iiinova — where your digital self keeps evolving

Reposted by @dlants.bsky.social

Michael Pershan @mpershan.bsky.social · 15/04/2026

Over the past 15 years few people have been wrong more frequently than Sal Khan.

Reposted by @dlants.bsky.social

Chris Dodds @liquid-chicken.bsky.social · 10/04/2026

Wrote about a road trip I took with a friend who's since died. "The Desert" is up in Marrow Magazine, Issue 16. marrowmagazine.com/the-desert/

marrowmagazine.com

021

dlants.bsky.social @dlants.bsky.social · 28/03/2026

I took a dabble into podcasting at one point and found descript.com life changing. Edit your audio/video like you edit your writing. It took me from like 20-40 hours per episode to about 4. I think it's particularly useful for doing multiple takes and restitching them together. Worth a try!

descript.com

Descript – AI Video & Podcast Editor | Free, Online

Descript makes editing video and audio as easy as editing text. Record, transcribe, edit, and publish in one tool. Try for free, with powerful upgrades for creators & teams.

030

dlants.bsky.social @dlants.bsky.social · 08/03/2026

I put together a #reading recs page on my blog. Any recommendations for things I might enjoy are welcome! dlants.me/reading-recs...

dlants.me

reading recs

110

dlants.bsky.social @dlants.bsky.social · 05/03/2026

New blog post! How does #AI change software engineering? dlants.me/ai-se.html

dlants.me

How does AI change Software Engineering?

010

dlants.bsky.social @dlants.bsky.social · 15/02/2026

New blog post! Why I don't think AGI is imminent dlants.me/agi-not-immi... #ai #llm #agi

dlants.me

Why I don't think AGI is imminent

033

dlants.bsky.social @dlants.bsky.social · 26/01/2026

I've found it invaluable as I get ramped up on a new system and have a hard time keeping all the info I'm learning straight. The perfect pairing for my #neovim #nvim ai plugin https:// github.com/dlants/magenta.nvim

000

dlants.bsky.social @dlants.bsky.social · 26/01/2026

I really think this could be a great way to manage documentation for a large/complex code repo, since it makes docs a lot more discoverable. Docs that get found end up getting maintained.

100

dlants.bsky.social @dlants.bsky.social · 26/01/2026

Agents make it really easy to crawl your code base and distill the actual code + comments into markdown summaries. Or to audit your markdown summaries to verify that they're still in-line with what the code actually does.

100

dlants.bsky.social @dlants.bsky.social · 26/01/2026

The main goal of this is that I have a growing collection of various process / system design / incantation notes, and I wanted my coding assistant to be able to discover and apply them for me. I was keeping them in skill.md files, but they were getting kinda large, and discovery wasn't great.

110

dlants.bsky.social @dlants.bsky.social · 26/01/2026

Spent the weekend hacking together [a personal knowledge base cli](https:// github.com/dlants/pkb) / agent skill.

110

dlants.bsky.social @dlants.bsky.social · 26/11/2025

The big win for me was replacing the puppeteer mcp server with the puppeteer skill. It exposes a programmatic interface (which means fewer round trips between the agent and the tool), and takes up a lot fewer tokens in my system prompt due to progressive disclosure! github.com/dlants/dotfi...

github.com

dotfiles/magenta-skills/browser at main · dlants/dotfiles

my dotfiles for vim, zsh, i3, etc. Contribute to dlants/dotfiles development by creating an account on GitHub.

000

dlants.bsky.social @dlants.bsky.social · 25/11/2025

I made the transition to using just ghostty after watching this video www.youtube.com/watch?v=o-qt... I was able to replace my "project switcher" with hammerspoon github.com/dlants/dotfi... Still really miss some parts of tmux though, like github.com/ghostty-org/... though.

youtube.com

If Mitchell Hashimoto succeeds, Tmux & Zellij will disappear

YouTube video by Changelog

130

Reposted by @dlants.bsky.social

Walker Sumida @sumida.page · 16/11/2025

I’ve released a new Neovim plugin: deepl.nvim. It provides a simple DeepL translation workflow directly inside Neovim — no switching windows or copying text around. #neovim #nvim #lua #deepl github.com/walkersumida...

011

dlants.bsky.social @dlants.bsky.social · 15/11/2025

After reading about it for a bit, it seems like Claude Code sprinkles in system reminders periodically to encourage the agent to use the skills jannesklaas.github.io/ai/2025/07/2...

jannesklaas.github.io

Agent design lessons from Claude Code

First, acknowledge the obvious: The last post on this blog is from 2019. Most of the other posts here are about Uni. Some are still pretty good! Others maybe less so.

010

dlants.bsky.social @dlants.bsky.social · 15/11/2025

I imagine the real trick behind skills is whatever they're doing to get the agent to make use of the progressive disclosure efficiently. Maybe tuning? Maybe they periodically remind the agent that skills are available?

000

dlants.bsky.social @dlants.bsky.social · 15/11/2025

Even prior to skills, I experimented with introducing progressive disclosure to my context md files - having it be a "directory", pointing to other md files that had more details about specific topics, but I find that the agent just ignores those links.

100

dlants.bsky.social @dlants.bsky.social · 15/11/2025

hey @simonwillison.net, I don't suppose you have done any reverse engineering of the skills implementation within claude code? I'm really curious how they instruct the agent to use the skill descriptions, and how they keep the skills from being lost in the early context as the agent works.

200

dlants.bsky.social @dlants.bsky.social · 24/09/2025

I wrote a new blog post about the culture of hard work in tech, perfectionism, self-compassion and my dreams for the tech industry. You can read it here: Self compassion and the disposable engineer dlants.me/self-compass...

dlants.me

self compassion and the disposable engineer

030

dlants.bsky.social @dlants.bsky.social · 22/09/2025

@udini.bsky.social really enjoying the book! For me it's been a nice reminder to resume my efforts to let go of chasing measurable strength and chasing fatigue. Leaving the gym when you're not tired is tough!

010

dlants.bsky.social @dlants.bsky.social · 31/08/2025

strongerbyscience is great for no-nonsense, evidence-backed nutrition advice. Some of it angles towards "getting ripped" but it is generally grounded in science and approaches it with a great 80/20 mentality. You might want to start from this guide: www.strongerbyscience.com/diet/

strongerbyscience.com

The Definitive Diet Setup Guide: How to Build and Adjust a Smart Nutrition Plan

This guide covers everything you need to know to set up a well-structured diet that supports your performance and body composition goals.

010

dlants.bsky.social @dlants.bsky.social · 13/08/2025

So the best way to get access to gpt-5 for this purpose is to set up a script that burns through $50 of tokens to get you to tier 2. That's absolutely bonkers! Just let me preload my account with $50 of credit to get access to the higher tier!

010

dlants.bsky.social @dlants.bsky.social · 13/08/2025

30K TPM in tier 1 basically prevents you from being able to use a coding assistant. And there's no way to pay your way to a higher tier, you have to get there by organically spending $50

110

dlants.bsky.social @dlants.bsky.social · 13/08/2025

I develop a coding assistant and OpenAI feels really hostile towards developers. Their sdk is a mess (does not adhere to jsonschema, is poorly documented). Recently I tried to run some experiments on gpt-5 and immediately ran into their rate limits / tiering system.

110

dlants.bsky.social @dlants.bsky.social · 13/08/2025

Open source tools should just let you define a regex for finding context files. (Like `autoContext` in magenta github.com/dlants/magen...)

010

dlants.bsky.social @dlants.bsky.social · 13/08/2025

- I added authentication via anthropic's max and pro plans, which lets you use tokens the same way as claude code (thanks to the opencode folks for their open-source implementation for how to do this). This is much cheaper relative to using the pay-per-token API for heavier users.

000

dlants.bsky.social @dlants.bsky.social · 13/08/2025

- I renamed "@compact" to "@fork", and also changed it from a forced tool use to just a regular tool. This means the agent can think before using it, improving the quality of the summary, and also this now takes advantage of the conversation cache, making these tool calls a lot faster and cheaper

100

dlants.bsky.social @dlants.bsky.social · 13/08/2025

Some updates for my #neovim #nvim ai plugin github.com/dlants/magen... - I improved the turn-taking. You can now interrupt the agent by sending additional messages or use the @async prefix to your message to enqueue it to be sent at the next turn-taking opportunity

github.com

GitHub - dlants/magenta.nvim: A tool-use-focused LLM plugin for neovim.

A tool-use-focused LLM plugin for neovim. Contribute to dlants/magenta.nvim development by creating an account on GitHub.

110

dlants.bsky.social @dlants.bsky.social · 01/08/2025

I can now have multiple ghostty windows open, one per tab, and use a command shortcut to quickly switch between them :tada: Now I just need to figure out how to make my ghostty sessions persistent, and do some tweaking around how tabs are numbered, and I'll basically be there.

000

dlants.bsky.social @dlants.bsky.social · 01/08/2025

this uses hammerspoon to launch a ghostty terminal. There it runs a script that uses hammerspoon's cli to query the open windows and tabs (using the stuff that ghostty exposes for a11y). It then feeds it into fzf, and when fzf returns a selection, uses hs again to switch to that window/tab.

100

dlants.bsky.social @dlants.bsky.social · 01/08/2025

After a night of hackery, I was able to replicate something workable using #hammerspoon and ghostty's accessibility features! github.com/ghostty-org/...

110

dlants.bsky.social @dlants.bsky.social · 01/08/2025

After watching @mitchellh.com talk about this, I was inspired to try eliminating tmux from my workflow and using #ghostty directly www.youtube.com/watch?v=o-qt... One thing I missed was being able to have a tmux session per project, and my fzf session switcher github.com/dlants/dotfi...

github.com

dotfiles/scripts/tmux-session-using-fzf at main · dlants/dotfiles

my dotfiles for vim, zsh, i3, etc. Contribute to dlants/dotfiles development by creating an account on GitHub.

110

dlants.bsky.social @dlants.bsky.social · 27/07/2025

ok this was actually pretty dope. I asked claude sonnet 4 (using my magenta plugin) what the actual clickable area of a "tick" was in d3. It created a demo html page, opened it using the playwright mcp server, and ran some experiments to give me a grounded answer.

a simple graph illustrating what the target click zones for d3 ticks are in red rectangles

000

Reposted by @dlants.bsky.social

Simon Willison @simonwillison.net · 26/07/2025

I'm seeing a lot of commentary blaming the egregious data leak from the Tea dating safety app on vibe coding I'm confident that, in this particular case, that's not what happened: the code at fault looks to have been written back in late 2023 simonwillison.net/2025/Jul/26/...

simonwillison.net

Official statement from Tea on their data leak

Tea is a dating safety app for women that lets them share notes about potential dates. The other day it was subject to a truly egregious data leak caused by …

611425

dlants.bsky.social @dlants.bsky.social · 26/07/2025

One cool thing is that you can use options to [append to the system prompt](github.com/dlants/magen...). I think by providing additional [examples of how you want it to behave](github.com/dlants/magen...), you can have it be a lot more useful for your specific use-case.

000

dlants.bsky.social @dlants.bsky.social · 26/07/2025

I also opted to have this be manually triggered (Shift-Ctrl-l by default in insert or normal mode). This is a lot [less distracting](unstable.systems/@sop/1148985...).

unstable.systems

sofia (@sop@unstable.systems)

Attached: 1 image A shitpost that's been brewing in my head for a while now

110

dlants.bsky.social @dlants.bsky.social · 26/07/2025

One thing that is interesting about this is that I wasn't able to get good results from smaller/faster models like claude haiku, so I opted to use a larger model instead. I found that the small delay of about a second was worth it for more consistent results.

100

dlants.bsky.social @dlants.bsky.social · 26/07/2025

- Finally, I show the find/replace in the buffer using [virtual text extmarks](github.com/dlants/magen...), applying a comment effect to the added sections, and a strikethrough to the removed sections

100

dlants.bsky.social @dlants.bsky.social · 26/07/2025

- I then feed that along with the [context surrounding the cursor](github.com/dlants/magen...), and a [system prompt](github.com/dlants/magen...) into an LLM, [forcing a tool use for a find/replace within the context window](github.com/dlants/magen...)

100

dlants.bsky.social @dlants.bsky.social · 26/07/2025

- I used an [lsp server](github.com/dlants/magen...) to track opened files and aggregate text changes to get a stream of diffs.

100