Isaiah Dahl

Father of four, Head of Product & Development @praisecharts

[Isaiah Dahl @isaiahdahl]

@karrisaarinen @linear Is there a chance we end up on a place where it could run on my own hardware with sign in with ChatGPT inference?

[Isaiah Dahl @isaiahdahl]

@karrisaarinen @linear are you guys going to support Sign In With ChatGPT to power linear agent, loops etc? Would love to make use of more native linear workflow but just doesn’t make sense with the inference value in subscriptions.

[Isaiah Dahl @isaiahdahl]

@cramforce You had me until "That's a real loss."

[Isaiah Dahl @isaiahdahl]

Would Omarchs be pronounced oh·​m​archs even if you pronounce Omarchy oh·​ma·​chee?

[Isaiah Dahl @isaiahdahl]

@dhh We're in the google workspace world. Do I need to give that up to embrace hey?

[joshpuckett @joshpuckett]

In Defense of Writing.

A disturbing trend I see emerging is people lazily generating longer form content from bullet points or dictation they give to an LLM, and then passing it off as their own.

Beyond the obvious breach of trust and social expectation when doing this, there are several more nuanced but equally insidious problems with doing this.

First, writing is thinking. If you aren't taking the time to write, edit, rework, reshape, and play with your words, you're shortcutting a key aspect of refining an thought. You rob yourself of this opportunity if you just skip to the end.

I have yet to read anything generated that even comes close to the clarity and impact of a well-written piece.

Second, respect. Very few people will tell you this to your face, but as soon as they read something 'from you' that has all the tell-tale signs of AI slop, their respect (and trust) for you drops.

What you are communicating is that you don't take the time and effort to do things properly, or at least entirely honestly. This is damaging in way many don't realize. I instantly discount anything I read as soon as I recognize it as AI slop.

Third, and I think most important, you are training yourself to take the easy way out. I think this is different than 'working smart'. It's intellectual laziness, effectively choosing cheap calories rather than a nourishing meal, even if it takes longer to prepare. That effort is where good things, as well as your own growth, come from.

Many days on here I feel like the last man alive who wants to actually read what you wrote. It's entirely possible that this is a losing battle and the nature of media and medium is trending in an irreversible way. But I really hope it's not.

I'll leave you with a philosophical question: every social media platform is going to great lengths to label AI-generated images and video. Why not writing, as well?

[Isaiah Dahl @isaiahdahl]

danngerously is an absolutely brilliant GitHub username, bravo.

[Isaiah Dahl @isaiahdahl]

@joshpuckett @benspringwater I second that!

I use “My Wife” so Siri never trips up on “call/text my wife”

[Isaiah Dahl @isaiahdahl]

@karrisaarinen @linear workspace: praisecharts

[Isaiah Dahl @isaiahdahl]

Best of both worlds is separate repos but they are in a git ignored folder of a parent repo that just holds tooling. So "core" repo has apps folder gitignored and then put the sub repos in the apps folder. Then run agents out of the root repo where they have context across backend and frontend. Root agent tooling files can have instructions/skills about how to run each stack and still lets you give an agent domain to do work across both stacks.

Feel like I would always first try to have it as one monorepo, but this allows CI or branch based logic to be much more specific to each project.

[Isaiah Dahl @isaiahdahl]

@badlogicgames can pi config be edited while in a chat? I also ended up creating my own 'roster' extension where I could call /roster, it's basically parity with pi config (with some extrta stuff I don't really need like being able to quick view and edit etc).

Mostly I don't like having to close pi and then write pi config, make my changes, and then esc, pi, and /resume to pick up where I left off.

Am I missing a short key or something?

[Isaiah Dahl @isaiahdahl]

Why not? Sounds like you’ve tried using skills and haven’t found them worth using… but what are those reasons.

I use voice transcribing for 98% of my prompting and find it easier to speak out my prompt and say use the “blank” skill somewhere in my prompt ramble.

Genuinely curious about your thoughts behind this.

[Isaiah Dahl @isaiahdahl]

@karrisaarinen @linear Great to hear. Would love to start using linear docs for more than project specs. Always seemed odd there was no top level place to keep docs. Would love to have a place for org docs as well!

[Isaiah Dahl @isaiahdahl]

@mattpocockuk /research-with-questions

[Isaiah Dahl @isaiahdahl]

@theo curious how you came to the conclusion it was worth it to license Proximavara for https://t.co/43i9F8R6qH

[Isaiah Dahl @isaiahdahl]

@namyakhann @claudeai @ChatGPTapp Design

[Isaiah Dahl @isaiahdahl]

What a turn around! Signed out just to try it. Works! Thank you!

[Isaiah Dahl @isaiahdahl]

Hey @joshpuckett just reading uncommon care and wanted to point something out. Every time I sign in (I bounce around a few devices) I have to go through the whole create your library card on-boarding experience. It was cool the first time, now it’s annoying.

Loving the content so far though!