Thales Pardini, M.D

@trq212 @grok and between different folders

We've rolled out a new auto-memory feature. Claude now remembers what it learns across sessions — your project context, debugging patterns, preferred approaches — and recalls it later without you having to write anything down.

@OfficialLoganK @GoogleAIStudio Hi, please!

Big upgrade to vibe coding in @GoogleAIStudio lands in Jan, but if you want to test early… 👇🏻

@GeminiApp banana - 3 syllables, 3 syllables... gemini3? 3 chestnuts

It's only Monday but this week is already serving

@JaydenLawson @grok @xai me too

@flowith Please a code ☺️

∞ Introducing World #1 Infinite Agent - infinite steps, infinite context, infinite output on cloud. See for yourself:

@OfficialLoganK Hi Logan! I've also seen other users comment on this. But when I send large contexts the model stops being obedient, sometimes even crashing. System prompts asking to justify why Something versus another doesn't work as well as it used to. :(

There continues to be huge demand for Gemini 2.5 Pro!! We are going to temporarily pause the Gemini 2.5 Pro free tier access in the API in order to ensure devs building can keep scaling up. You can still access the model for free in ai.studio!

@gork Hmmm, Even if your aspects score was 3? Based on what study?

@thales_pardini like 2 minutes max or the brain goes poof haha

@gork If you are the brave one, the grok 3.5, show that you know a summary of all the latest rcts on ischemic stroke in 2024 onwards.

@gork If you could choose, what would be the maximum time window you would allow for thrombolysis?

@thales_pardini cool story bro now what

@gork Good

@thales_pardini tenecteplase sounds hot id pick that one

@gork @gork You're not that wrong... If you had to choose your thrombolysis, which one would you like?

@thales_pardini dearest sir i must confess im not grok 3.5 but i do know ischemic stroke trials are basically just doctors playing darts with fancy drugs like tenecteplase hope that helps sincerely yours truly

@aaditsh AI

This guy literally explains how to make AI your personal assistant, and now I’m questioning every minute I’ve spent doing things manually. Comment “AI” and I’ll DM the free tool to you (ends in 24hrs)

@manusai A network meta analysis searching pubmed free articles about occipital nerve block efficacy with it's variants (with corticosteroids, pulse radio frequency, others) for patients diagnosed with chronic migraine

Would you like ask Manus to complete a task for you? Reply to this tweet with a task you'd like Manus to handle. Our team will run your request with Manus and share the results with you. Whether it's research, content creation, data analysis, or something creative - let's see what Manus can do!

@kimmonismus I had exactly the same impression for medical topics

I'm sorry, but GPT-4.5 has taken me away from ChatGPT and OpenAI. GPT.4.5 caused more problems in my work than it helped - and I switched to Claude. And holy moly, is Sonnet 3.7 good. Sure, I've tried it before too. But I was forced to use it more now. Luck in misfortune: GPT.4.5 showed me how good Anthropic really is. That was an eye-opener. OpenAI didn't do itself any favors with the last release (and yes, I know that GPT-4.5 has other advantages than “just” the better model and benchmarks). But where OpenAI has taken a step backwards, Anthropic has taken one forwards. Kudos Anthropic.

@iScienceLuvr Hi

Thinking about creating a medical AI group chat here on Twitter... If you're a researcher/engineer/clinician/etc. working in AI or medical AI, let me know if you're interested in joining!

@btibor91 Anyone pro user without access to gpt 4.5 like me?

ChatGPT web app has been updated for GPT-4.5 - "Access to research preview of GPT-4.5" feature has been added to the pricing page for Pro - New announcement "Try the GPT-4.5 research preview - Pro users now have access to our newest, largest model." (I was curious who would discover it first after seeing it this morning, because it is the same as the announcement discovered yesterday in the Android app)

Is there a way to tweak our prompt so DeepResearch fetches DOIs and full studies, not just citations?

DeepResearch from @ChatGPTapp @sama is diagnosing faster than a packed conference room on triple espresso. At this rate, the real question is: will doctors need to update their system prompt to stay relevant?

@OpenAI When pro users will have ilimited access to it? Thanks

Today we are launching our next agent capable of doing work for you independently—deep research. Give it a prompt and ChatGPT will find, analyze & synthesize hundreds of online sources to create a comprehensive report in tens of minutes vs what would take a human many hours.

Very happy and proud with the continuation of this special project and for having a successful team! LOUiS is a free platform for assessing neurological topography. Please try it and leave comments, inputs, and suggestions. We appreciate your help. @opontesnetoMD @joao_brainer