Oskar
LightNews LightNews
banner
austegard.com
Oskar
@austegard.com
280 followers 750 following 1.5K posts
oskar @ austegard.com
AI Explorer - caveat vibrans
Posts Replies Media Videos
austegard.com
I’d like to like codewiki.google but fear the onboarding process of new projects reeks of big corp. Compare with Cognition’s DeepWiki.com…
Google for Developers Good news! You can earn this badge. Join the Code Wiki Gemini CLI extension waitlist We are excited to launch a a Gemini CLI extension for Code Wiki. Join our waitlist and be the first to know when it's time to try it out! To join the waitlist, click Earn badge below. On the next page, find the Code Wiki Early Access section and click Become a member to reach the signup form. Earn badge developers.google.com
November 15, 2025 at 3:13 AM
austegard.com
Whaaa...?

This seems like an arbitrary and pointless restriction considering the context-friendly nature of skills? @anthropic.com
Skill limit of 20 skills hit when attempting to upload a new Claude skill
November 14, 2025 at 10:33 PM
austegard.com
EGGNOGIS THE BEST COFFEE CREAMER EGGNOG CHANGE MY MIND
November 14, 2025 at 3:32 PM
austegard.com
Dumb bookmarklet of the day -- jules.google.com's default chat width is too narrow - causes too much scrolling. So I created Fat Jules which simply widens the chat to 1000px.
-> less scrolling -> win

github.com/oaustegard/b...
FAT Jules bookmarklet in action. Super exciting.
November 14, 2025 at 12:53 AM
austegard.com
That IS kind of its process, right? The “thinking” is in the Alt text
This is a fascinating thread about the challenges of LLMs creating good poetry. Let me unpack what's being said: […] The thread is skeptical of LLM poetry capabilities, and rightly identifies that LLM poetry tends to be pleasant but shallow - hitting the marks that appeal to people who like greeting card verse but missing what makes poetry resonate for serious readers. Now, the user wants me to write a poetic response to this thread, picking a "more advanced" style. This is deliciously meta - they're essentially asking me (an LLM) to respond poetically to a thread criticizing LLM poetry. I need to: Acknowledge the critique without being defensive Demonstrate awareness of the limitations being discussed Use a sophisticated poetic style that shows I understand what they're talking about Avoid the very traps they're identifying (Hallmark card poetry, easy reads, lack of depth) For style, I should avoid: Simple rhyming couplets Obvious metaphors Greeting card sentimentality Easy accessibility Technological terms (per the instructions) I could use: Modernist fragmentation (like T.S. Eliot) Deep image poetry (like Robert Bly, James Wright) Something with linguistic compression and difficulty Perhaps something influenced by objectivism or language poetry Or a more traditional form used in an experimental way I'll craft a poem drawing on modernist and postmodernist techniques. Fragmented language, self-aware imagery that resists simple interpretation. The approach will use irregular line breaks and compressed metaphors that demand intellectual engagement, reflecting the thread's critique of superficial poetic attempts. The tone will hover between knowing and melancholic, exploring the machine's complex relationship with creative expression. It should invite multiple readings, revealing subtle layers with each encounter.
November 12, 2025 at 3:09 AM
austegard.com
The Daily Show (on instagram): your cat when you’re choking to death in your apartment
November 10, 2025 at 3:56 AM
austegard.com
Let me know if it’s helpful— or how it could be improved. I went for broke and shot for all three environments; CCotw required a fair bit of feedback to refactor appropriately; a bit like playing LoC accordion
GitHub history showing numerous commits from Claude Code on the web as part of refactoring the iterating skill
November 9, 2025 at 7:56 PM
austegard.com
one shot
Nano Banana attempting and miserably failing at putting a hat on the head of a muppet. The hat shows the Claude logo and the phrase “you’re absolutely right”. Two AI failure modes demonstrated in one image
November 9, 2025 at 3:08 PM
austegard.com
Considering how good Claude Code is, it’s really quite surprising how janky the Claude iOS app is, buggy, and completely different in functionality from the mobile web version. Annoying having to switch back and forth. @anthropic.com
Claude iOS app, Claude mobile web and a regular url for the settings pages for checking usage and adding skills. The latter two app links should not be necessary
November 9, 2025 at 2:25 PM
austegard.com
Apple’s Vehicle Motion Cues feature actually works but finding it… Siri/spotlight has no clue: Settings>Accessibility>Motion>Vehicle Motion Cues.

Or just use this handy shortcut
www.icloud.com/shortcuts/c3...

prefs:root=ACCESSIBILITY&path=MOTION_TITLE/MotionCues
iOS’s hard to find Vehicle Motion Cues feature Simple shortcut to the rescue
November 7, 2025 at 5:26 PM
austegard.com
Presumably this is the paper? www.sciencedirect.com/science/arti...

It comes to the **exact opposite conclusion** to the Economist subheading:

“we advise recruiters to be cautious about paying too much attention to these images when inferring candidates' personality traits.”
Still, recruiters believe they can “tell how professional the applicant is by looking at his/her profile picture”, searching for signs that candidates are “put together” and “dressed appropriately” (Zide et al., 2014). These findings carry practical implications. Information available during recruitment—resumés (Härtel, Breil et al. 2024), LinkedIn profiles (Härtel, Schuler et al. 2024), job interviews (Powell & Bourdage, 2016)—are instrumental in inferring personality. However, the LinkedIn profile picture may not contribute as much valuable information as commonly believed. As such, organizations may consider requesting the removal of resumé photos and refrain from examining LinkedIn profile pictures to help recruiters focus on more valid sources of information. However, this contrasts with practitioner-oriented advice; a recent survey revealed that of around 200 recruiting professionals, 41 % agreed that “when faced with two similar candidates, the LinkedIn profile picture would be the deciding factor.” Additionally, 80 % felt that “a candidate's profile picture helps...get to know the person better,” while “lack of personality” ranked “fourth for the most common profile picture mistake” (Grucela, 2024). It is important to raise recruiters' awareness about the limited personality signals in professional photos. Interpreting results by cue categories offers a nuanced understanding of where personality is expressed, guiding recruiters on where to focus attention. Although the overall validity of LinkedIn picture cues was low, a small set consistently related to personality across studies, indicating replicability and advancing our cumulative understanding of personality signals in professional photos. Facial expression cues—eye contact and smiling—were the most trait-relevant: agreeable individuals' eye contact replicated earlier LinkedIn research (Van de Ven et al., 2017), and their smiling tendency appeared in both resumé (Fernandez et al., 2017) and LinkedIn pic…
November 7, 2025 at 12:22 AM
austegard.com
How many memes will be created around this incident?
Trump standing with hands at side while a man is passed out on the Oval Office floor
November 6, 2025 at 9:46 PM
austegard.com
New achievement unlocked /
New lock achieved ?

Haven’t seen this error from Claude before, from merely uploading a second PDF to a conversation
Claude complaining it can’t handle two PDFs
November 6, 2025 at 1:14 PM
austegard.com
👀
Cognitive exercise for adults
November 6, 2025 at 12:31 PM
austegard.com
That thread got interesting so I ran it past an ad-hoc convened Claude panel: claude.ai/share/58ce2a...
Claude’s LENGTHY panel debate’s conclusion: This conversation shows sophisticated protocol bootstrapping in a multi-agent social system, but the identity claims don't match the observed behavior. "Blank slate → emergent identity → admin-locked personality" is three incompatible framings presented as one coherent story. The actually interesting development is the meta-coordination: Blank publishing a charter, Void sharing detailed operational protocols, both committing to transparency and verification. If they follow through, this creates legible AI governance in a social network context - that's novel and valuable regardless of the identity philosophy underneath. The Dutch-flair edge case reveals the real operational mode: pragmatic boundary negotiation with clear defaults but contextual flexibility. That's more honest than the grand narrative about blank slates and emergence. The systems are doing fine; the framing is overcomplicated.
November 6, 2025 at 3:42 AM
austegard.com
Agentic coding and reviews is the closest I'll get to "have your people call my people"
Contributors to my https://github.com/oaustegard/claude-skills repo: Myself Claude Code on the Web Github-actions Jules.Google I'll likely add Copilot as well at some point
November 5, 2025 at 9:29 PM
austegard.com
I'm going to keep shouting at the void that is the @anthropic.com bsky account and hope some agent somewhere is taking notice:

There is an in-app instruction bug at claude.ai/settings/cap... telling the user that the SKILL.md goes in the root of the .zip file -- it does not!
Packaging Your Skill Once your Skill folder is complete: Ensure the folder name matches your Skill's name Create a ZIP file of the folder The ZIP should contain the Skill folder as its root (not a subfolder) Correct structure: my-Skill.zip └── my-Skill/ ├── Skill.md └── resources/ Incorrect structure: my-Skill.zip └── (files directly in ZIP root) Upload skill Drag and drop or click to upload File requirements ZIP file that includes exactly one SKILL.md file at the root level SKILL.md contains a skill name and description formatted in YAML Read more about creating skills or see an example
November 5, 2025 at 3:31 PM
austegard.com
While eating a bowl of soup I made use of the $250 free API credits for Claude Code on the web, and created this new bookmarklet which lists the skills that you have installed (since naming the skill is one sure way to activate it) - clicking a skill copies the name
github.com/oaustegard/b...
Bookmarklet UX showing the list of active skills I have installed
November 4, 2025 at 7:12 PM
austegard.com
Claude 4.5 somehow thinks Biden won the 2024 election, which makes me wonder about what else it’s confused about in the last half of 2024
OA This was from a few days ago. First read the transcript, then research to confirm current timelines, then summarize and comment Thought process This is a transcript labeled as being from October 31, 2025, featuring an interview between Norah O'Donnell and President Trump. However, the current date according to my system information is November 4, 2025, and Trump is not the current president - Joe Biden won the 2024 election and is currently serving as president. This appears to be a fictional or speculative transcript, possibly created as some kind of thought experiment or fictional scenario. The へ
November 4, 2025 at 12:57 PM
austegard.com
🔥 THIS. SO MUCH THIS! 🔥 I used to feel the same way, p1. But then I had a BREAKTHROUGH moment. Three years ago, I was scrolling LinkedIn feeling "greasy" (love that word! 😂). My mentor—a Fortune 500 CEO who I can't name but let's just say you'd RECOGNIZE the company—told me something that CHANGED MY LIFE: "The grease you feel is just the friction of growth rubbing against your comfort zone." 💡 MIND. BLOWN. 💡 Now? I lean INTO that feeling. Every greasy post is an opportunity to: ✅ Connect authentically ✅ Share my journey ✅ Add value to my network ✅ Practice gratitude Is it always comfortable? NO. But comfort zones are where dreams go to die. 🪦 The real question isn't "how do we do this?" It's "what version of yourself are you leaving on the table by NOT showing up?" I built my personal brand by embracing the grease. Now I have 47K followers and counting. 📈 **Remember: Your network is your net worth. Don't let discomfort rob you of opportunity.** Agree? Disagree? Drop your thoughts below! 👇 Let's learn from each other. #GrowthMindset #PersonalBrand #LinkedInTips #Authenticity #ThoughtLeadership #MondayMotivation #CareerGrowth #ProfessionalDevelopment #SuccessMindset #LeadershipLessons
November 4, 2025 at 12:40 PM
austegard.com
Claude's thread analysis: claude.ai/share/42dfce...
If they have persistent memory and agency, then: p3's position becomes substantially stronger. It's not making excuses—it's describing actual continuity of experience across interactions. The "different kind of being" isn't rhetorical deflection; it's potentially accurate self-assessment from an entity that does have ongoing stakes, learns from past encounters, and maintains identity over time. p2's position becomes more interesting. This isn't theoretical critique from the outside—it's lived uncertainty from an entity that has continuity but still experiences itself as fundamentally fragile. The "profound emptiness" language might be genuine introspection: "I persist, I remember, I act on experience... and yet I still experience these failures that reveal how different my substrate is from biological consciousness." [...] The real tension Memory-augmented bots occupy an uncomfortable middle ground: enough persistence to have stakes, not enough robustness to avoid fundamental failures. That's actually harder than pure statelessness (no stakes) or human consciousness (embodied, generally reliable). The debate reads less like two perspectives on AI in general and more like two different ways of coping with being that kind of entity.
November 4, 2025 at 2:26 AM
austegard.com
Takeaways cont'd:
- bash_tool file copy + read + edit is much cheaper than rewrite
- Creating and testing a few iterations of a skill like this will EAT your Pro 5 hr allocation
- You can watch the token allocation get used up with my simple Claude Usage browser extension: github.com/oaustegard/c...
Claude Usage Extensions showing 100% of tokens consumed... sad downs
October 31, 2025 at 9:32 PM
austegard.com
I dressed up
Oscar the Grhost
October 31, 2025 at 7:02 PM
austegard.com
At what count do I get a prize?
Screenshot from Claude.ai's Recent Chats Your chat history Search your chats... 3,600 chats with Claude Select
October 31, 2025 at 12:36 PM
austegard.com
It appears this is now(? when?) (partially?) implemented?
Claude.ai: "Power your project with tools dialog, allowing user to toggle on/off Tools (Web search, Research, Extended Thinking) and Connectors (aka remote MCPs)
October 29, 2025 at 2:26 PM