mudasobwa

mudasobwa

Harness, not model is what matters most

Somewhere, right now, a senior engineer is on the verge of a nervous breakdown because his company will not let him switch from Claude to GPT-5.2, or from GPT to Gemini, or from any of them to a locally-hosted llama that smells faintly of the intern’s vape juice. He is convinced that the model is the product, that the difference between shipping and slop is measured in the number of parameters, and that if only management would approve the more expensive API key, all his problems would evaporate like a hallucinated citation.

He is wrong. Spectacularly, expensively, and in a way that will cost him exactly the difference between the two API tiers he is agonising over.

Allow me to explain, in the manner of a man who has spent the last year building the thing he is about to tell you matters more than the model itself.

Important notice: my blog has been moved to https://blog.yokerhood.com for good.

Most Liked

mira_tokarev

mira_tokarev

I agree that the harness is where a lot of the practical economics lives, but I’d separate orchestration from one quieter cost: how much already-seen state gets serialized into every next call. A model swap can hide that variable, whereas a deterministic local compression step gives the harness a reproducible place to measure it before adding routing or memory complexity. One small tool I’ve been evaluating is Contextpress (GitHub - Taha-azizi/contextpress: Deterministic context compression for LLM chat, RAG, and agent pipelines · GitHub · contextpress · PyPI); it operates locally on the message list rather than making a second model call. I’d compare harnesses on cost per successful task, retries, and time-to-result, because “more capable model” and “less repeated context” are different levers.

smithjj

smithjj

The framing is a bit dramatic but the point lands. The harness, context handling, and how you structure prompts usually matters more than which model you’re calling.

Where Next?

Popular Backend topics Top

Scorpil
I dabbled in Phoenix for a while now, but never really got my hands dirty with it right up until now. Apart from the whole framework bein...
New
First poster: bot
Part 1: Introduction to Postgrest. In Codd, we trust In the field of Computer Science and Engineering, few things come close to the dura...
New
AstonJ
Just finished doing a clean install of macOS (which I highly recommend btw!) and have updated my macOS Ruby & Elixir/Erlang dev env s...
New
First poster: bot
I discovered Elixir and Go at about the same time (2019). I had pivoted almost eight years of working as a Java developer, and part of me...
New
First poster: bot
I’ve been more serious about learning Rust recently, after dragging on with passive learning for a while. My first real programming langu...
New
brainlid
We take a deeper dive with Nathan Long into IOLists in Elixir. We cover what they are, how they work, the power they have when concatenat...
New
wolf4earth
Louis Pilfold is the creator of the Gleam programming language. He explains what Gleam is and tells us where it came from. He then dives...
New
chikega
Mark Hoffman, the author of Programming WebAssembly in Rust, is a pretty hilarious lecturer if you like a dry sense of humor.
New
GoulvenClech
Hi everyone :wave: I’m excited to share an article detailing how we have reorganized our Elixir/Phoenix project’s directory structure. W...
New
brainlid
Episode 264 of Thinking Elixir. News includes Phoenix v1.8 shipping with an AGENTS markdown file for new apps to enhance coding agent exp...
New

Other popular topics Top

PragmaticBookshelf
Andy and Dave wrote this influential, classic book to help their clients create better software and rediscover the joy of coding. Almost ...
New
PragmaticBookshelf
Ruby, Io, Prolog, Scala, Erlang, Clojure, Haskell. With Seven Languages in Seven Weeks, by Bruce A. Tate, you’ll go beyond the syntax—and...
New
AstonJ
There’s a whole world of custom keycaps out there that I didn’t know existed! Check out all of our Keycaps threads here: https://forum....
New
PragmaticBookshelf
Rust is an exciting new programming language combining the power of C with memory safety, fearless concurrency, and productivity boosters...
New
AstonJ
I ended up cancelling my Moonlander order as I think it’s just going to be a bit too bulky for me. I think the Planck and the Preonic (o...
New
PragmaticBookshelf
Tailwind CSS is an exciting new CSS framework that allows you to design your site by composing simple utility classes to create complex e...
New
AstonJ
Continuing the discussion from Thinking about learning Crystal, let’s discuss - I was wondering which languages don’t GC - maybe we can c...
New
New
PragmaticBookshelf
Programming Ruby is the most complete book on Ruby, covering both the language itself and the standard library as well as commonly used t...
New
PragmaticBookshelf
Build modern server-driven web applications using htmx. Whatever programming language you use, you’ll write less (and cleaner) code. ...
New