You're viewing the discuss.systems public feed.

Federated feed Local feed

Shriram Krishnamurthishriramk@mastodon.social
Sep 24, 2026, 11:40 AM
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
When you live in a high-friction world, you really, really need to get the spec as right as possible, no matter how humanly difficult that is. When that friction reduces massively, you can write specs far more incrementally.
This is not new. When we had only batch programming, we programmed in fundamentally different ways than once we got interaction, REPLs, etc. ↵
💬 1🔄 0⭐ 0

Replies

Shriram Krishnamurthishriramk@mastodon.social
Sep 24, 2026, 11:41 AM
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
To be clear: I am NOT saying that removing friction is good. It can be very bad! I grew up in the "batch" model, so I also know the upsides to thinking carefully over hacking away. I've often fantasized about adding an exponential backoff to the "Run" button in Pyret/Racket. Run too often and it says "chill, buddy, think harder". ↵
💬 1🔄 0⭐ 0
Shriram Krishnamurthishriramk@mastodon.social
Sep 24, 2026, 11:43 AM
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
Likewise, with GenAI coding, if you over-commit to code up front, you have *already* created technical debt, in the first hour of a project! But something that has gotten really good with top-end models is planning modes. I write my spec, then I have it poke at it, then we go into an extensive planning phase. I ask it to ask me all the questions it can think of; even my "good spec" can inspire 15-20 follow-ups. No code early. ↵
💬 1🔄 0⭐ 2
Shriram Krishnamurthishriramk@mastodon.social
Sep 24, 2026, 11:44 AM
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
This is a model that works especially well, and what I'm also teaching to my students. We do high-level planning, then we go over all the data structuring (eg, what tables, what indices, what cross-references, why aren't those two tables one, why isn't this table two, etc.), types in the code, intended key function signatures, etc., etc. Planning doc iteratively improved to 20-30 items. THEN you "let it cook". ↵
💬 1🔄 0⭐ 1
Shriram Krishnamurthishriramk@mastodon.social
Sep 24, 2026, 11:46 AM
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
So the same GenAI that can lead to slop code can actually lead to *really good specs*. And as a result, much higher-quality software. Certainly a combination of me, a planning document, the agent's memory, and a checklist/todo list can accomplish orders of magnitude more than I can alone, while producing much richer and maybe even (*shudder*) higher-quality software than me alone. ↵
💬 1🔄 0⭐ 0
Shriram Krishnamurthishriramk@mastodon.social
Sep 24, 2026, 11:47 AM
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
But please, let's not pretend that the average or even super-average programmer ever wrote great specs. Or, even more so, *maintained* them (one of the oldest and most persistent problems in SE). Once past textbook problems, specs are complicated, messy, contested, incomplete, inconsistent, and wrong. A good GenAI model will actually *help you find those issues*. If you have the patience to correct them, you get vastly better SE.
💬 2🔄 0⭐ 1
Dan Frumindif@mathstodon.xyz
Sep 24, 2026, 11:59 AM
@shriramk @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif interesting to hear about your experience, and it does confirm what i have seen: the main component is still located between the keyboard and the chair
💬 0🔄 0⭐ 1
Marco Devillerssprout@mathstodon.xyz
Sep 26, 2026, 7:24 PM
@shriramk @dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif I can see generative AI generating code for an underspecified spec ('I want a game'), but I am not convinced it will generate correct code for a full spec. I find it more likely that it'll hallucinate some best approximation. But I am ready to be proven otherwise.
💬 1🔄 0⭐ 0
Shriram Krishnamurthishriramk@mastodon.social
Sep 26, 2026, 7:31 PM
@sprout @dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
Come on, it's 2026, are we still doing this?
💬 1🔄 0⭐ 0
Marco Devillerssprout@mathstodon.xyz
Sep 26, 2026, 8:07 PM
@shriramk @dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif Sure we are, we need evidence. It's only 2026, and we're still in the early days of agentic AI. But I am ready to be surprised.
💬 1🔄 0⭐ 0
Shriram Krishnamurthishriramk@mastodon.social
Sep 26, 2026, 11:00 PM
@sprout
Okay, feel free to believe that.
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
💬 1🔄 0⭐ 0
Marco Devillerssprout@mathstodon.xyz
Sep 26, 2026, 11:11 PM
@shriramk @dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif Hey! I don't need your permission to believe anything? Anyway, we'll find out.
💬 1🔄 0⭐ 0
Shriram Krishnamurthishriramk@mastodon.social
Sep 26, 2026, 11:56 PM
@sprout
It's called a figure of speech. Even an LLM would understand that.
@dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif
💬 1🔄 0⭐ 0
Marco Devillerssprout@mathstodon.xyz
Sep 26, 2026, 11:57 PM
@shriramk @dif @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif I am not an LLM.
💬 1🔄 0⭐ 0
Dan Frumindif@mathstodon.xyz
Sep 28, 2026, 12:38 PM
@sprout @shriramk @sandorspruit @nicoformanek @spdegabrielle @dimitriselectif that's exactly what an LLM would say :)
💬 0🔄 0⭐ 0