Our spend on DataDog is too high ->
Hey Opus 5.5 switch everything to Grafana and VictoriaMetrics ->
1 day later we spend 38x less on all logs, alerts, and graphs. No loss of functionality.
Nvidia board underestimated the challenge of managing global semiconductor supply chain.
There are 1.3m subcomponents in a Vera Rubin rack. Prob 1,000 high-tech vendors and 85% of are in East Asia (South Korea, Taiwan, China, Japan).
Many of those deals have no contract and are negotiated over a local beer (probably mixed with a rice-based liquor), some type of deep fried protein, comically small restaurant chairs and then closed with a spit and handshake.
I dislike semantic-layer and ontology obsession because it is fundamentally a fixation on non-terminal outcomes. We have an enormous appetite for building and optimizing the preconditions for useful work, without establishing that those preconditions are actually a binding constraint on achieving useful outcomes or meaningfully contribute to them.
Much of the time I suspect there is actually not much genuine interest in achieving truly useful outcomes in the first place despite whatever vague platitudes are trotted out.
Solche Schmiedehämmer wurden den deutschen nach dem Krieg verboten. Deshalb perfektionierte man die Schmiedepressen. Damit wurde man dann wieder führend in der Welt.
I ran a PageRank-driven analysis on all recent news coverage related to Jensen, and traced how the New York Times shaped the entirety of this narrative: https://t.co/qKGMJ2LBV8
--
NVIDIA has lost over $1 trillion in market value since the first New York Times story broke about Jensen. I dug deeper to analyze how the news originated and spread, running a swarm of agents which analyzed almost 2000 stories, across 40 US and European news outlets, and applying PageRank to understand how they cited each other.
Core findings:
- Primary news driver: NYT, with 88 stories, most-cited
- Volume drivers: WSJ - 99 stories; Bloomberg - 140 stories; NY Post - 68 stories
All of this started from unknown sources who gave information to the NYT, which then ran the spy story (still unproven), and it was then picked up in other news publications. Curiously, even after that story, there was a 9 day period of extremely low volume reporting (28 stories only), after which there was a sudden spike after Jensen's own letter to NVIDIA staff. NYT then had multiple sequential spy and affair stories, which fed a wave of further news coverage. It was the originating hub of negative Jensen coverage. Multiple outlets since then had an explosion in stories about him starting earlier this week as well.
Overall, as you see this data, you will observe this was an exceptional media onslaught against Jensen with sharply negative coverage about him, his work, style, and family. Infact, it was brutal, and unlike coverage in the past of CEOs who have had affairs (such as Intel CEO in 2018). For eg, NYT ran just 2 stories about Intel's CEO who had an affair with his employee, compared to 88 on Jensen! Why ?
This analysis used a technique of how Google originally ranked webpages, using PageRank, and does deep dive link analysis so you can view how the news spread. What struck here was that it did not matter if there were proven facts or credible sources: the outcome here was pre-decided. The news was making the reality which it wanted.
During this period, NVIDIA has lost $1.27 trillion in market value since the first story broke. On Nov 12th-13th, further news broke that both the US Justice Department, and Singapore - are unable to even conclude the spy allegation.
This has been a catastrophic attack on one of the hardest working founders in modern times, who took an idea from a Denny's booth, through multiple instances of almost going out of business, to building the foundation of the entire modern world with how the NVIDIA story played out. Thanks to Jensen, we have hope that many formerly incurable diseases will get solved by AI, that quality of life will and have improved for billions around the world.
Now I do not know if he will come back as CEO or not, but I hope he does. What happened to him here, and to the wider industry, was not fair.
call me crazy but its pretty clear now.
rea + mitmproxy is going to expose more apps in 2026 than every data leak combined.
mitmproxy records everything an app sends over the network. rea reads that recording and points at the exact code that sent it.
so you dont just see "something phoned home". you see what left, where it went, and which part of the app did it.
if this lands on your timeline dont scroll past it.
heres the 60-second setup, free:
1. install mitmproxy and point one app on your own machine at it
2. save the session as a .har file
3. run npx rea-agents setup
4. tell claude code: "read session.har with rea. list every request that carries my data and the code that sent it"
run it on the apps you already trust. thats where it gets uncomfortable.
thats it. thank me later.
most people will never check what their apps send.
the ones who do will stop trusting the rest.
simple as that.
Paradigm is open today: https://t.co/scXrlIfCTR
Each reply below shows one thing Clover, our tutor, can do.
If there's something you've always wanted to learn, reply with it. We'll build the first lesson for as many as we can today.
Vibecoders, 𝗜'𝗺 𝗯𝗲𝗴𝗴𝗶𝗻𝗴 𝘆𝗼𝘂, add this to your AGENTS.md:
"Walk through two-way doors and show me after. Stop at one-way doors.
Two-way door: anything you can undo. Code, branches, PRs, test data, dev infra.
One-way door: anything you can't. Prod data, deploys to users, force-pushing a shared branch, deleting what you didn't make, a message sent to another person.
If my answer would be a rubber stamp, don't ask. If running something could answer the question, run it instead. Save questions for taste and product calls only I can make. Ask one at a time, with your recommendation, using your built-in question tool."
Google's 19K-star GitHub repo deliberately gives its AI reviewers the memory of a goldfish.
And there's a surprisingly good engineering reason for it.
Imagine spending two hours with a coding agent discussing a new feature. You've explained the architecture, argued over edge cases, rejected three approaches, and finally agreed on a design.
Now you ask that same agent to review the specification.
It understands everything because it remembers the entire conversation. Even if the document leaves out half the reasoning, the agent can silently fill in the gaps.
A new engineer reading that document next week won't have that luxury.
Google engineers built the Elephant-Goldfish Model around this problem.
One agent, the Elephant, retains the project context and helps develop the specification. Fresh Goldfish reviewers receive the document and its referenced source material, without the earlier conversation.
They examine whether the design makes sense on its own, challenge architectural decisions, look for overlooked edge cases, and check implementation readiness.
The engineer reviews the findings, resolves the important ones, and approves the specification before implementation.
The open-source plugin includes seven skills covering brainstorming, drafting, independent reviews, resolution, codebase documentation, and documentation drift checks.
It works with coding assistants including Claude Code, Codex, and Antigravity.
The idea is beautifully simple.
If a fresh engineer cannot understand your design without sitting through the original discussion, you probably haven't finished explaining it.
Here's the GitHub Repo: https://t.co/YbLeOWKGVR
Introducing Facade Code: https://t.co/xl8bFRBeOe
It's a VS Code extension that adds an agent panel to allow you to run agents in parallel, and it also allows agents to communicate and read each agent's screen and type directly in the input box to provide the "agent use" feature. Also, it integrates with SSH and remote control to allow agents to communicate with agents on different machines and also allow you to use your phone to control the whole agent cluster.
This week we improved support for open-source models and enhanced our docs with more examples.
Below we demonstrate with a Codex and DeepSeek example, where GPT only makes the plan and sets the standard, and a DeepSeek team handles all the execution to build a bakery website. We also compare it with Codex and DeepSeek working alone.