John Anthony

web developer

[John Anthony @thawnet]

I pledge allegiance to the flag of the United States of America, and to the Republic for which it stands, one Nation under God, with liberty and justice for all.

[Valuetainment @valuetainment]

NEW: XBOX CCO Matt Booty says gamers are too obsessed with single-player games.

[Ihtesham Ali @ihteshamali]

Palantir sells governments a war room that costs millions a year.

So, a guy named Elie just rebuilt it, put it on GitHub, and gave it away.

It's called World Monitor.

Open it and you get a live 3D globe with 500+ news feeds pouring in across 15 categories, all summarized by AI as they land.

> Military movements.
> Economic shocks.
> Natural disasters.
> Cyber incidents.
> Flight paths.
> Shipping lanes.

+ 56 different map layers you can stack on top of each other.

It scores 31 countries on a stress index and updates the number as things happen.

It watches 29 stock exchanges, commodities, and crypto in one panel.

It runs local AI through Ollama, so you can use the whole thing without a single API key.

Native desktop app for Windows, macOS, and Linux. 25 languages. Works out of the box after one clone.

[Oliya Scootercaster 🛴 @ScooterCasterNY]

NOW: Moment of EXPLOSION that went off outside of the 26 Federal Plaza in NYC around 8:30am this morning, with Immigration agents and FBI Rushing out guns drawn and FPS apprehending the suspect. Sidewalk has been shut down and building evacuated.

NYPD on scene confirmed it was a shooting and explosive device, suspect is apprehended.

Video by Cristina Panagi | Licensing @FreedomNTV [email protected]

[Breaking911 @Breaking911]

Mamdani’s NYC.

[Breaking911 @Breaking911]

INSANE FLOODING: A Queens firetruck drove through floodwaters deep enough to float an SUV as firefighters rescued stranded drivers from the roof of a truck.

[MJTruthUltra @MJTruthUltra]

This is some serious shit..

🚨 NSA Admits: “We Deliberately Massaged” Intel out of Presidential Briefing to HIDE China’s Election influence in favor of Biden

In this November 20, 2020 email chain (just declassified by President Trump, two senior intelligence officials are complaining about how the IC handled China election intelligence.

• An NSA analyst openly admits: “We have deliberately massaged our one pending PDB to avoid any direct links to the election.”

• They also chopped up a big report into 13 smaller ones and downgraded them so the China-election connection would be harder to include in the official 45-day assessment.

• The National Intelligence Officer for Cyber pushes back, saying the IC has been deliberately avoiding any mention of China and elections for months — not because of weak evidence, but for “non-substantive reasons.”

This shows clear evidence that parts of the intelligence community was actively conspiring against President Trump with a Foreign adversary.. this is literally Treason.

Under Chinese Influence
https://t.co/XulRxPkaR3

[The SCIF @TheSCIF]

Link to ALL New Declassified Election Files:
https://t.co/YFM9tYV22w

[Lara Logan @laralogan]

Watch it over and over again. Pay attention to every word. This is the moment millions of Americans who voted for accountability have been waiting for & whether you believe it or not, the enemy knows it. Buckle up. This will be the ride of our lives.

[End Wokeness @EndWokeness]

AND THERE IT IS…

China used CCP assets in the US media and social media to incite 2020's BLM uprising:

[Tim Pool @Timcast]

BLM is China

[Breaking911 @Breaking911]

New video captures the bomb blast in Monaco that targeted Ukrainian billionaire Vadim Ermolaev.

[Katie Pavlich @KatiePavlich]

Every American needs to listen to this entire speech. Not just clips. It is phenomenal. Thank you @SecRubio for recognizing the severity of the problem and most importantly, working to combat it.

[AJ Huber @Huberton]

🚨FULL SPEECH: President Trump Delivers an Address to the Nation - 7/16/26 #TrumpSpeech

220 MILLION U.S. voter files were stolen by the People’s Republic of China.

CNN, ABC and NBC Fake News are THE ENEMY OF THE PEOPLE!

Even when significant evidence of fraud has been detected, it has been buried and covered up.

[Project Constitution @ProjectConstitu]

‼️SHOCKING: I Think I Just Figured Out WHERE Blake Neff Went The Morning Of 9/10 — Was This Blake's Black SUV TAILING The Alleged Shooter Through The Neighborhood?🤔

New footage appears to show an all-black, government-style SUV slowly following the individual the FBI claims is Tyler Robinson as he walks through a residential neighborhood earlier on September 10th.

As the person turns the corner onto the street where the Steele family’s Ring camera later captures him, the black SUV pulls up and slows to a crawl — classic low-profile surveillance behavior. This is not a random car looking for an address. The driver is pacing him.

Here’s why this matters: Blake Neff has admitted he was in a black SUV that morning after landing in Salt Lake City with Charlie Kirk’s group. He claims he has almost no memory of where that SUV went or what he was doing during that time. He says they were just “marking time.”

Was the second SUV that carried Blake Neff the same vehicle seen shadowing the alleged shooter through the neighborhood? Or was another black SUV involved?

If Tyler Robinson was truly a lone actor, why was an all-black SUV trailing him? And why has Blake Neff’s whereabouts that morning remained so conveniently foggy?

We need the plates. We need the driver identified. The high-resolution footage exists. The questions are only getting louder.

CC: @RealCandaceO @baroncoleman

[𝗩𝗢𝗬𝗔𝗚𝗘𝗥𝗦 𝗥𝗘𝗩𝗘𝗡𝗚𝗘 @VoyagersRevenge]

Call of Duty Modern Warfare 4 early gameplay footage showcasing realistic weapon and animation design. The attention to detail is incredible

[West Lord @MyWestLord]

Andrej Karpathy, the CEO of Obsidian, and Claude Code just built the smartest second brain on earth.

It started with a 1-page gist that 21M people read.

Karpathy frame flips everything you know about notes: Obsidian is the IDE, Claude Code is the programmer, and your notes are the codebase. You don’t ask AI questions it forgets by tomorrow you make it maintain a living wiki.

3 commands run the whole system.

Ingest: drop an article, a podcast, a PDF, and Claude splits it into atomic pages linked to everything you already know.

Query: ask anything and it answers from your own notes, in your own words, citing your own pages instead of guessing from training data.

Lint: once a week Claude walks the entire vault, flags contradictions, kills stale claims, and wires orphan notes back in.

Then Steph Ango made his move.

The Obsidian CEO didn’t bolt an “Ask AI” button onto the app he shipped 5 skill files that teach Claude to write Obsidian’s native language: wikilinks, Canvas, Bases, the CLI. The repo crossed 13,900 stars in weeks and sits at 41,000 now.

Karpathy runs it on his own reading: 100 articles and 400,000 words, cross-linked and maintained while he sleeps.

No vector database, no embeddings, no $20 a month memory app just a folder of plain markdown and an agent that never gets tired of the boring part: the linking, the filing, the upkeep that killed every Zettelkasten since 1965.

Your vault has 3,000 notes nobody will ever reopen.

His read all of themselves by breakfast.

Every app promised a second brain this is the first one that thinks.

[Palmer Luckey @PalmerLuckey]

shipping on July 28th, same day as orders start!

[Jamon @jamonholmgren]

I'm just going to dump my whole agentic setup out here, because I see too many people missing giant chunks of this and it's hurting them.

Here's what I have and recommend:

0. an AGENTS.md that is a router -- it sends the agent to the right skills, docs, tools

1. a standard workflow doc/skill customized to my needs ... (grab Matt Pocock skills if you don't already have something) ... I tag this in most sessions with `@/AGENT_WORKFLOW.md` and it pulls it in.

2. self-healing docs for every system, and agents are instructed to keep them updated ... I tag the ones I know I need, or let the agent find them through AGENTS.md ... I also provide a more detailed summary in the first 7 lines of every doc, so they're easily greppable to find the right thing, and this is documented in AGENTS.md

3. agents always run the app ... the agent should always actually run the app itself, and test its work and fix issues as it goes, especially if running autonomously / asynchronously

4. end-to-end tests and instructions to write more and keep up to date, and docs on how to write tests, what to avoid, and a list of all the tests and what they test in yet another markdown doc ... write and run targeted tests during implementation, improve and commit with work

5. custom linters at precommit hooks looking for any problems you run across, with `--fix` fixing the problems automatically, OR if that's not feasible, it shells out to a cheaper LLM like Composer 2.5 or Sonnet to fix the problems -- NOT just flagging them, but actually resulting in cleaned code

6. cross-agent review at each major point: research, plan, implementation, and wrap-up. I mean codex, claude, cursor, whatever -- but it shouldn't be the same model reviewing the same code. And specific docs for agent review, what to look for, how to approach it. Also, personas -- looking at the code from different perspectives, such as maintainability, code quality, security, performance, AI smells, domains (e.g. "financial services expert" or whatever) ... and each persona also "owns" a set of system docs too and keeps them up to date

7. agent traces / worksheets that track what the agent is doing each session. if the agent fails partway through, you should be able to hand this worksheet to another agent and it could finish the job. commit this worksheet with the work so it's all connected and easy to reference later (you will reference these later!!), also have the agent apply git tags that correspond to specific worksheet names so they're easy to find

8. automatic agent feedback to you at the end of the session, added to a doc that is also committed with the work, that you periodically ingest into an interactive session and improve your workflows

9. a tools or bin folder that contains python or bash scripts that the agent has skills to make to make its job easier (for example, I have an `agent_review` bash script that lets the agent kick off agent reviews via CLI without knowing each agent's particular incantations) ... docs on how to make scripts effectively, and instructions to constantly build these out more

10. periodic agent sweeps through recent commits, looking for problems / gotchas from a higher level across commits

11. a coding conventions doc that is just for specific coding conventions you want to see in the code base, your review agents use these a lot (but a lot of this should be in linters)

12. an agent loop / night shift skill for autonomous work, that lays out how the agent is to approach this, from an orchestration standpoint

13. a task queue that is accessible to the agent (mine is just a TODOS.md, but yours might be in Linear etc, with a CLI to fetch via API)

14. a periodic false-confidence test audit skill that looks for tests that aren't actually testing what you think they're testing, and that fix those

15. visual regression tests -- take screenshots, compare via tool and with agent visual review, commit with work (git lfs useful here) or at least push into the PR

16. automatic performance benchmark tests that notice when performance degrades

17. performance profiling tools that can be used by agents for targeted benchmarking, trying new techniques, comparing outputs, and comparing profiles

18. end-of-shift full validations, including running all tests, performance, agent reviews, sweeps, everything -- when you return, it's all as pristine as it can be

If you have all this, your agentic coding experience is going to be very different than dry prompting and manually guiding it toward the right thing every time.