David Golden (@xdg) header
David Golden (@xdg) profile picture

Senior Staff Engineer (ex Director) @ MongoDB. I like building things, solving problems and playing games, occasionally at the same time. Opinions are my own.

New York, NY
Joined February 2009
Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)Photo by David Golden (@xdg)
I'm a doctor. A deep subspecialist. If you have unexplained symptoms, or a diagnosis where the treatment isn't working, upload ALL your records into a frontier LLM. Tell it not to just agree with you. Suggested prompt in first reply. This WSJ story about a "medical mystery" solved by AI after decades of specialists missed it? It's not rare. It's not even uncommon. It might be the norm. I see it literally all the time. Sometimes I'm the specialist who missed it. At reading your whole history and connecting the dots across it, any frontier AI is WAY better than your doctors. None of us ever has time to read the whole chart. I strongly recommend Claude, but any frontier model works. Set it to the highest reasoning and effort. Tell it to ask you every question it needs answered. Tell it you know it can't diagnose you, and your goal is the most likely differential diagnosis and a one-page summary with its rationale. Take that to your doctor. If they don't take it seriously, find a new doctor.
After years of suffering from perplexing symptoms, WSJ’s Katherine Bindley turned to AI—and finally got answers to the complex condition her doctors had overlooked. Read more: 🔗 mrf.lu/27KSt
48
65
14
642
141,585
David Golden retweeted
Attention all companies: I never want to use your AI assistant on your website. I want to use *my* AI assistant on your website
234
479
134
8,274
253,203
[new blog post] Writing as a thinking tool muratbuffalo.blogspot.com/20…
3
24
6
214
30,613
[new blog post] Atlas Infinite: MongoDB's Disaggregated Architecture muratbuffalo.blogspot.com/20…
16
74
6,858
How to effectively debug with agents when you no longer read or understand the code In this post, I propose a debugging framework for agents that doesn’t rely on human knowledge of code to get to the right “root cause” The TL;DR are the screenshots. Link to post in the reply.
Writing a post about “how to effectively debug code when you no longer fully understand it”. This is real bug I had to fix in ~9K LOC (100% AI generated). None of the tactics I started with here helped “root cause” the issue, lol. Had to take a different approach to isolate it.
40
126
25
1,691
152,108
David Golden retweeted
you know who else thought a lot about sandboxing? paul atreides
6
10
203
6,893
David Golden retweeted
You can now set Claude Code's output style to Concise. Claude leads with the result, keeps responses short, and still gives full detail when you ask. Turn it on in /config → Output style, or set "outputStyle": "Concise" in settings.json.
937
990
767
19,280
3,369,788
David Golden retweeted
MongoDB is looking for a Senior Engineering Manager. DevProd AXIS team (AI, X-functional tools, Insights, and Signals) responsible for metrics, observability, & agentic ecosystem for AI-driven development across engineering. mongodb.com/careers/jobs/805…
3
5
481
David Golden retweeted
The @latentspacepod team and I will be speaking at Mongodb's .local buildfest today 10a-4pmish, come by! mongodb.com/events/mongodb-l… We'll be covering: - tba Agent infra with @BazeleyMikiko! - the state of embeddings/reranking with @frankzliu @VoyageAI head of Applied ML - wearable AI with @a_israelov, CTO of Mentra! - their state of managed MCP with Gaurab Aryal - Jim Scharf, CTO MongoDB - AIE top speaker Apoorva Joshi click on only if you are gonna come... take one of my tix MDBLCL26INSIDER!
19
4
1
25
9,892
When I saw the movie "Don't Look Up" I thought it was unrealistic. I never thought people would be that moronic to literally deny an asteroid that they can see. But seeing all the cynicism out there thinking that rogue AIs are just marketing stunts, I kinda get it now.
46
84
13
1,305
79,855
David Golden retweeted
What if Raft could deliver fast, consistent reads without the usual lease complexity? The new MongoDB Research Blog launches with its first post from @jessejiryudavis on LeaseGuard, a simpler approach to Raft leases designed to reduce read overhead, improve read availability, and restore write throughput quickly after leader failover. Discover here how to recover reads faster and move past the downtime: mongodb.social/6010BElHtC
1
5
22
8,957
David Golden retweeted
Excited to get my pre order copy of @catehall ‘s new book! You can just preorder it 😊
3
12
880
David Golden retweeted
I’ve been thinking a lot about this pattern recently, because volatility: You believe X. X doesn’t come true. You accept this and learn from it: “X is not true” You move on to believe Y. But … you never asked yourself “why did I believe X in the first place?”
1
1
19
1,762
David Golden retweeted
At first AI seems to reduce the cost of software development, so people lower the bar on what projects seem worth it. So more software gets developed. However, it turns out that costs may not be reduced, just the illusion of cost through faster delivery. We can move faster, but that speed requires tokens (which is money). The other thing is that with more software comes more responsibility. If too much software gets written, we face catabolic collapse as we get crushed by the sheer amount of software we now need to support. This all tells me the following. 1) AI can speed up delivery but not necessarily save money. 2) We can't just write software because it appears easier to do, because else we drown in low value software that must be supported. 3) Low value software may help with tactical issues but not strategic ones as strategy cannot be built on commodity. 4) If AI doesn't save money and a high volume of (lower value) software is bad, then we should use AI instead to work on harder projects with clear ROI. Projects that might have been unviable due to the complexity and risk of implementation and/or lack of expertise. The lesson is that we should continue to apply sensible constraints on what we build, and leverage AI to do harder more strategic projects (as well as fast prototyping).
2
5
1
36
3,362
[new blog post] Our MongoDB TLA+ Workshop muratbuffalo.blogspot.com/20…
2
7
1
31
2,610
David Golden retweeted
Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we thought, and the implications deserve greater attention. anthropic.com/institute/recu…
1,708
4,502
2,991
28,175
18,967,812
David Golden retweeted
some thoughts on working with ai models • context as infra • taste as config • verification for autonomy • scaling via delegation • closing the loop eugeneyan.com/writing/workin…
40
45
7
300
31,470
David Golden retweeted
excited to share this and help everyone be more cyber secure
Claude Security is now in public beta for Claude Enterprise customers. Claude scans your codebase for vulnerabilities, validates each finding to cut false positives, and suggests patches you can review and approve.
2
2
8
3,588
David Golden retweeted
Today, we're introducing MongoDB Agent Skills. Official, curated skills that give your coding agents the MongoDB expertise it needs to produce reliable schemas, queries, and code that follow proven best practices. Install in seconds: npx skills add mongodb/agent-skills Or grab the plugin for @claudeai Code, @cursor_ai, @GeminiApp CLI, and VS Code ➡️ mongodb.social/6010B6lwca
6
12
32
5,128
David Golden retweeted
do this to protect yourself against supply chain attacks $ cat ~/.npmrc min-release-age=7 $ cat ~/.config/uv/uv.toml exclude-newer = "7 days"
if you don't have these in your configs you're ngmi
51
276
23
2,739
411,400