Oskar
@austegard.com
📤 264
📥 732
📝 1334
oskar @ austegard.com AI Explorer
pinned post!
I have an update to my Vibe Coding Effectiveness chart
5 months ago
1
23
9
Claude + Skills perform admirably on
@simonwillison.net
‘s Pelican on a Bicycle test, by generating an svg then visually inspecting it and iterating until satisfied. Could probably tweak the skill to be more critical: this was its 3rd attempt
claude.ai/share/d94dfb...
1 day ago
2
12
1
I may have missed it but the computer as a service implications of Claude Skills seem to not have received the deserved attention yet: Eg the Python environment (currently) has 184 different libraries your skill scripts can import
claude.ai/public/artif...
loading . . .
python_packages_inventory.md | Claude
Complete inventory of 184 Python packages in Ubuntu execution environment. Includes data science, document processing, web frameworks, computer vision & more.
https://claude.ai/public/artifacts/87ae1fd6-3817-4af9-8459-8d5c6b9bc490
1 day ago
1
12
0
I don’t know when it happened but noticed Claude can now move conversations between projects and the project instruction is changed with the move. This is great for “manual” multi-agent like work (use 2 different ICL experts, potentially armed with different project RAG) in 2 turns of same convo.
2 days ago
0
3
0
Behold my first Claude Skill -- a
@preactjs.com
Preact Developer skill
github.com/oaustegard/c...
Very first attempt, asking Claude to create something awesome:
austegard.com/fun-and-game...
loading . . .
https://github.com/oaustegard/claude-skills/blob/main/preact-developer/SKILL.md
3 days ago
2
4
1
I -- ok Claude -- created a browser extension that shows your current Claude usage as a handy gauge in your extensions bar
github.com/oaustegard/c...
3 days ago
0
1
0
CLawd (and
claude.ai
) now has Skills -- including an animated Gif creator -- SKILLS transcript here:
gist.github.com/oaustegard/9...
loading . . .
3 days ago
1
2
0
If you ever need programmatic access to anything in the
claude.ai
interface... chances are you'll find it _somewhere_ in the massive
claude.ai/api/bootstrap
response -- looks like most of the interface is driven from that one file!
loading . . .
Claude
Talk with Claude, an AI assistant from Anthropic
https://claude.ai
3 days ago
0
0
0
Sonnet 4.5 on different prompting strategies between it and Haiku 4.5:
claude.ai/public/artif...
loading . . .
haiku-sonnet-differences-summary.md | Claude
Master when to use Haiku 4.5 vs Sonnet 4.5 with practical prompting strategies, cost optimization tips, and performance comparisons for AI workflows.
https://claude.ai/public/artifacts/be52a5c4-9037-4e47-82a4-6a3e23160857
4 days ago
0
2
0
Kudos again to the
@prefect.io
crew on doing documentation right for the AI era. I love everything about this -- mcp server, llms.txt and copy as markdown shortcut behavior
5 days ago
1
9
3
How might we coax an LLM, like Claude to more readily consider cross-domain parallels to a given concept? I generated a userStyle that can be applied in a two-turn exchange with Claude seeking to broaden its search before synthesizing its answer: (README in comment)
gist.github.com/oaustegard/2...
add a skeleton here at some point
5 days ago
0
2
0
Another reason to ban golf ⛳️
add a skeleton here at some point
6 days ago
0
1
0
jules.google
has been pretty handy in documenting all my independent tool scripts, but it has an odd minor bug in its PR code review design: It encourages users to mention it by @jules -- problem is GitHub resolves that as the actual user
github.com/jules
... not associated with
jules.google
7 days ago
0
1
0
Another itch, another bookmarklet: The Claude Last Week's Conversations bookmarklet makes use of the underlying GET api callable from any Claude page to list your recent conversations, across your whole account, including each conversation's summary, and renders it in MD
github.com/oaustegard/b...
loading . . .
https://github.com/oaustegard/bookmarklets/blob/main/claude_last_week_conversations_README.md
7 days ago
1
1
0
3 years ago I was asking text-davinci-002 to use phonetic markup to entice it to create simple rhymes. Now, Sonnet 4.5 not only gets but can respond in style to a spatially structured poem like the below
add a skeleton here at some point
8 days ago
1
3
0
It took
Claude.ai
a frustrating 13 tries to *recreate* this (just from the four lines of code below) though arguably 11 of those were duplicate ID/styling/color related more so than actually getting the WebGL and shader code right... Added scroll to zoom for fun:
austegard.com/fun-and-game...
add a skeleton here at some point
9 days ago
1
3
0
Hmmmm
9 days ago
1
1
0
My github-toc web component is becoming quite useful... Here listing inventory of two different repo paths, with different settings for include/exclude and link-prefix Source:
github.com/oaustegard/o...
README:
github.com/oaustegard/o...
Example:
github.com/oaustegard/o...
=>
austegard.com/biking/
10 days ago
0
1
0
Features missing from Claude Enterprise (
@anthropic.com
). I fear this will become a lengthy thread... - Enterpise users can't use Claude Code without a Premium license!! What? - A Team concept within the Enterprise. Surprising omission -- or is this the undocumented nested Organization feature?
10 days ago
1
0
0
Plausibly overkill, but here is a drag and drop instruction you can give
jules.google
to generate a brand new
AGENTS.md
file for your Github repository. (Iteratively generated with Claude, of course...) WOMM, YMMV
gist.github.com/oaustegard/a...
Example result:
github.com/oaustegard/o...
loading . . .
AGENTS.md Generator for jules.google
AGENTS.md Generator for jules.google. GitHub Gist: instantly share code, notes, and snippets.
https://gist.github.com/oaustegard/abe91e15c6244616ceb2030aa04e7d2f
10 days ago
0
3
0
With Sonnet 4.5 (and plausibly GPT-5 Thinking) my chart below is too pessimistic. My latest vibe-coding tool is 1436 lines of html/js/css and went through 56 internal Claude revisions with only two minor error cases -- all the other iterations was me dreaming up scope creep.
add a skeleton here at some point
11 days ago
0
1
0
It’s cute how the Anthropic UX folks think 5 lines is an appropriate size for Project Instructions…
11 days ago
1
0
0
For the Claude Enterprise "owner" users out there -- I crafted a log viewer that lets you simply parse the zip formatted audit log file you can download via the management console:
github.com/oaustegard/o...
loading . . .
https://github.com/oaustegard/oaustegard.github.io/blob/main/ai-tools/claude-enterprise-log-viewer_README.md
12 days ago
1
1
0
jules.google
doesn't get enough attention. It's really quite good, and nicely implemented, the way it runs in a vm with a clone of your project, thus able to locally test its contributions before issuing the PR. Not sure when they added memory functionality? I tend to use it for clean up/docs
12 days ago
1
2
0
reposted by
Oskar
Grace
12 days ago
loading . . .
Give me a single reason why Sora2 should exist.
YouTube video by Hank Green
https://youtu.be/Vz0oQ0v0W10?si=hybk0VIQUFheongz
3
29
6
You’d think communications professor at a prestigious business school could form an argument cogent enough not to be defeated by the very technology he derides: Point:
www.dn.no/innlegg/kuns...
Counterpoint:
claude.ai/public/artif...
#norge
#ki
loading . . .
KI er keiserens nye klær
Løftet var todelt: en produktivitetsrevolusjon for næringslivet og en teknologisk snarvei til å løse menneskehetens store utfordringer. Begge deler viser seg nå å være en illusjon.
https://www.dn.no/innlegg/kunstig-intelligens/ki/ai/ki-er-keiserens-nye-klar/2-1-1880203
12 days ago
0
1
0
reposted by
Oskar
Joseph Cox
17 days ago
New from 404 Media: Apple just removed ICEBlock, the app for reporting sightings of ICE, from its App Store after DOJ pressure. ICEBlock's developer tells me "we are determined to fight this." "Capitulating to an authoritarian regime is never the right move."
www.404media.co/iceblock-own...
loading . . .
ICEBlock Owner After Apple Removes App: ‘We Are Determined to Fight This’
Apple removed ICEBlock reportedly after direct pressure from Department of Justice officials. “I am incredibly disappointed by Apple's actions today. Capitulating to an authoritarian regime is never t...
https://www.404media.co/iceblock-owner-after-apple-removes-app-we-are-determined-to-fight-this/
66
1299
629
Sonnet 4.5 is a hell of a web developer, even when just vibe-coding in
Claude.ai
; this took a few iterations, but only because I kept scope-creeping: every iteration worked as I had requested up to then:
bsky.app/profile/aust...
add a skeleton here at some point
16 days ago
0
7
0
App stores bending over to authorities and refusing unicorn tracking? 🦄 Good thing the web is unstoppable! Install this PWA straight from your browser to your Homescreen. Community-powered magical creature spotting 🌈✨with GPS🛰️and notifications 🔔 enabled!
austegard.com/fun-and-game...
loading . . .
🦄 Unicorn Spotter - Track Magical Creatures!
Track and report magical unicorn sightings in your area!
https://austegard.com/fun-and-games/unicorn-spotter.html
16 days ago
1
6
2
reposted by
Oskar
David Bier
17 days ago
Holy hell. DHS just openly stated that its agents use “reasonable suspicion” to make ARRESTS. This is blatantly unconstitutional. The Supreme Court is clear that you need probable cause to arrest someone, as opposed to stop them to ask them a question or two. This is huge b/c…
473
13987
6086
🦀
18 days ago
0
2
0
Hello, fellow 5-hr shift workers
add a skeleton here at some point
19 days ago
0
3
0
PSA! Absent a system prompt, both Sonnet 4 and Sonnet 4.5 believe they are actually Sonnet 3.5... I wonder what this signifies? Is it training data timing related -- that the current model at the time of training 4 was 3.5?
19 days ago
1
2
0
Hey at least now I can tell prior to hitting 98% token allowance usage...
20 days ago
1
2
1
I should create a hat that says You're absolutely right. Even Claude 4.5 tells me I am...
20 days ago
2
3
0
I'm not vibe coding, I'm flibbertigibbiting
20 days ago
2
5
0
Ok, this is fascinating. Claude 4.5's document creation tooling uses an external
SKILL.md
file for explicit instructions on how to use PowerPoint. Presumably the same for other office types. See
gist.github.com/oaustegard/4...
20 days ago
1
6
2
PSA: The recent_chats tool in
CLaude.ai
is ok, but far from complete. It does not capture any context (file/fetch result, etc) or extended thinking by the model. If you truly want to continue a conversation you're better off copying manually or via a tool e.g Claude Pruner
github.com/oaustegard/b...
loading . . .
https://github.com/oaustegard/bookmarklets/blob/main/claude_pruner_README.md
20 days ago
0
0
0
Is there an active bug in
Claude.ai
and/or Opus 4.1? At times when Opus 4.1 is chosen it identifies itself as Sonnet 3.5, other times as Sonnet 4.0 (And here I was surprised at the superficial answers I was getting from Opus, compared to Sonnet) Paging
@anthropic.com
(is there anybody out there?)
20 days ago
1
2
0
reposted by
Oskar
G. Willow Wilson
21 days ago
I mean yes this is funny, but the fact that these unconstitutional stormtroopers are so directionless that they literally stand around waiting for random nonwhite delivery guys to bike past them is just pathetic. No mandate, no mission, no clue. Just racism.
add a skeleton here at some point
598
26200
7751
Pardon the efficiency of my method of presentation: but what if
@anthropic.com
tweaked Claude Desktop into a recursive agentic framework?
claude.ai/public/artif...
loading . . .
Claude Desktop as Agentic Framework | Claude
Transform Claude Desktop into an AI workforce operating system - discover how Projects could become coordinated agents. Built with Claude AI.
https://claude.ai/public/artifacts/178c529b-7c34-4e51-9f9b-d94a23dccf38
21 days ago
1
6
0
Scam ads are getting stranger and stranger
22 days ago
0
0
0
reposted by
Oskar
Mother Jones
22 days ago
This is madness.
loading . . .
Trump says he'll send troops to Portland and sanction “full force” against Americans
That would be illegal, except perhaps in moments of serious unrest—which this is not.
https://www.motherjones.com/politics/2025/09/trump-us-troops-military-portland-oregon-full-force-truth-social/
47
349
142
reposted by
Oskar
Senator Ron Wyden
22 days ago
Taken just a few minutes ago outside the ICE facility in Portland that Trump claims is under siege. My message to Donald Trump is this: we don’t need you here. Stay the hell out of our city.
loading . . .
509
13175
5516
Again I don’t want government by AI but OMG is AI better than some in government:
claude.ai/share/932dd6...
🍊👬Misrepresented 2014 Article:
jamanetwork.com/journals/jam...
22 days ago
0
4
1
reposted by
Oskar
Matthew Guariglia
23 days ago
I spent the week at the police surveillance convention and let me tell you my biggest observation: The name of the game now is consolidating as much information as humanely possible from surveillance devices, the internet, other governmental data, and literally a million other places. 🧵
46
1970
1046
🤢
add a skeleton here at some point
23 days ago
0
2
0
I'm so glad they ended the weaponization of the federal government (
www.whitehouse.gov/presidential...
if you'd forgotten) It presents yet another opportunity for Claude to shake its AI head:
claude.ai/share/c41cb9...
loading . . .
Federal government action investigation
Shared via Claude, an AI assistant from Anthropic
https://claude.ai/share/c41cb940-a940-4a71-9f81-909a6137f818
24 days ago
0
0
0
TikTok is looking like an absolute steal compared to TEGNA, just saying. Engagement, demo, growth (or lack of decline), regulatory burden, geographic constraints...
24 days ago
0
0
0
I guess they did NOT learn from the confusion around Claude 3.5 Sonnet 061024 and Claude 3.5 Sonnet 102224 ...
add a skeleton here at some point
24 days ago
0
3
0
I can't make up my mind if this Bluesky stat is good or bad. I _think_ good?
add a skeleton here at some point
24 days ago
0
0
0
Load more
feeds!
log in