"I am still willing to admit I am wrong. That I'm not holding the GPS properly. That navigating with real-time satellite data is its own skill and I have not spent enough time with it. I have changed how I get around before, and I'm sure I will do so again.
Map-reading evangelists, are you willing to admit that you just might not be that good at driving a car? Maybe you once were. Maybe you never were."
Great exercize, but for most use cases - people will continue reaching for jsPDF.
I think if you have a markdown->PDF function included, where I can send in markdown and get PDF, that would solve quite many needs, and would be useful.
What you like is for yourself. What you seem to dislike are things that improve others (team/stakeholders). Seniors are such because they take on more of the latter.
This will now become even more normalized given that on technical skills seniors are no longer needed for juniors to skill up. AI and the evolving ecosystem will help and assist them way more. In the new world, the more technical and non-technical work you do towards customers/teams/organization, the more senior you become. I see many not liking it, but I'm also seeing first hand that is how it is.
I feel you. Infact, IMO, SWE1 level coding industry seems to be a couple years lagging on this aspect.
The trouble is that learning fundamentals now is a large trough to go past, just the way grade 3-10 children learn their math fundamentals despite there being calculators. It's no longer "easy mode" in creative careers.
We've done some transcription exercises. The way to get the timestamps to line is :
1) break up the audio into minutes, and pass it in, one after another, so the chat completions prompt looks like:
Here's minute 1 of audio
[ffmpeg 1st minute cut out.wav]
Here's minute 2 of audio
[ffmpeg 2nd minute cut out.wav]
Here's minute 3 of audio
[ffmpeg 3rd minute cut out.wav]
and so on..
The cutting step is simple, and token count is pretty much the same, but the crucial additional detail allows for excellent transcription fidelity time wise.
We've also experimented passing in regular TTS (non-llm) transcript for reference, which again helps the LLM do better.
It's a mixture-of-experts model. Basically N smaller model pieces put together, and when inference occurs, only 1 is active at a time. Each model piece would be tuned/good in one area.
Same terms - gentlemen's agreement. The loser owes the winner a meal whenever they meet :). For a HN visitor to blore, I'll happy to host a meal anyway :)
Yeah, it's not quite there yet, but think of this as Stable Diffusion 1, or DALL-E 1/2. It's hard to imagine this not being a part of the VFX workflow within 5 years.
reply