔎 Run @slashlast30days before you /ce-plan
🥣 @meetgranola everything. Drop the RAW transcript in, don't summarize
✋ You're the taste; the agents are the hands
🎬 Build video in the CLI so an agent can write it (@HyperFrames_ )
📚 Point your agents at your notes + memory (@garrytan's GBrain, @supermemory)
✈️ Work from anywhere: mosh, tmux, @NousResearch's Hermes + @openclaw
📄 Share a plan with a human in Proof by @EveryInc
🛠️ Anything you do twice, write a skill for it. That's the compounding part
🌟 Contribute to the open source you love
🔋 Never-sleep laptop + a battery brick in the bag
🤖 Printing Press by @ppressdev: CLIs that run real life. Tesla, groceries, flights
⚠️ Watch for AI psychosis. Touch grass, talk to the people you love, build things people want (even if people is just you)

🚀 The YOLO TL;DR: paste this whole article into your agent and tell it to make a plan to set ALL of it up, one by one.

[Marco Russo @marcorus]

DAX User-Defined Functions (UDF) are generally available!
The cherry on the cake is optional parameters: a long-awaited feature during preview is included in this release.

For now, read the official Microsoft announcement; we'll produce more content on SQLBI in the coming weeks!
https://t.co/H6rfKPVLua

Now you have no more excuses!

#dax #powerbi #udf

[Dariusz Kuśnierek @dkodr]

Obniżyłem plan Anthropic z Max 20x na 5x iiiiiiiii... shit, tak się nie da żyć 😭

[Dariusz Kuśnierek @dkodr]

@dani_avila7 or use this: https://t.co/rJjXyq9ezi

[Lydia Hallie ✨ @lydiahallie]

if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt

Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result!

[Dariusz Kuśnierek @dkodr]

@RobertJBye Please extend the list of supported languages. Polish is still missing.

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[Dariusz Kuśnierek @dkodr]

@lisciasty_ Dzięki! 🙂

[Dariusz Kuśnierek @dkodr]

Chyba szybko się przyzwyczaję…

[Dariusz Kuśnierek @dkodr]

@lisciasty_ Zamieniasz na Macu miejscami Command i Option, czy przyzwyczaiłeś się do pozycji?

[Dariusz Kuśnierek @dkodr]

Warto się pospieszyć!

[SmoothCSV @smoothcsv]

The Early Supporter price for SmoothCSV License ends on May 19.

It's $19 until then, and $29 after that.

All features remain free, with or without a license.

https://t.co/e08tKxjLgx

[Claude @claudeai]

New in Claude Code: agent view.

One list of all your sessions, available today as a research preview.

[Dariusz Kuśnierek @dkodr]

O w mordę! Agent view to absolutny game-changer... 😯 A dopiero co przyswoiłem metodę pracy z wieloma zakładkami terminala i eksperymentowałem z tmux. Teraz powoli można próbować o tym zapomnieć.

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.139 changelog:

New features:
• Added agent view (Research Preview): a single list of every Claude Code session — running, blocked on you, or done. Run claude agents to get started. See https://t.co/FavKkBfWRB
• Added /goal command: set a completion condition and Claude keeps working across turns until it's met. Works in interactive, -p, and Remote Control. Shows live elapsed/turns/tokens as an overlay panel
• Added /scroll-speed command to tune mouse wheel scroll speed with a live preview
• Added claude plugin details <name> to show a plugin's component inventory and projected per-session token cost
• Added transcript view navigation: ? for keyboard shortcuts, {/} to jump between user prompts, v to toggle shortcut panel
• Added hook args: string[] field (exec form) that spawns the command directly without a shell, so path placeholders never need quoting
• Added hook continueOnBlock config option for PostToolUse — set to true to feed the hook's rejection reason back to Claude and continue the turn

Fixes:
• Fixed a deadlock where expired credentials and the forceRemoteSettingsRefresh policy setting blocked claude auth login/logout/status with no way to recover
• Fixed autoAllowBashIfSandboxed not auto-approving commands with shell expansions like ＄VAR and $(cmd)
• Fixed a bug where a hook writing to the terminal could corrupt an on-screen interactive prompt; hooks now run without terminal access
• Fixed unbounded memory growth when an HTTP/SSE MCP server streams non-protocol data — response bodies now capped at 16 MB per SSE frame
• Fixed Skill(name *) permission rules — the wildcard form now works as a prefix match, matching Bash(ls *) behavior
• Fixed settings hot-reload not detecting edits to symlinked ~/.claude/settings.json
• Fixed plugin details failing to load when the marketplace key differs from the manifest name
• Fixed /model picker "Default" row not reflecting ANTHROPIC_DEFAULT_OPUS_MODEL/ANTHROPIC_DEFAULT_SONNET_MODEL overrides
• Fixed spurious "stream idle timeout" 5 minutes after a response completed, caused by the watchdog timer not being cleared on stream cancellation
• Fixed silent exit 1 when 10+ MCP servers are configured and the cache directory is unwritable — the error message now includes the underlying cause
• Fixed a typing cursor blinking on tab names, list pointers, and select rows in dialogs
• Fixed transcript view letter shortcuts not working after mouse click
• Fixed Bash-mode up-arrow history repeating the first entry and clobbering the in-progress draft
• Fixed pasting or dropping multiple images only inserting the last one
• Fixed hyperlinks using unreadable dark navy on dark themes — they now adapt to the active theme
• Fixed model picker showing a redundant "Current model" row for third-party users whose model is set to the opus alias
• Fixed legacy Opus picker entry on PAYG 3P providers resolving to the same model as the default entry
• Fixed mouse wheel scrolling speed in Cursor and VS Code 1.92–1.104; the trackpad now scrolls at a steady rate and the mouse wheel keeps ~3 lines per notch
• Fixed scroll behavior in Windows Terminal and VS Code when attached to background sessions
• Fixed MCP resources from disconnected servers lingering in @server: autocomplete
• Fixed two-file diff snippets over-reporting the number of truncated lines by one
• Fixed Grep results not relativizing Windows drive-letter paths and count mode reporting wrong totals for single-file paths
• Fixed border-embedded text overflowing on CJK/emoji due to visual cell width miscalculation
• Fixed fuzzy-match highlighting splitting emoji and astral-plane characters mid-pair
• Fixed skill argument names containing regex metacharacters breaking argument substitution
• Fixed ProgressBar rendering a full block for an almost-full fractional cell
• Fixed task polling and https://t.co/T2AxnKEHDb being resurrected when the last subscriber leaves while a fetch is in flight
• Fixed plugin dependency resolution leaving a stale count when the manifest name differs from the source identifier
• Fixed Insights Time-of-Day chart skewing when a session has an unparseable timestamp
• Fixed keybindings using only the cmd/super/win modifier being flagged as unparseable
• Fixed claude_code.active_time.total OpenTelemetry metric not being emitted in --print mode
• Fixed claude plugin update not preserving cross-plugin symlinks inside a marketplace

Security/safety change:
• Remote Control, /schedule, https://t.co/ldz5BaC3j0 MCP connectors, and notification preferences are now disabled when ANTHROPIC_API_KEY / apiKeyHelper / ANTHROPIC_AUTH_TOKEN is set, even if a https://t.co/pbkNxHm7P4 login also exists. Unset the API key to use these features

Other changes:
• MCP stdio servers now receive CLAUDE_PROJECT_DIR in their environment, matching hooks. Plugin configs can reference ＄{CLAUDE_PROJECT_DIR} in commands
• Compaction prompt now asks the model to preserve sensitive user instructions
• /mcp Reconnect now picks up .mcp.json edits without a restart, and shows the HTTP status and URL when reconnecting fails
• /context all per-skill token estimates now account for the model's tokenizer and show rounded values
• claude plugin install <name>@<marketplace> now auto-refreshes the marketplace and retries before reporting a plugin as not found
• /plugin installed-plugin details now show hook event names and MCP server names cleanly
• /context now shows the providing plugin's name for plugin-sourced skills
• Remote MCP server reconnect retry on transient failures is now enabled for all users
• API requests from subagents now carry x-claude-code-agent-id / x-claude-code-parent-agent-id headers, and claude_code.llm_request OTEL spans include agent_id / parent_agent_id attributes
• [VSCode] Press Cmd/Ctrl+Shift+T to reopen the most recently closed session tab, configurable via claudeCode.enableReopenClosedSessionShortcut

Source: https://t.co/MyJd77ZI3d

[IFTTT @IFTTT]

Your AI assistant now has 1,000+ app connections.

IFTTT just launched as an MCP server, meaning tools like @claudeai can trigger automations, run Applets, and move data between your apps just by being asked.

Automation that talks back.
Check it out: https://t.co/m8eaR0AkYN