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.
Kalvium | SDE2/Sr. Software Engineer | Bangalore, India (HYBRID)
If you have a CS degree from India, you know the problem: our education system is outdated. We've fixed it. Kalvium is the B.Tech CS degree you always wanted, leveraging GenAI to power a self-directed curriculum. We run in 22+ universities. We've built our company in a bootstrapped, "default alive" way.
Our engineering team is a core group of about 15. We're looking for someone to distill and implement insights from the finest pedagogy experts.
You'll thrive here if you are a high-ownership individual ready to grow at full speed, value learning above other factors, and want the fastest path to growth (We have a two-quarter promotion policy), you are fully committed to transforming higher education (missionary, not mercenary).
Work Mode: Hybrid - Bangalore. 9 AM to 6 PM, 6 days a week. Product/engineering is in the office Wednesdays and Saturdays.
Pay: SDE2: ₹14L (Base + bonus), Sr-Lead: ₹19L-30L (Base + bonus), ESOPs based on interview and experience.
Experience: SDE2/3/4: 1.5–5 years (launched and maintained 1 product end to end), SDE3: 3+ years (launched/maintained multiple products). Beyond these - reach out anyway, and we can see if any other role fits. Lead: 4+, currently a successful IC, and you aspire to take on engineering management duties.
We run one in India (kalvium.com). The key differentiation is to being real world work for students for upto 6 semesters, leading to extended hands on learning.
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.
reply