FindLogan
281 posts

FindLogan
@FindLogan
SWE who won't shut up about AI agents. Follow along to learn more about AI👇
United States Katılım Ağustos 2020
36 Takip Edilen48 Takipçiler
Sabitlenmiş Tweet

@intheworldofai This is insane that a flash model from Google is getting thinking-level quality of outputs from just around a year ago.
I would be interested in seeing how this affects game dev with the latest models of Gemini.
English

🚨 BREAKING: A brand new Gemini Flash (3.1 or 3.5?) model has just been spotted on LM Arena.
Looks like Google might be preparing another major Gemini update. Should be dropped at Google I/O!
can@marmaduke091
🚨 Google updated Gemini 3 Flash in arena It still has the same name "Gemini 3 Flash". However, output quality is two tiers above it. It could be 3.1, 3.2 or 3.5 Flash. Not sure what they'll call it. It's performance is closer to current 3.1 Pro than the current 3 Flash. Huge upgrade.
English

@thsottiaux Codex has received so many updates I am not sure if I can even keep up without stalking X like a guy checking in on his ex.
English

Say hello to my new pet
OpenAI Developers@OpenAIDevs
Pets. Now in Codex. Use /pet to wake your pet.
English

OpenAI never has degraded a model over time. (Or at least, I haven't seen them do it). Now... they DID introduce Goblins... but c'mon - that's a feature.
Can't say the same about Claude.... but it's good that OpenAI has some competition - makes it so that OpenAI is expected to come out with newer and drastically improved models instead of just small improvements for the sake of profit.
English

In case your GPT-5.5 adventures feel alone.. you can now setup pets inside Codex.
This is a interesting twist.. didnt Claude have a feature similar before they did ?
OpenAI Developers@OpenAIDevs
Pets. Now in Codex. Use /pet to wake your pet.
English

To create your own pet, install the hatch-pet skill:
Morgan Germani@MorganGermani
@OpenAIDevs We don't have a /hatch command yet :(
English


It's so hard to describe the vibe difference between Opus 4.7 and GPT 5.5 (for coding)
GPT is smarter and can unblock you, but it gets stuck in stupid ways and strangles itself with context sometimes.
Opus will go down the most insane paths and refuse to acknowledge obvious answers, but it understands intent better and has more taste.
Whenever I use one for more than an hour, I always reach to the other to "clean up".
Best part? All of this changes every few weeks 🙃
English

@FindLogan @ajambrosino They've clearly state that it will be one consolidate model going forward with no separate codex
English

@icanvardar GitHub is failing at basic functionality. I blame them for trying to be more.
But most people will probably blame AI on when github messes up their PRs.
English








