Here's one exactly in this spirit:
"Why can't we just give steroids to people with muscular dystrophy?" [0]
HN Discussion: https://news.ycombinator.com/item?id=28306559
https://trevorklee.com/why-cant-we-just-give-steroids-to-peo...
113 karma · joined September 20, 2023
"Why can't we just give steroids to people with muscular dystrophy?" [0]
HN Discussion: https://news.ycombinator.com/item?id=28306559
https://trevorklee.com/why-cant-we-just-give-steroids-to-peo...
We know he's innocent, and he knows he's innocent, but how does he prove it?
> Prosecution: Mister Klayme, the criminal messages were sent from a Kik username called "fus ro dah". What's your Kik username?
> Klayme: It's "fus ro dah".
> Prosecution: It logically follows that Mister Klayme was the sender, and is therefore guilty of the offense.
Instead of each paying full price to generate a SOTA model in competition, they could share the result and split the cost. This gets even simpler if they merge.
https://www.deepsouthventures.com/i-sell-onions-on-the-inter...
https://notnotp.com/notes/what-job-interviews-taught-me-abou...
Here's a nearly-strawman-but-definitionally-valid example: a landlord may want to remove a tenant who's being unusually hard on the place and accelerating the wear-and-tear. Could be serious enough that paying the tenant to go away would be cheaper than the cost to remediate the damage accrued over the length of the contract.
If they're the only ones who ̶a̶r̶e̶ ̶w̶i̶l̶l̶i̶n̶g̶ ̶t̶o̶ ̶b̶e̶ ̶t̶h̶e̶ ̶e̶n̶g̶i̶n̶e̶ ̶f̶o̶r̶ ̶a̶u̶t̶o̶n̶o̶m̶o̶u̶s̶ ̶k̶i̶l̶l̶b̶o̶t̶s̶ can draw a reciprocation dingle-arm to reduce soinosoidal repleneration, then "I'm sure the government will buy it" [0]
Container not even needed, there's projects like Tamago [0] that let you run your golang application without even needing an OS
LLM extraction of the information from the Product Owner is becoming the way to overcome poorly-documented business context.
Non-technical folk are using things like `/grill-me` [0] to seed the LLM with the long-tail complexities that they didn't know they didn't know they needed to put out.
Trailers hint is in my global CLAUDE.md so it knows: when debugging, saying something like "didn't we already discuss this in a previous session?" it will know what to look for.
I also have a manually invoked `/search-session-transcripts` that I can use to natural-language inspect previous session by day, project, session id etc. Claude often uses this skill to narrow down on parts of the conversation that are relevant to the current query.
> How often are you using the trailer lookups?
Mondays are usually the day I need to refer to previous sessions from the week before. Trailer lookups are also good for continuing buildout of adjacent features. They've also been excellent in incident post-mortems where the PR text and commit message aren't enough to gauge the "how" of decisions that led to issues.
> Any idea how this relates to token usage?
I tested this. Session-transcripts are append-only so `/clear` and `/compact` don't clear out old messages, they stay stable and accessible. I also don't clean out my `~/.claude/sessions` ever so there's a lot in there, but the info is valuable and cheap.
It allows Claude to look back into the session where a change was made and see the decisions made, tradeoffs discussed and other history not captured by code, tests.
> This made sense when agents were unreliable. You’d never let GPT-3 decide how to decompose a project. But current models are good at planning. They break problems into subproblems naturally. They understand dependencies. They know when a task is too big for one pass.
> So why are we still hardcoding the decomposition?
Would you mind publishing the `PROJECT_MIND_MAPPING.md` file that's referenced in `MIND_MAP.md'?