I wonder if anyone from HN would be willing to input their opinion into some features I'm building, which is really outputting LLM generated writing.
It's basically automating release notes and sprint summary's from existing systems like Jira and Linear. The target user is a product team, the target reader are business stakeholders who want to validate your existence. I've found this process to be stupidly time consuming for both our delivery manager, and whichever Dev they decide to tap on the shoulder to help contextualize tickets.
I feel like LLM's are a really good _summarizer_ and it can easily highlight if your tickets don't have enough context for actual people, if even an LLM can't write a summary with good enough context.
Idk, maybe it's a sensible usecase because you REALLY don't want novel ideas from the LLM in this case. You want it to tell you 1:1 what you did this sprint based on a list of issues.
I'm saying more and more "if you don't have the time to write it then I don't have the time to read it". Therefore my first impression is: if the process is so formulaic that you can automate it, then the content itself cannot be of any interest and the whole song and dance should probably be scraped altogether - think of a person asking ChatGPT "make this one-liner sound professional" and then sending it to someone who auto-summarizes it.
You mention that the target audience is "stakeholders who want to validate your existence", which makes me think that your target audience doesn't really care about what you actually did but rather about being heard. If that's the case then replacing the Delivery Manager (who is arguably doing a good job) with a machine that screams "I want to think about you as little as possible" is definitely a risk. It may work well to provide the DM with a first draft, though.
Disclaimer: I don't know your team nor stakeholders and I'm probably not in your industry.
Interesting... I built an MCP server for their initial browser render as markdown, and I just tell the LLM to follow reasonable links to relative content, and recurse the tool.
Haha people have sent it to me! I'm currently trying to make it on my own in the wide world though.
I never disagreed with the decision to lay people off to become profitable. That's part of the implicit agreement when you take employment in the US. You can quit whenever you want and they can fire you whenever they want! I knew that going in!
I agreed with it, but of course it stung. That's only natural!
Sam and I are all good though! To his immense credit he reached out to me directly a little while back to mend any hurt feelings, of which I had a few. We're friends. He even came on my podcast and we talked for over an hour like old buds.
I have a lot of feelings and sometimes they get hurt. Sam has a fiduciary responsibility to the company. Today PlanetScale is a going concern and I'm happy and doing great! All is well.
Wow I didn't know he got laid off. I remember watching his videos a few years ago and absolutely loved his way of teaching. He's the reason I found out about PlanetScale to begin with.
Looking at their youtube channel, Aaron's videos had a total of ~1.4m views over 24 videos (an average of ~58k per video). Their recent videos don't even get past 1k views...
After they ditched there free tier, it became basically untenable to justify trying Planetscale for $30 (USD as well) on a POC or MVP product, and it also felt like you were paying a lot for unneeded hardware.
I went backpacking last year for only a little over a month. Absolute pain in my chest when someone who I'd gotten to known over the past few days said it was their last day lol.
Wait, I'm confused. Do you mean that I correspond with the caricature by which you're accustomed to see HN users represented, presumably not by themselves, on other social media platforms? Or do you mean instead that I correspond with a caricature of the caricatured representation that etc.? Your comment is ambiguous. Please clarify.
Slowing in this context means going down. Basically they look at 'age acceleration', I.e. how old are you epigentically compared to chronologically. They saw a reduction of several years in this measure over a much shorter period, basically meaning their epigenetic ages went down.
Although one of the clocks they used, DunedinPACE, only looks at pace of ageing, so in that case you can only infer that it slowed (as you do not get an 'epigenetic age' figure from DunedinPACE).
It's basically automating release notes and sprint summary's from existing systems like Jira and Linear. The target user is a product team, the target reader are business stakeholders who want to validate your existence. I've found this process to be stupidly time consuming for both our delivery manager, and whichever Dev they decide to tap on the shoulder to help contextualize tickets.
I feel like LLM's are a really good _summarizer_ and it can easily highlight if your tickets don't have enough context for actual people, if even an LLM can't write a summary with good enough context.
Idk, maybe it's a sensible usecase because you REALLY don't want novel ideas from the LLM in this case. You want it to tell you 1:1 what you did this sprint based on a list of issues.
reply