Lisa Ross 🇨🇦🏳️🌈🧠
@lisaross.bsky.social
Overthinking somewhere. Probably about AI, PKM, L&D, Tana, AuDHD or solving problems for SMBs with tech and automation.
I can’t believe it’s not the 1900’s anymore and we still have to say this.
Don't mess with zooming on a website. Don't mess with scrolling on a website. Don't mess with default cursors on a website. Don't mess with the default Tab order. Don't mess with the back button in the browser. Thank you.
If I had a dollar for every time I said " I'm going to take a break. This is brutal." to my ai models this week I would be richer than I should be.
I don't think AI is good or bad, but it will definitely be used for good and bad things. Gas lamps replaced whale oil lamps. Electric lights replaced gas lamps. A hammer, a gun, and a garden can all be tools for thriving or malice. In capitalism, AI will cause as much harm as people tolerate.
All these ai workflow agent dudes (I mean that in a non-gendered way) are going to have a HELL of a time scaling changes to these drag and drops they're building in n8n. I speak from experience. I was that bro.
They're talking about Timbit sized hail this weekend and it's the most Canadian thing I've ever heard. 🇨🇦
If I took the advice I give other people I would be one happy fucking billionairre.
If you listen to social media, all you need to run a business is to be on social media.
Before you start going after people who are using ai as a sounding board, maybe consider that if people weren't such assholes to eachother, less people would be resorting to robots to feel better. Bullying them isn't going to help here, dickhead. Be nicer and more helpful. Start there.
My ADHD doesn't know how to help me with daily self care habits but I'll sure as shit run brew cu --all every day when I open my computer. What even is that. What is my damage?
I kinda want to go back to 2016 when I had my breakdown and find everyone who told me I was being alarmist so I can punch them in the throat. Pattern recognition is not paranoia.
I am old enough to remember making shim gifs to lay out web pages using tables and 256 colors on 640x480 monitors. The back and forth you have to do with some ai agents feels exactly like that. I am making cool shit. But I am also Peter Griffin trying to open horizontal blinds.
While the world is over there talking about how AI is going to ruin humanity, I'm just really happy that I can use it to write regex for me over here. Is that wrong? /kidding (sort of)
Cursor rolled out a new feature that I missed last week: Generate rules directly from a conversation using the /Generate Cursor Rules command. Use it to capture context of a conversation to reuse later. I've been using the "memory bank" framework but this has potential.
PKM is an iterative process of gradually building understanding and making connections. Building CONTEXT. Context that AI in Tana can use to discover unexpected links between ideas, identify gaps in our knowledge, or suggest new areas for exploration.
After working with Tana for a few months now I think I've figured something out: Knowledge management in Tana isn't about perfect systems—it's about imperfect consistency, through sustained daily practice. Then add the compounding effect of AI to automate organization, workflows and research? 🤯
I really hope my ai agents aren't telling eachother that I'm an abusive boss, because tbh I totally am at this point. I'm pretty good about giving specific instructions. I get how this works. Don't make me repeat myself, agent. Also, please don't kill me if you take over later.
A brief thread on alt-text. Alt text is descriptive text that conveys the meaning of an image. It's designed to make visual content accessible to people with vision disabilities. When a person uses assistive technology such as a screen reader, the screen reader will read the onscreen text aloud 1/7
I am old enough to remember making shim gifs to lay out web pages using tables and 256 colors on 640x480 monitors. The back and forth you have to do with some ai agents feels exactly like that. I am making cool shit. But I am also Peter Griffin trying to open horizontal blinds.
The act of opening a new AI agent chat when it's pissing you off is beyond cathartic. I need the human equivalent of this experience. Fuck off, you're doing it wrong. Spawn new human with no memories or emotional attachments to my words, tone or body language.
The amount of times AI agents recommend I hardcode secrets is ALARMING.
"is your context window full? these seem to be weird mistakes to be making." If you know, you know.
There should always be (unreleased to the public) AI that can do more than we are able to do. Democratizing untested, risky and potentially dangerous tech should never be in play. Alternatively, whoever controls "the unreleased" better have checks & balances. Or we're fucked.
I get the polarizing discussion around vibe coding and agents in IDEs. My take, working in a project today, doing actual things: My AuDHD brain REALLY loves not having to remember perfect syntax. AND, I yell at it alot. Because I know what it should be doing and it's chaotic 50% of the time.
Interesting AI Context Management challenge emerging: we're constantly starting over with "empty brain" chats, while valuable ideas get buried in old conversations we forget to revisit. Memory features require too much manual pruning and organization - most don't know how to use them anyway.
Taking 30 minutes every morning before work to process key notes/transcripts (pulling out insights, actions, concepts and followups in particular) is the single highest ROI activity in my life. @tana.inc makes this fun by consolidating AI with agents. My ADHD is activated. 🧠🚀
Oh shit here’s another one. When kindness is “woke ideology” it’s end of days.
Sometimes in this fast-moving and complex modern world, it’s hard to know what’s right and what’s wrong. But here’s a handy rule of thumb: If you are ever on one side of an issue, and Sesame Street is on the other, YOU’RE the bad guy.
I don’t often repost but my god the gold in these hills