This is a really cool idea. So much context is lost within agent conversations these days, and it requires far too much discipline to have the conversation between you and your agent in a shared place like GitHub (plus, thee conversation isn't always just a comment and response - it's... an actual conversation).
I'm very glad to see folks innovating in this space.
congrats! the paper that is published alongside this (Cordis) is super interesting. has anyone on the team given a talk or published a talk about this? would love to hear the authors break this down
While this is true, there is also a layer in the harness between the output of _any_ tool output (eg stdout or hand-rolled tools) and the LLM. A tool could read the file but then the agentic harness could redact the output before returning it back to the llm if any of the contents matched the file contents. We do something similar in Plotly Studio where we check the entropy of strings in the user input and flag & redact any high entropy strings to the user as “potential credentials” thay the user might have inadvertently copied and pasted into the prompt before sending to the llm.
There are ways around this - the llm can always be clever by invoking tools to read the file contents in a different way than the direct file contents - but this is all to say that the agentic harness layer _does_ allow for deterministic logic in between tool output and the LLM requests.
This is really cool. And timely! Check out the recent paper by Google et al re "Societies of Thought": https://arxiv.org/html/2601.10825v1. It goes into how different conversational behaviors (raising questions or just say "but wait..."), perspective shifts, conflict of perspectives, tension, tension release (jokes!), asking for opinions) and different personalities (planner, expert, verifier, pragmatist) is both a sign of and can result in much higher performance reasoning.
So I'd be curious to see if encouraging certain conversational behaviors might actually improve the reasoning and maybe even drive towards consensus.
The issue goes beyond access and into whether or not the data is "trusted" as the malicious prompts are embedded within the data. And for many situations its hard to completely trust or verify the input data. Think [Little Bobby Tables](https://xkcd.com/327/)
I think the designers are coming from the CMYK world of newspaper printing and such, where, due to alignment issues, text must be printed using a separate black ink ("K" black) even though it could theoretically be produced by mixing Cyan/Magenta/Yellow. This is due to the difficulty of perfectly aligning three different color plates, as well as imperfections in the ink.
In printed photographs, on the other hand, all four inks can be mixed to produce a darker black than is seen in the surrounding text ("rich" black). Thus, in newspapers, the contrast ends up being higher in photos than in text.
But this is due to limitations of paper printing technology--none of this applies to computer displays, where R/G/B components are always perfectly aligned.
Even in digital media, you might want a 10000:1 contrast in photos, videos and games, but you only want 10:1 in text.
It's not reasonable to constantly change your monitor's settings, especially when you want to display both in the same document.
With HDR content, this is already possible, full brightness in an HDR video will be far brighter than #ffffff in css.
But even for regular media, this is an issue, which is why you should configure your screen for the maximum possible contrast and then reduce contrast of text in software.
If you set text to maximum contrast, you need to reduce contrast in your monitor settings, which then also affects photos (which you obviously don't want).
> Decreasing dynamic range, increasing the contrast, is trivial.
How would I do this on MacOS or Windows?
Most people have one adjustment easily available--the screen brightness setting. This setting can decrease the contrast of pure black/white text, but it cannot increase the contrast of off-black/white text. Same with the Night Light setting on Windows 11.
Ideally you'd create a proper icc profile for your monitor. The ideal way is to use a calibration device, but both OS have a wizard where you can manually adjust contrast and brightness and generate a profile out of that.
This can be used to both increase or decrease contrast.
Plotly's 3D viz is built with WebGL & SVG, using libraries like regl & stack.gl. SVG is used for axes & text and WebGL for the high performance rendering of points and surfaces. Surfaces, lines, points, and subplots are all supported. See https://plotly.com/python/#3d-charts.
For more complex 3D objects, Dash users can use dash-vtk. This includes things like point clouds, CFD simulations, 3D mesh, or 3D images.
Hello HN! Nice to see this up here. Chris here, cofounder of Plotly.
Falcon is open source and works without an internet connection or a Plotly Chart Studio account. Falcon wires together our graphing library plotly.js (https://github.com/plotly/plotly.js/), the plotly.js chart editor (https://github.com/plotly/react-chart-editor), Electron, and some open source NPM packages for connecting to databases.
Just FYI - As a company (Plotly), we're spending most of our development effort these days on Dash Open Source (https://github.com/plotly/dash) and Dash Enterprise (https://plotly.com/dash). Truth be told, we found that most companies we worked with preferred to own the analytical backend. We also heard many stories of organizations running into roadblocks with off-the-shelf SQL or BI tools (Falcon included!). Our approach with Dash is to provide the visualization and application primitives so that you could build your own tailor-made dashboards, analytical apps, or yes, even SQL editors.
Any reason the Github page advertises Windows and Mac but not Linux? I saw that its built in Javascript and checked the releases page,you guys built a Linux version too. Is it just something that, while possible, you don't want to support officially with more than a build?
Hi, just wanted to thank you for pivottable.js which I'm using since 6 years ago. I discovered today you're at plotly, I started using dash this year :)
I actually like plotly.js, it seems to be one of the only good alternatives to R‘s Shiny library. Still, I prefer to keep JavaScript libraries inside a web browser.
I'm very glad to see folks innovating in this space.