garfij

I've been playing around with this recently too and started getting much better results when I told it how to produce rendered PNGs of the file and to inspect it from several angles during iteration. I'm really only just getting going with it though, so if you have any tricks to share, I'd love to hear them!

FWIW I've only ever been on the API based plan at work and we never seem to run into the majority of the problems people seem to be very vocal about. Outages still affect us, and we do have the intermittent voodoo feeling of "Claude seems stupider today", but nothing persistent.

Of course it's a stupid amount of money sometimes, but I generally feel like we get what we're paying for.

Do your markdown files have frontmatter configuration?

We use them extensively in our agent framework at work for all sort of things. You can make up whatever you want, if the tags are semantic enough it just gets it, or you can add a bit of explanation about it in the system prompt or whatever.

  - Circuit breakers when it seem like it's stuck in a loop
  - Warnings about running low on context
  - Reminders about task lists (or anything)
  - All sorts of warnings about whatever

We've done varying forms of this to differing degrees of success at work.

Dynamic, on-the-fly generation & execution is definitely fascinating to watch in a sandbox, but is far to scary (from a compliance/security/sanity perspective) without spending a lot more time on guardrails.

We do however take note of hallucinated tool calls and have had it suggest an implementation we start with and have several such tools in production now.

It's also useful to spin up any completed agents and interrogate them about what tools they might have found useful during execution (or really any number of other post-process questionnaire you can think of).

Probably less sensible than you think. How many terms would they need to do this over? How many terms would they need to do it for _at once_? How many tokens would that add to every prompt that comes in?

Let alone that dynamically modifying the base system prompt would likely break their entire caching mechanism given that caching is based on longest prefix, and I can't imagine that the model's system prompt is somehow excluded from this.

Thank you for saying this out loud. I've been losing my mind wondering where the discussion on this was. LLMs without Tool Use/Function Calling is basically a non starter for anything I want to do.

What do you find difficult about distilling your own prompts?

After any back and forth session I have reasonably good results asking something like "Given this workflow, how could I have prompted this better from the start to get the same results?"

I believe if you read carefully, it's not blocked, it's rate limited to once daily, with very clear remediation steps included in the response.

The officials each responded with “that very tired mantra: ‘But the virus is worse,’” Dr. Murphy recalled. “Yes, the virus is worse, but that doesn’t obviate doing research to make sure that there may be other options.”

We had a version of Bomberman that was written in some version of BASIC in high school (maybe QBasic?). It was great because we could hack on it to modify the game and immediately play with those modifications.

  aria-hidden=true

Other people have said it in this thread, but I think your experience is being severely clouded by Oracle. Postgres, MySql, and all have the `TEXT` datatype which are variable length (though with some upper bound)

Thanks for this, I"d been meaning to work up the energy to deal with their retention ops, but this was super easy.

For anyone else looking to do this, the trick is to choose "Other" instead of "Too expensive" or "My rate is going up" as the reason for cancelling. The later will just result in them trying to sell other standard subscription offers to you.

I feel like your perspective might be more narrow than you think it is.

I've been coding professionally for 20 years and at every job I've ever had we've made the decision to move away from ORMs or as much as possible given the constraints of our system in preference of directly writing SQL. My previous employer dumped Rail in favor of a Go backend (a language whose userbase almost entirely eschews the idea of ORMs) and my current employer never even had one to start with, choose to write SQL directly in a typescript backend.

I'm not going to pull the stats for you but this very website is FULL of articles talking about the benefits of writing your own SQL and I can't even remember the last time someone tried to pitch me a shiny new ORM.

teaching people arcane terminology distinctions like between WHERE and HAVING

This is akin to complaining about needing to teach people arcane terminology distinctions between FOR and WHILE. I think it's a crime that many CS degrees I see don't include a course in database and SQL. There are of course some arcade corners of SQL (I sometimes have to look up the different JSONB operators in postgres), but WHERE and HAVING ain't it.

flipping a coin on whether the query engine will use the index and execute in 10 ms, or decide to follow a different execution plan and take 5 minutes to run

Heavens, if you think using an ORM is going to help you here, have you got another think coming.

Your take on this is so foreign to me I was honestly shocked to see it. That being said, you probably aren't the only one, so perhaps my perspective is more narrow than I had assumed as well.

Following the example from the original comment, I would argue that if the content is otherwise unavailable for purchase or rent, then yes, it is ethical for anyone and everyone to pirate it.

Conversely it is unethical to retain the rights to shared cultural artifacts and _not_ provide a way for people to access them.

I'm papering over some grey area where if it's not available for purchase but you could get it from the library, maybe via inter-library loan, then maybe in aggregate it's better ethically to do that.

Why isn't it?

My gut reaction is that I don't agree with you, but I can't immediately put into words why. I think it's possibly that I view a "console" for gaming as a combination of a form factor and development environment and this seems to fit that bill.

I'm interested to hear the other side though.

It's like the difference between a curated collection and flipping through a card catalog.

I spent about 6 years writing Go at $dayjob, and while what you're saying is technically true, idiomatically you also generally wanted to avoid scenarios where you would _want_ to observe them independently. The standard behavior is is if `err != nil`, the result should be ignored.

Someone should Google about the .git-blame-ignore-revs file.

Not at all https://play.golang.com/p/c5tGTMamjj_a

What sort of platonic ideal project do you work on that the majority of SQL you write doesn't need dynamic WHERE clauses? You're positing a majority use case I haven't encountered in 20 years of professional and personal projects.

It is no longer the case that pizza boxes are not recyclable. Paper Mills all over the country have no problem recycling them even with grease and cheese on them. Some localities haven't updated their guidelines so please check yours and let people know.

https://www.afandpa.org/news/2021/lets-set-record-straight-p... https://www.sierraclub.org/sierra/yes-you-can-recycle-your-p...

What are some signs a résumé was created in LaTex?

A sibling comment points at https://github.com/charmbracelet/bubbletea as a Go alternative with a similar architecture

What makes "invisible to everyone but you" a more "logical" interpretation of "shadow ban" than "banned but didn't tell you"? Are shadows invisible to everyone but you?

My understanding was that Postgres fixed this back in version 12. Are there still limitations here?

I've used CTEs fairly extensively so I'm generally familiar with their pitfalls, but I don't quite grok your point here. Can you go into a little more detail about what you mean by "take on any dependency in the parent tables"?

Have _you_ heard of Primark? What about Primark even pretends to be about quality?

I'm in no way defending what Microsoft is doing here, but I would like to be able to have different clients for http:// & ftp://. Segregating client software by protocol makes perfect sense