I just sent the following in email to Manton after I posted a long article to my blog only to find micro.blog had deleted all the paragraph breaks:
Manton, I am very frustrated with Micro.blog and have been for months. I am looking around for alternatives but can’t find anything that suits me. Micro.blog is too. damn. buggy. I have scaled back what I am trying to do with it, moved my newsletter back to MailChimp, am no longer posting memes on Micro.blog and STILL it frustrates me.
From my perspective, you’re adding shiny features and gadgets and not addressing bugs. It’s like painting a house when the foundation is rotten.
Please please please take a few weeks or months to address bugs in Micro.blog. Don’t add new features, don’t launch a new service, just fix what we’ve already got.
I responded to your email this morning in more detail, but for completeness here I will add that I hear the frustration. I’m always fixing bugs but I know it sometimes doesn’t look like that if there is some part of Micro.blog that hasn’t gotten enough attention. Will keep working to improve it!
MarsEdit is a great app but it’s definitely not required. I’m almost always just using the official Micro.blog apps to post.
I don’t use Drafts, which also has an action and Mitch uses that-- but then he copies and pastes into the site versus using the post action. That said, I have not been able to reproduce this error with any of my text editors.
@manton Thanks for the timely response. Do the official micro.blog apps support cross-posting controls? Posting to drafts? As far as I can see, they do not, which is why I do not use them.
@danielmrose I don’t use Obsidian. It’s an enormous, hairy app to use for this one thing.
@jsonbecker While I do often use Drafts in the manner you describe, in this particular case I was not doing that. I wrote the post in Google Docs, downloaded it to the Mac in Markdown, then imported it to DevonThink and cut-and-pasted from DT to the Micro.blog web editor. (I know that sounds like a crazy roundabout route, but there were reasons why I did it this way.)
Importantly, the text looked fine in the Micro.blog web editor and in the preview in that editor — the paragraph breaks were only lost after I published the post.
@manton and @sod got back to me promptly in email to follow up on my bug report, and I will respond to those emails when things get a little quieter for me elsewhere.
I use the macOS desktop app and it does indeed save to draft and have cross-posting controls. There are some things I prefer the web app for, such as uploading images and site management, and I don’t like that the editor window keeps moving every time I open a new one, but for me I just work around them. Give it a go and be sure to check the menus for various bits of functionality and if you have any questions just tag me and I’ll do what I can to help.
Well, that’s interesting. I guess I’ve gotten used to Mac apps that don’t use the menubar anymore, because I did not think to look there. I was peering around the screen looking for a gear icon or something similar.
I will try the Micro.blog app for posting in the future, and if that works, I will consider this problem solved.
I’ve seen this behavior too. The preview looked fine but then after posting it was a wreck. Updating the post and copying the same content eventually fixed it. It also ruined the cross-post content with Medium.
Thanks for letting us know you’re also seeing missing paragraphs, @darkandnerdy. @MitchWagner and I have been troubleshooting this over email. While we can’t be 100% sure there’s no Micro.blog bug, my current working theory is that a combination of browser extensions and/or posting workflows is causing the issue.
@darkandnerdy, if you have an example text that consistently produces missing paragraphs when published, could you share it here along with:
Your operating system and version
Your web browser and version
Any browser extensions you have installed
Any other programs on your device that could potentially interfere (like clipboard managers or accessibility tools)
It wasn’t consistent. If memory serves on the third update, it worked and without me fiddling with the source file.
MacOS Sequoia 15.3
Safari Version 18.3 (20620.2. 4.11.5)
Extensions
Clip to DevonThink
Save to Pocket
Day One Journal Clipper
1Password (but disabled)
Download Video (disabled. Part of the Parallels VM Toolbox)
Save to GoodLinks (disabled)
Send to MarsEdit (disabled)
Open In Button for “Edge” (disabled. Part of the Parallels VM Toolbox)
Screenshot Page Safari Extension (disabled)
I run the Alfred.app launcher and I’ve enabled the Clipboard History feature with it. No other accessibility tools that I can think of.
If it happens again I’ll be sure to post it. The attached document (the article I was posting) was written with IA Writer but I didn’t publish it via IA Writer. I just copy and pasted into the Micro.blog web app.
Hope this helps.
p.s. Just realized you can only attach images, so copying and pasting the text of the article. Published version is on my blog.
My Conversion to a ChatGPT Promoter
I’ve been lukewarm on ChatGPT and generative AI. I saw the potential but predicted (erroneously) that we were still far removed from it being generally useful and reliable. Those ideas were formed through experience, incorrect comparisons and a lack of imagination on my part.
I wanted to write this post to give context to my skepticism and provide examples (with prompts) on generative AI’s usefulness. When I read articles on the web I see these very vague stories and trivial use cases that don’t inspire me. (Except meeting note transcribers, which in my experience have been universally amazing) I hope someone finds this useful and inspiring.
A little history
I’d used MidJourney, an image generation tool, for a bit to create images for my D&D game. MidJourney generally performed well if I kept the prompts basic. But the tool (at the time) had some odd side effects. For example, it was horrible at generating images of hands, so anything that required hands, like a wizard casting a spell, was a hot mess. It also didn’t do a good job of interpreting my intent and translating that into a sensible image. Minutes before writing this blog post I used the following prompt with MidJourney.
a centaur in the forrest hunting a deer with a bow and arrow
It generated the image below
Not exactly instilling confidence in me. This helped to shape my perception of what AI was capable of.
When it comes to incorrect comparisons I naively created a mental model where AI was just the next iteration of our smart assistant technologies like Siri, Alexa and Google Assistant. Those tools are great for keeping shopping lists but can be infuriating with some of the most basic tasks. This subconsciously created a mental ceiling on my expectations of what ChatGPT and other GenAI tools could do for me.
With these two things combined, my lack of imagination of what to even attempt to use ChatGPT for was in full-effect. I’d dismiss use cases without even attempting them, the way you would dismiss your 8 year old son as a viable helper to move a piano. Anything but the mundane just wasn’t possible.
Getting my feet wet
As the Internet started buzzing more and more about ChatGPT, I would hear a lot of chatter about how awesome it was but without any tangible time-saving use cases for me. I did begin to use it to do things like generate location names for my D&D game and the results were helpful!
Generate a list of 20 names of a cult organization in a fantasy setting that is tasked with preventing demons from entering the world
That prompt responded with a list (cut down for brevity)
1. The Veilwardens
2. Order of the Abyssal Seal
3. Guardians of the Broken Gate
4. The Demonveil Covenant
5. Wardens of the Unseen Lock
6. The Chainbound Order
7. The Seraphic Vanguard
8. Watchers of the Nethergate
9. The Crimson Sigil
10. The Sanctum of Eternal Vigil
Not bad, but again, a cheap parlor trick in my eyes.
Can ChatGPT help me professionally though?
As the generative AI fervor continued to heat up, I feared becoming a dinosaur. That guy in the office that does things “the old school way” and has the young folk running circles around him. (I already feel that way about Email vs Slack/Teams) I decided to start looking more seriously at ChatGPT.
This week I made a LinkedIn Post asking how people were using AI in their role as managers. It didn’t get a ton of traction but a few articles posted got me thinking of possibilities.
I’ve been working out some performance metrics for my team and I’d been thinking about using a Z-score to create a comparable value for story points completed across people on different teams. (Different teams might have different pointing methods so a direct comparison isn’t fruitful) I wasn’t 100% confident that statistically speaking, what I was trying to do was fair. I asked my wife, who is stronger in statistics than I and she pondered it for a bit before saying “Ask ChatGPT”. It sounded ludicrous to me but what did I have to lose.
Prompt
Can I use the z-score to compare developer stories per sprint for teams that use different story pointing methods
Response
Yes, you can use the z-score to compare developer stories per sprint across teams with different story-pointing methods, but you need to be cautious about how you interpret the results.
Why the Z-Score Could Work
Standardization – The z-score helps normalize the number of developer stories completed per sprint within each team. This allows you to compare how far each sprint’s performance deviates from that team’s own average, regardless of absolute values.
Relative Performance – Since different teams may use different story-pointing methods (e.g., Fibonacci vs. T-shirt sizing vs. linear scales), the absolute values might not be directly comparable, but their distributions within each team can be.
Potential Pitfalls
Different Definitions of “Story” – Some teams might split work into smaller or larger stories, which means a higher count of stories per sprint doesn’t necessarily mean more work was done.
Variance Differences – If one team has a much more volatile sprint performance (high standard deviation) compared to another, z-score comparisons might exaggerate or downplay certain trends.
Context Matters – Even with a z-score, a high number of completed stories might not indicate better productivity—it could just mean different estimation practices.
How to Use It Effectively
• Compute z-scores within each team for a fair comparison.
• Look at trends rather than absolute z-score values.
• Complement with other metrics like velocity trends, cycle time, or throughput to get a more holistic view.
It answered my question and my concerns almost perfectly. The one mistake, and this is a prompting mistake, is that it assumed I was using stories completed versus story points completed. But the advice is still sound. Now my creative juices are flowing.
I’ve wanted to do spend analysis on a few of our contracts. I’ve been avoiding it because getting the contract data into a workable format is tedious. Previously I’d dismissed ChatGPT as a viable solution, “it would be more effort than just entering it myself” was my unspoken stance. But now I had the audacity of hope.
I picked a vendor that had some quirks in terms of how the data was structured. A basic line item on the contract consisted of
Service
Quantity
List price
Sale price
It was also formatted in sections as opposed to all the line items being one after another. The other complication is that the list and sale prices were grouped in bundles, so the sale price would read “$10 per 10k executions” for example. I was just going to throw it at ChatGPT and see what I got.
I uploaded 4 years worth of annual invoices (after upgrading my ChatGPT subscription to the pro plan) and gave the following prompt.
Process the attached PDFs and convert the Committed Services section to a CSV file. The columns should be Service/Feature, Quantity, List Price and Sales Price. Add an additional column named “Contract Year” and fill that columns value with the year taken from the Start Date. Add another column that calculates the total price by multiplying the sales price and the quantity and then multiplying that value by 12
Given my experiences, I thought this was a bold ask. ChatGPT performed flawlessly. A few things that impressed me.
It was smart enough to understand the “$10 per 10k executions” and convert that to a per execution value for the sake of doing the math.
The response it gave back indicated that it understood my intent with the math. Part of the confirmation response was “Total Price (calculated as Quantity × Sales Price × 12 to reflect the annual cost)” It was smart enough to infer that the billing details were monthly and I wanted an annual total.
I downloaded my CSV, checked the totals against the invoices and they were spot on. I launched Excel, ready to import my new data and get to analyzing when I realized that my lack of imagination was still getting in my way. I went back to the ChatGPT prompt.
Analyze the attached CSV and describe for me any trends that you find. Also tell me what is the biggest driver of my spend year over year
It came back with a table (which I can’t share) that listed my annual spend per contract year, another table with my top line item spend per year and then a narrative about that year with inferred reasons for that spend. (“X became the highest cost driver, showing a move towards Y”) It recognized that the increase in specific line item categories showed an overall shift of investment and focus in those areas. It also performed a linear regression-based forecast on my top spending line items for the next three years. It also identified areas of negative growth in terms of usage/adoption and suggested identifying what was driving that trend and if it’s expected, to accelerate it to reduce costs.
To put a bow on it I asked ChatGPT one more question. I personally have estimated a total spend on the annual contract value where once we cross it, we should begin evaluating bringing that work in-house. (Eventually, it can become cheaper to run things yourself once you’ve hit a certain scale) I asked ChatGPT when it projected I would hit this number and it projected late 2027 with an estimated annual dollar amount. This was all done in under 15 minutes.
Next Steps
I’m now convinced that ChatGPT needs to be part of my toolbox. Instead of wasting 30 minutes of my time and then moving to ChatGPT for some tasks, I’ll start there, uninhibited by expectations, and see what magic I can wrought out.
Of course ChatGPT still has its deficiencies but we shouldn’t assume those are the norm. I asked it to generate a slide for me and regardless of the efficacy of my prompt, ChatGPT still doesn’t know how to spell words in images.
