Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.
- 33
- 1
What is this place?
This website is a place for people who want to move past shady thinking and test their ideas in a
court of people who don't all share the same biases. Our goal is to
optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.
The weekly Culture War threads host the most
controversial topics and are the most visible aspect of The Motte. However, many other topics are
appropriate here. We encourage people to post anything related to science, politics, or philosophy;
if in doubt, post!
Check out The Vault for an archive of old quality posts.
You are encouraged to crosspost these elsewhere.
Why are you called The Motte?
A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently,
it's an element in a rhetorical move called a "Motte-and-Bailey",
originally identified by
philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial
but high value claim to a defensible but less exciting one upon any resistance to the former. He likens
this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for
the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired
propositions to which one retreats when hard pressed."
On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.
New post guidelines
If you're posting something that isn't related to the culture war, we encourage you to post a thread for it.
A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts
such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a
submission statement. A submission statement is required for non-text sources (videos, podcasts, images).
Culture war posts go in the culture war thread; all links must either include a submission statement or
significant commentary. Bare links without those will be removed.
If in doubt, please post it!
Rules
- Courtesy
- Content
- Engagement
- When disagreeing with someone, state your objections explicitly.
- Proactively provide evidence in proportion to how partisan and inflammatory your claim might be.
- Accept temporary bans as a time-out, and don't attempt to rejoin the conversation until it's lifted.
- Don't attempt to build consensus or enforce ideological conformity.
- Write like everyone is reading and you want them to be included in the discussion.
- The Wildcard Rule
- The Metarule
Jump in the discussion.
No email address required.
Notes -
Tooting my own horn. December 1, 2022 I predicted:
This was before GPT4 was on the scene. Reiterated it 3 months ago
And then today I read this nice little headline:
If they can stop the damn thing from hallucinating caselaw and statutes, it might already be there.
But, let me admit, that if we don't see downward pressure on first-year wages or staffing reductions this year, I missed the meatiest part of the prediction.
There's the counter-argument that AI lawyers will actually stimulate demand for attorneys by making contracts way more complex. I don't buy it, but I see it.
Paralleling @JarJarJedi's story, I tried to outsource some annoying research to Gemini and it just gave me the run around. [TW: Boring ops work] I was trying to find a way to copy a large-ish Cloud SQL MySQL DB from one GCP project to another. Solutions I was given:
In the end I probably could have just spent 30-45 minutes reading the docs and figured out what my real options were rather than spending severally hours trying half-baked solutions. I just use Gemini for short scripts, text editing operations, and boilerplate now.
[PS. I think we can use PSC to solve the problem above]
I copied your post into o4-mini ChatGPT, without the last two paragraphs and the PSC idea, and this was spit out after a minute:
—————————
Here’s a proven, zero-Downtime–capable way to copy your Cloud SQL for MySQL database from Project A into Project B without dumping to GCS or exposing it publicly: use Database Migration Service (DMS) in the destination project, treating the source instance as a “self-managed” MySQL endpoint. This leverages private connectivity (VPC peering) so data never traverses the public Internet.
Prepare your source Cloud SQL instance • Enable binary logging & GTID, and use row-based replication on your source: set log_bin, binlog_format=ROW, gtid_mode=ON, and retain logs (expire_logs_days or binlog_expire_logs_seconds) for at least a week. • Create a replication user with REPLICATION SLAVE, REPLICATION CLIENT, SELECT, SHOW VIEW, EXECUTE, TRIGGER, etc., per your migration type .
Enable DMS in the destination project • In Project B, enable the Database Migration Service API and grant yourself the Database Migration Admin role.  • Ensure the DMS service account has compute.networkAdmin so it can set up peering. 
Set up private connectivity (VPC peering) • In Project B, create a Private Connectivity Configuration under DMS → Private connectivity. Select the VPC from Project A that holds your source instance’s private IP; DMS will automatically peer its service-network VPC into that network. 
Create your Source Connection Profile • Still in Project B’s DMS UI, go to Connection Profiles → Create Profile → Source. • Engine: MySQL • Classification: “Self-managed MySQL” (even though it’s Cloud SQL)—this bypasses the same-project restriction . • Host: the private IP (or public IP + authorized network) of your Cloud SQL source. • Credentials: use the replication user you created. 
Create & run the Migration Job • Go to Migration Jobs → Create Migration Job in Project B.
DMS will do an initial data copy over the peered VPC, then (if you chose Continuous) apply changes in near real-time.
Why this works • No GCS buckets or manual dumps needed.
• Data never leaves Google’s private network—no public IP exposure.
• Cross-project works seamlessly by treating the source as self-managed and running DMS in the target project.
• Scales to multi-TB databases with minimal downtime (CDC mode)
———————————-
Is it wrong?
IIRC Gemini gave me this too. It's correct except this one line, where it hallucinates that it's possible to select a VPC from another project (you can't), and therefore the whole set of instructions are useless.
This btw is an extremely common failure mode in my opinion. You ask it to do something complex, and it builds a very nice way to do it, except there's one link in the chain that it completely invented out of the thin air. And it totally worked just like that if that link existed, except it does not. It could be an API method, a tool, a UI option, I've encountered a number of things - it all looks very neat, except for one detail that completely ruin the whole thing. And if you note about it, it cheerfully congratulates you on discovering it and even more cheerfully explains why it has always known this doesn't work and can't work. If a person kept doing this to me I'd be infuriated but you can't really blame a bunch of numbers.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link