I guess I will break the general hypocrisy and be the one to say this can be replicated with AI. Fable almost one-shotted it.
The devil is in the details. I ended up tinkering quite a bit because Samsung's software decides for you wether to use the real 3x camera or do a digital zoom (which defeats the purpose). Long story short I got a prototype working, but only when shooting outdoor with good day light. No I will not share it or publish it. The result was terrible for a close up portrait. It works beautifully for outdoor shots of plants/trees.
Here is the catch : when you share your detailed shot by WhatsApp (for example), it gets compressed and you lose those precious details.
Would you mind giving more insight into how you make the videos (sourcing clips or generating them for Remotion videos, agentic?, and how you handle rendering issues and QA for the Manim videos) and costs?
Both workflows follow the same broad pattern. First, break the video into a set of scenes, then plan the scene, write the code, render it, and iteratively refine the result.
For Remotion, the AI determines what resources the scene will need, whether that be images, generated assets, or prebuilt visual components. This part doesn't happen in Manim because its more for math based visualizations.
Re costs, both workflows have a series of presets that make the implementation less expensive and more consistent. The reduction in price for the Terra model series has been particularly helpful for us.
2. Sometimes I split a Git repo into two, and I want to preserve the commit history (authors and dates) on the files that end up in the new repo - effectively replay the history of just one folder from the original to help create the new one.
3. I occasionally mess up cleaning up and merging a PR from an open source contributor such that the work is incorrectly credited to me. I'll fix the commit so that it credits the right person.
Yes, for instance it could be useful if someone’s been accidentally committing with a bogus email address. Or if you’re cleaning up some sort of mess and would like to recreate an accurate history.
Obviously as with any “force push” situation, the usual caveats apply if this is on a branch others have checked out, but if the mess is big enough, it is sometimes worth it to send everyone a script to reset or just to have people delete and re-check-out.
Yes. Absolutely! Many times I had a wrong configured terminal and messed up the author. Often I work in different projects, privately and in my work, and I use different authors for both
- An agent messed with my git config for some reason so I had to go back and fix the commit authorship
- I created a PR mostly based on work that someone else did, so I reauthored most of the commits to be in their name
Very rarely. But it can come up if you archive change history in git for things that aren't originally tracked in git.
Take laws for example. Legalize[1] is a project that documents all laws into a git structure where each distinct change is a commit with the proper timestamp of tha change. Sure, this specific project builds that entire git history once and it's unlikely a retroactive change required such edits. But do something like this for historical sources where information is still coming in, and you might need to change a date when new findings occur.
The few times I've wanted to completely rearrange a repo, It's been enough just make a backup branch and then dump the log from there and pull what I want.
I have script somewhere I think it's called git-cherry-replace, which soft resets a commit id and copies the commit message and optionally populates GIT_COMMITTER_DATE and whatnot.
What I described is probably simple enough that an LLM can implement it.
But unless you're trying to retroactively reconstruct something to preserve the exact meaning, you should consider whether a rebase even makes sense.
This proves that OpenAI models reason in grug speak to save tokens! I wonder if open models are going to start doing that too to save on reasoning tokens.
In the BlackHat presentation on the HuggingFace incident, OpenAI showed some excerpts from the reasoning traces, and they had that grug speak too (skipped articles, etc.). So the OP's method must have indeed found the actual reasoning traces.
> I wonder if open models are going to start doing that too
Yes, some of them do do that. For example Moonshot tried to reward shorter reasoning traces in between Kimi-K2.6 and Kimi-K2.7 Code, and the latter has a mild caveman accent in its reasoning traces that the former lacks.
Qwen3.8-Max also has terse reasoning, but I don't remember this being the case for Qwen3.6 models I ran locally.
It's an amazing tool, but I wish it were open source.