Jim Faster

Currently building

[Jim Faster @Jim_Faster]

I just launched MachinesFluent.📣
Downloads are now active. 6 months of hard work.

You speak -> it writes + reformats using prompts, which adapt to your current app.

It works with local & cloud models. You decide.

More info below -🧵👇

[Matthew Prince 🌥 @eastdakota]

Welp, that happened faster than I predicted. Thought it would be end of 2027, then early 2027, but agentic traffic growing so fast that bots have now passed human traffic online for the first time in the Internet's history. https://t.co/2zX5bHdhsa

[Jim Faster @Jim_Faster]

@pbakaus @OpenAI Ah I see. You're probably right. I updated the app, then saw a pop-up about plugins.

plugins --> product design --> audit --> mentions impeccable.

I guess codex somehow identified it as relevant to product design and grouped it with their bundle. I'm confused too.

[Jim Faster @Jim_Faster]

@thsottiaux Mobile / Desktop sync on win11. I'm still waiting.

[Jim Faster @Jim_Faster]

@Rasmic SvelteKit video maybe?
After you mentioned it I got interested and it seems overall better than Next.js for a solo dev. Less moving parts, leaner, etc. But my main concern is really, how familiar AI agents are with it.

[Jim Faster @Jim_Faster]

I had a 800 LOC file that needed a fix.
GPT-5.5 Pro Xhigh, changed almost 100 LOC to solve the problem and failed.

The answer was to replace "^" by "or"... literally a
characters fix...

Imagine the garbage that accumulates when we don't pay attention.

[Jim Faster @Jim_Faster]

MachinesFluent v1.0.6 is out.
Btw, you don't need to wait for app updates to get the latest models. They're available as soon as a provider releases them; e.g. Opus 4.8

Login directly (OAuth) with OpenAI - Minimax - Qwen.
No API keys needed for them.

https://t.co/S3lzVEQmQb

[ThePrimeagen @ThePrimeagen]

benchmarks are stupid for models

Just ignore them

[Jim Faster @Jim_Faster]

@Rasmic @cursor_ai codex got the same issue.
Even roo code extension is VS code, in contrast, used to have this revert to checkpoint feature almost perfectly functional over a year ago.

[Jim Faster @Jim_Faster]

@bridgebench Thanks for the feedback. That's what I thought. I respect Deepseek but we gotta be real with the performances. It's not even close GPT-5.5 Pro is something else.

I'd like to save money but subpar coding just makes you lose even more time.

[Jim Faster @Jim_Faster]

@ashleevance Very impressive. Thanks for the content. I can't help thinking this is inevitably going to drift into usage unrelated to disabilities...

[Jim Faster @Jim_Faster]

@OpenAIDevs am I having a bug, or did you remove the context window status metric?

Because there is literally 0 good reason to do so imho.

[Jim Faster @Jim_Faster]

@bindureddy This is spot-on, I'd say.

[Jim Faster @Jim_Faster]

@vinayjain404 @Scobleizer Looks impressive tbh

[Jim Faster @Jim_Faster]

@NapierHolland @NorthstarBrain No worries mate.

[Jim Faster @Jim_Faster]

What do you call this?

I just spent $100 and 4 days while having a bad flue, intense fever and muscle ache, just so I could gain 500 f*cking milliseconds of speed on my app, to improve UX...

I must really not have my sh*t together. Lmao.

[Jim Faster @Jim_Faster]

I don't need much to be happy. Simple things like this can make my day even though it only lasts a few minutes. Will build more tomorrow. Time to rest.

[Jim Faster @Jim_Faster]

@0xSero @AlexFinn Hopefully, it punishes grifters

[Jim Faster @Jim_Faster]

@om_patel5 The animations are really good. Not sure it's a good idea fundamentally, but implementation is cool nevertheless.