Josh Saint Jacque

Seattle-area Staff Software Engineer. I love Ruby and Rails. Interested in AI and LLM discussions.

Writing on

[Josh Saint Jacque @JoshSaintJacque]

@The_Alex As funny as that would be it appears to be from a Chinese lab.

[Juampi @juampitech]

Post got a lot of traction, so I made a rank with the anti-slop skills people need to install.

1. stop-slop - @hvpandya
https://t.co/tGzmiWKFAu

2. no-ai-slop - @petergyang
https://t.co/Gj3ctyZUfK

3. humanizer - @blader
https://t.co/6lrzaEpMfs

4. unslop - @poteto
https://t.co/u52zh9EXwa

5. slopbeth - @synopsi
https://t.co/AMCKYbFVgj

6. humanizer - @AdamBoudj
https://t.co/KaWaNAbJu8

7. deslop - @strnr
https://t.co/NtoTm2qpZY

8. anti-slop - @elithrar
https://t.co/0NXaY0FYaD

9. humanize - @aashatwt
https://t.co/NdhCs13gO8

10. anti-ai-slop-writing - @jalaal_tweets
https://t.co/g9gYshaHUj

[Josh Saint Jacque @JoshSaintJacque]

@elshayib_ I just keep rambling, even though what I’m asking for is changing as I’m talking. The models are usually pretty good at figuring out where I ended up.

[Josh Saint Jacque @JoshSaintJacque]

@sudoingX A benchmarking tool so I can actually quantify which models I like for which tasks.

[Josh Saint Jacque @JoshSaintJacque]

This has been my experience, too. It's an interesting model that might be compelling depending on pricing, but it's not at the frontier.

[John @jrysana]

Lots of talk about "Ox Alpha" on here, so I figure I should contribute some results I found.

On a (fairly tough) private benchmark (i.e. with zero chance of contamination in any model), with minimal/low reasoning, it underperforms quite a lot, even with a reasoning advantage:

[Josh Saint Jacque @JoshSaintJacque]

@aarondotdev I should say that one practice I do that seems to help is heavy AI adversarial review. I usually have ~a dozen subagents pick the work apart until it's there aren't any issues left to find.

[Josh Saint Jacque @JoshSaintJacque]

I read the code. I’d be curious to see the critical mistakes you’re finding. My experience has been that frontier models don’t make coding mistakes. The worst I see is they make assumptions based on ambiguous requirements, and that’s usually resolved with something like /grill-me up front.

[Josh Saint Jacque @JoshSaintJacque]

@PremiumGoblin @t3dotcodes Huh, no repro here it dismisses when I tap in the results area

[Meng To @MengTo]

I open-sourced ThreeUI, my library of three.js components and landing pages.

160+ are free, and the tool is free too. It includes procedural 3D hero sections, icons, and motion designs. Copy the prompt or source, give it to your agent, then change the theme, lighting, motion or layout.

Live site: https://t.co/rtCfqeZnOP

Repo: https://t.co/B66ahgxHVl

I'm adding a lot more soon. Pro comes with 50+ extra components, MCP, and skills. Early adopters get 50% off right now.

[Josh Saint Jacque @JoshSaintJacque]

Try it yourself. It's nowhere near Sol/Fable level.

[Cline @cline]

Ox Alpha (stealth model) is now free in Cline.

Early benchmarks shows marginal improvement over Fable and GPT.

Try it with:
npm i -g cline
and use /models to see it under Free options

[Josh Saint Jacque @JoshSaintJacque]

@ChrisGPT Based on my own testing I don't believe this. There's no way this model is near Fable, let alone beyond it.

[Josh Saint Jacque @JoshSaintJacque]

@agarwal @pitdesi This is a wildly different question from whether or not people support ALPR‘s like flock.

[Josh Saint Jacque @JoshSaintJacque]

I’m sorry what

[Nous Research @NousResearch]

Ox Alpha is free via Nous Portal for a limited time. We have capacity for 1 quadrillion tokens per day.

Let the tokens flow at https://t.co/4KFwhsReyA

[Josh Saint Jacque @JoshSaintJacque]

@ImLunaHey This is a brand new sentence.

[lauren @poteto]

every team needs a gardener. someone quietly watching the stream of PRs flowing into your codebase, noticing the smells: the third isRecord this week, the lint suppressions creeping like ivy across your carefully planned garden. a steady hand tending the weeds that would engulf it in slop if left unchecked.

with careful grooming it stays a garden. every weed you pull becomes a rule, so it can't grow back. without that, it's just whatever grew.

[George Mayer @GeorgeMayer]

Wife: "You picked up the kids from school, right?"

Me: "Three findings, and one of them is more serious than the question you asked."

[Thariq @trq212]

a skill people at Anthropic have been using a lot recently: ELI5

/eli5 <what you want explained>

"explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words"

[Wes Bos @wesbos]

I added a a stick shift to my computer. It's like Raycast but for truckers.

Window management, LLM Model selection, Shift up/down for reasoning levels.

It feels right

[Josh Saint Jacque @JoshSaintJacque]

This has already been the case at startups for many years.

People who have experience working in startup environments where you have to wear many hats are going to have a big advantage going forward.

[Cory House @housecor]

Roles are collapsing.

If you're a "Software Engineer" today, you may be a "Product Engineer" soon - with many more responsibilities.

So:
- Learn design/UX/QA/PM skills.
- Focus more on the user, and less on the syntax.

Image via Gartner.