Pallav Agarwal
@pallavmac
Followers
3K
Following
3K
Media
777
Statuses
3K
SWE in NYC | iOS and Web AI founder. Developer of: Pal Chat: https://t.co/MHhyXhJ02F Custom Wordle: https://t.co/azhjtEQ9mw All views are my own
New York, USA
Joined November 2014
Pal Chat remains the only way to interact with so many LLMs from one place using your own API Key. It’s also completely free and has absolutely no ads or usage tracking. Please share the app if you find it useful 🙏 App Store Link 👇 https://t.co/R7tnf1xoqG
19
11
90
Google cooked again with their latest release 🤯. Here's Gemini 3 Flash recreating the Android UI. It was very fast and it's going to be a great vibe coding model for quick iterations
10
17
324
Claude code nerfed proof?
3/3: Claude’s SlashCommand tool is removed. “/commit” and “/review-pr 123” are now treated as Skill invocations. Skill calls can include optional args, and Claude is explicitly told that “/…” syntax refers to skills. Diff: https://t.co/730b9jAIiJ
0
0
0
Claude Max has easily been the best purchase i've ever made. It's never been more exciting to have a problem
1
0
3
I made a very fast, minimalistic, and functional mermaid diagram editor Try out out here 👉 https://t.co/fvIejzRc2Y
0
0
4
Submitted my ChatGPT app 🚀! Lets you view mermaid diagrams inline in ChatGPT. Got any other ideas for me? https://t.co/8gr4m5uMsB
📣Calling all app developers! Starting today, you can submit your ChatGPT app for review. Approved apps will be listed in the app directory, a new surface for users to search for apps directly in ChatGPT.
1
0
1
Here are my Opus 4.5 thoughts after ~2 weeks of use. First some general thoughts, then some practical stuff. --- THE BIG PICTURE --- THE UNLOCK FOR AGENTS It's clear to anyone who's used Opus 4.5 that AI progress isn't slowing down. I'm surprised more people aren't treating
158
260
3K
ChatGPT Apps are now live! You can browse and install new ones using the Apps section in the sidebar
1
1
4
Google cooked again with their latest release 🤯. Here's Gemini 3 Flash recreating the Android UI. It was very fast and it's going to be a great vibe coding model for quick iterations
10
17
324
In @GeminiApp this is what you're working with now: Fast = 3 Flash Thinking = 3 Flash (with thinking) Pro = 3 Pro (with thinking) Our best line-up yet!
171
240
3K
Make the following image as high detailed and photorealistic as possible: Highly detailed close-up portrait of a person’s face, looking upward with awe. Emphasize the eye, sharp and reflective, filled with ambient light. The lighting is ethereal and cinematic, featuring soft,
0
0
0
New image model cooks. ChatGPT Image v1.5 (left) vs. NanoBanana Pro (right). Prompt in 🧵
2
0
2
Same prompt on ChatGPT images V2
1
1
3
Just submitted MysteryBench to the Vercel hackathon. It's an Akinator style game/benchmark that measures how well an LLM can play 20-questions. Built together with @rodasjateno. View the current leaderboard 👇
Just over 36 more hours to go 🥊 Win up to $1000 in AI Gateway credits and bragging rights. https://t.co/GYVI8HhBE3
0
0
3
I don't think the world is ready for is Anthropic ever released Claude 4.5 Opus with a 1 million context window
1
0
3
.@OpenAI finally liked one of my tweets and it’s a photo of garlic… 🧄 Still getting it framed though
0
0
4