This is pretty cool. I can see it saving users a bit of time.
Feedback - it might be worth adding an info button on what DSCR is and how your tool is calculating it (seems like a critical bit to understand to really get the value of your tool)
47 karma · joined November 7, 2019
Overall, a step in the right direction, but still early. I wrote more on this here. https://newsletter.victordibia.com/p/no-mcps-have-not-won-ye...
No, MCP's have NOT Won (Yet) https://newsletter.victordibia.com/p/no-mcps-have-not-won-ye...
In your opinion, what percentage of apps might benefit from this model where end users bring their own MCP tools to extend the capabilities of your app. What are some good examples of this - e.g., a development tool like Cursor, WindSurf likely apply, but are there others, preferable with end users?
How is the user incentivized to upskill towards finding the right tool to "bring in", installing it and then using it to solve their problem.
How do we think about about the implications of bring your own tools, knowing that unlike plugin based systems (e.g,. Chrome/extensions), MCP servers can be unconstrained in behaviour - all running within your app
Compact yet powerful: At just 5.8 billion parameters, this model can be optimized for deployment worldwide. As the official blog post mentions, it "delivers highly efficient low latency inference, all while optimizing for on-device execution and reduced computational overhead."
The initial interaction also sets the "scene" for other things, like letting the LLM know that there might be other dependencies and it should not assume behavior (common for most realistic software tasks).
An example prompt I have used (not by any means perfect) ...
> I need help refactoring some code. Please pay full attention. Think deeply and confirm with me before you make any changes. We might be working with code/libs where the API has changed so be mindful of that. If there is any file you need to inspect to get a better sense, let me know. As a rule, do not write code. Plan, reason and confirm first.
--- I refactored my db manager class, how should I refactor my tests to fit the changes?
Half the time, the LLM will make massive assumptions about your code and problem (e.g., about data types, about the behaviors of imported functions, about unnecessary optimizations, necessary optimization, etc.). Instead, prime it to be upfront about those assumptions. More importantly, spend time correcting the plan and closing gaps before any code is written.
https://newsletter.victordibia.com/p/developers-stop-asking-...
- Don't start by asking LLMs to write code directly, instead analyze and provide context
- Provide complete context upfront and verify what the LLM needs
- Ask probing questions and challenge assumptions
- Watch for subtle mistakes (outdated APIs, mixed syntax)
- Checkpoint progress to avoid context pollution
- Understand every line to maintain knowledge parity
- Invest in upfront design
[1] A guidance language for controlling large language models. https://github.com/guidance-ai/guidance
[2] Knowledge Infused Decoding https://arxiv.org/abs/2204.03084
Peacasso is a (yet another but really nice) user interface for interacting with stable diffusion models.
The current implementation of Peacasso provides a GUI for basic operations - text and image based prompting, remixing generated images as prompts (img2img), model parameter selection, image download. Also covers the little things .. like light and dark mode.
The discussion mostly looked at the novelty of transformer based multimodal models such as CLIP and DALL·E which have both shown interesting results.
TLDR
- Data is king! Getting better data might be the single biggest bang for buck in terms of performance improvement.
- Data curation toolkits, MLOps (and companies in this space) and will be increasingly important.
- Transformers are unifying the deep learning problem/solution space i.e transformer-based model architectures can be effectively applied to multiple domains e.g. image, text, speech.
- Models that can be parralelized and optimized for today's hardware will have more impact.
- New Research Frontiers? Models that learn continuously; Models capable of logic/reasoning; New objective functions and application areas; New approaches to data labeling; Model-first approach to benchmark design; New approaches to creating massive datasets (e.g. via simulations)
The talk was moderated by Russell Kaplan (Scale AI) and the panel included Richard Socher (You, Salesforce Research), Justin Johnson (University of Michigan, Facebook), Andrej Karpathy (Tesla).
The face/head errors is likely an artifact of transfer learning (handtrackjs is finetuned on the object detection model trained using the coco object detection dataset which contains a person category).
Current approach being explored to expand the training data to include faces/heads such that the model better discriminates this from hands.
There are also size and speed optimizations being explored (smaller models such as efficientdet, quantization).
The face/head errors is likely an artifact of transfer learning (handtrackjs is finetuned on the an object detection model trained using the coco object detection dataset which contains a person category).
Current approach being explored to expand the training data to include faces/heads such that the model better discriminates this from hands.
There are also size and speed optimizations being explored (smaller models such as efficientdet, quantization).