Jorge Colon (@JorgeConsulting) header
Jorge Colon (@JorgeConsulting) profile picture

Consultant with over 20 years of experience. šŸ¤–AI assisted development, programming,šŸ“ˆ self-improvement, and 🧠mindset. Available for projects. DMs open.

Orlando, FL
Joined May 2009
Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)Photo by Jorge Colon (@JorgeConsulting)
Starting the day at the gym for another productive day. Yesterday client was happy with AI Coding tutoring on Claude Code w/ the BMAD Method and Cursor. Liking it so much he’s booking 3rd session. If you have more money than time and want a tutoring session, book a session or connect with me to see if it’s a good fit for you. calendly.com/jorgecolonconsu…
5
31
1,929
YC-backed founder @Road_Kill11 has been working hard on this one. Check it out!
AI has outgrown the way we typically use it. Your agents are ready to take on far more. They just need something built for the scale of your ambition. Introducing Dexto, a multi-agent harness for AI-native teams. More in the thread below.
1
48
Jorge Colon retweeted
After Google acquired my AR startup, I started thinking about the next interface, this time for AI. Text and voice work fine, just like DOS did before the Mac. But nothing’s more intuitive than face to face. After two years of research, today we’re launching Atmee v2: a real-time avatar model that makes live video agents feel truly life-like. • Any character from 1 image + 10s of audio • Contextual expressions, gestures, even interacting with the environment • Live video calls, voice only, or video generation At its core, Atmee v2 is a video foundation model, it can render anything, but it’s built to excel at characters, which is what video models like Seedance 2.5 and Wan 3.0 are mostly used for. In comparison: Atmee v2 • Up to 50x faster • 10-100x cheaper Build tutors, sales coaches, support agents, companions, game characters, even whole living worlds. The interface after text and voice starts today.
508
815
368
14,874
3,619,436
now I can use ChatGPT Images 2.6 to send AI slop GIFs to my wife
šŸ¤– Made with AI
1
308
😱😱😱
ChatGPT Images 2.6 sets the scene. Tesseract brings it to life. Generate your visuals with Images 2.6, then make them move with Tesseract, from animating an SVG to turning a storyboard into a finished video. Direct the animation, effects, and sound through your agent, all in one editable project.
57
Highest reasoning for each task is often overkill. Here I show the pros and cons of different Gemini models to analyze videos.
1
1
395
Jorge Colon retweeted
If your company needs software dev help, I’d love to talk to you! I have some amazing experienced US-based devs on the bench who are very good at using agents and have a high quality bar. We are best at mobile and web and desktop apps, but can do much more than that. Average experience level is 15 years. You’ll love working with them. Great people, excellent devs. Appreciate retweets and any referrals!
3
45
1
139
6,499
These past few days I’ve been vibe coding an AI fact checker to understand what would be involved. I thought I’d use Jev to get better results. Got Opus 5.5 to build me something, do the evals, and improve on those. On the surface it looked good, but…
2
61
It does best when you curate the state AND the questions made against that state. Which if those questions needs to be dynamic based on the state then you practically lost the speed advantage. You have to call an LLM with the state and then generate the tailored questions.
1
7
Then send those questions back to Jev. At that point I question if the added layer of Jev was even worth it. Exploring if there’s still a way for me to take advantage of Jev to make the fact checker give higher quality judgements. I believe there is.
7
Jorge Colon retweeted
Guided Remove Background by @bria_ai_ is now live on fal: - Uses natural-language prompts to define what stays in an image - Removes the remaining content with true alpha transparency - Preserves original pixels without redrawing or regeneration
5
10
2
90
7,606
This is huge for those of us that want to create prototypes to understand Anthropic’s platform even better! It includes the Claude API, Claude Managed Agents + the Claude Agent SDK like before!
Replying to @ClaudeDevs
We’re rolling out monthly Claude Platform API credits for Max and Team plans: Max 5x: $100 Max 20x: $200 Team: up to $500, pooled Works on any model, including Haiku 5.5, in your code or third-party harnesses. How it works and full terms: support.claude.com/en/articl…
1
117
GrokBot + Tesseract + a couple of prompts Not award winning just yet. I’m sure with more iterations there could be a huge improvement. The interesting part of this workflow is creating videos while on-the-run or creating a fleet of agents that creates videos. @higgsfield_ai
75
I had GPT 6.1 Sol create a Langgraph AI video agent and to my surprise it tested a very specific video. Can’t believe I got rickrolled by Sol 6.1 šŸ˜‚.
2
2
128
This is a new step in AI Video Gen. @ltx_io I didn’t seem to see a way to specify in a prompt what specifically to isolate? If not, I think that could be an improvement to what it offers.
The last drop of VFX Week: Alpha Gen (Beta). Give it an ordinary RGB clip and get back an alpha matte that matches your plate frame for frame. No green screen, no masks, no prompt. Built for the edges that are hard to key or roto: hair, fur, smoke, fire, glass, water. 🧵
73
Dude. You’re a genius. Created an MCP used as an intake form and embedding yourself into someone’s workflow. Very very creative problem solving. Bravo!!
less than 24 hours after launch and already at capacity for the week. i will update the credit system to allow "fast" and regular speed so i can take on more interfaces.
53
You can get great results depending on the use case. The thing is that you need a golden data set where you know for sure a classification is good or not. If you blindly accept high confidence values as correctness you’re gonna be let down. But if you have a golden data set you can optimize the instructions and criteria to get you much better results.
This is what I tried to understand, too. Because you can get a JSON response from all the big classification models, it's an easy task. Jev is 100x faster / cheaper. But nobody is talking about the quality. I don't write a single line of AI in my tweets, yet all those Jev classifiers tagged them as AI. We need someone to compare smart models' (Fable / Astra) classification with Jev. I am sure Jev is great for dumb classification, but maybe even a simple machine learning model can be good.
47
ā€œAmong some other thingsā€ šŸ‘€šŸ‘€
Ladies and gentlemen... start... your... ENGINES. We are almost Tuesday and I promised a reset for Tuesday. Among some other things. See you soon.
51
I’ve been hacking away and comparing Jev to classifiers and I by no means am a machine learning expert yet. Through my experiments though I’ve realized that if you don’t have a curated eval data set to check how Jev behaves against, it’s hard to truly know if it’s working in the majority of the cases. High confidence scores ≠ correctness. It’s also hard to optimize because there’s no goal post to compare against. There’s also a lot of moving levers such as the specific state you give it as input, the instructions you give it on what to look for and the different questions you ask it. A small change in the instructions and criteria and the probabilities and confidence scores change. Typical in prompt engineering. So just record test cases, curate them and then run Jev against those. Even TypeSafe’s docs recommend doing that. It’s how you find out what thresholds you should be using based on your data. In all I am excited about this new primitive in AI engineering.
2
74