@GSto

Working on a book about product thinking for engineers: https://xitter.cf/t.co/twWMTEjoFI

 Chattanooga, TN
statetransition.co/
Joined March 2008
  • Tweets16.4K
  • Following554
  • Followers1.7K
810Media
The primary thing I've learned from playing around with AI personal assistants is that my life is not that complicated
50
"Street Fight Everything" is this year's Barbenheimer
1
1
62
"For all have slopped and fell short of the Glory of God" Romans 3.23 Max
1
42
I wish there was a Github for writers/editors
nader dabit
@dabit3Aug 28
a good way to go viral on X is to say you wish something exists that you know damn well already exists this works especially well with emerging tech where there are like 100 early stage companies all fighting each other
84
Maybe I'm an old grump now, but Summer has a real mental tax. Heat makes people grumpy. You can't even go on a silly little mental health walk when the heat index is 99º at 6 am. Everything I typically do for a 'screen break' now comes with misquitos and burns
1
2
80
friendly reminder that many companies would rather remove the unhappy employee than fix the root problem. Think before you speak up
Dwarkesh Patel
@dwarkesh_spAug 7
OpenAI HR told Leopold that a major reason for his firing was the memo he'd sent the board warning how broken OAI's security was. What happened next makes me even prouder to call him a friend. People may have forgotten, but up until 2024, OpenAI had this secret non-disparagement clause in their off-boarding agreement. If you didn’t sign it, they'd clawback all your equity. As far as I'm aware, there were only two people ever who didn’t sign it - @DKokotajlo, and Leopold Aschenbrenner. Of all the researchers who left OpenAI before 2024, who had far more to fall back on, Leopold, all of 22 years old, was one of the only ones willing to refuse the golden handcuffs, and say, "I want to preserve my right to talk about safety and security at OAI.” We have a lot of disagreements, but he's among the most principled and resilient people I know.
127
LLM-at-work etiquette: If a model wrote it, don't ask others to read it. That doesn't mean you can't use LLMs to write. LLMs are useful for ideation, transcription, proofreading, and research. But if I want to read output from a model, I'll go talk to a model.
2
1
2
76
AKA, don't be a meat proxy xitter.cf/joshtriedcoding/status…
Josh tried coding
@joshtriedcodingAug 4
alright whoever came up with the term MEAT PROXY is insane
37
Thrilled to announce my new AI-powered self-analysis tool, Myopic
Itamar Golan 🤓
@ItakGolMar 10
OpenAI acquired OpenClaw FaceBook acquired MoltBook Choose your company name carefully…
1
68
Glenn Stovall retweeted
Alp
@49agentsMar 6
Replying to @GSto
worktrees + terminal multiplexing + containerizing is exactly the stack that made AI agents viable for me at scale. the observability piece is what most people skip until something breaks at 2am
1
1
23
5 skills that increase AI-powered leverage: 1. Parallel branches (worktrees) 2. Terminal multiplexing (tmux, zellij) 3. Containerizing (Docker, Nix) 4. Observability Literacy (Grafana, Sentry) 5. Structured writing (tech specs, problem statements)
2
1
54
Glenn Stovall retweeted
Mercury
@mercuryFeb 18
Better together 🤝 Mercury Personal is now included with Mercury Business. *Mercury is a fintech company, not an FDIC-insured bank. Banking services provided through Choice Financial Group and Column N.A., Members FDIC.
1
4
3
36
10,234
10 days later, @AnthropicAI releases Claude Back, a tool to recover lost funds with AI
This quoted post is unavailable.
Try viewing anyway · View on X
1
77
I'm in this tweet and I don't like it
Maria Made in Cosmos is taking a break✨
@made_in_cosmosJan 28
easy, before AI every developer had at least 5 half-finished side projects, now they've all become 20x as productive and have at least 100 half-finished side projects
2
47
Glenn Stovall retweeted
Cedric Chin
@ejames_cJan 27
I know this is somewhat useless to say and it won't work, but: When keeping up with AI, just pay attention to field reports of use. Don't bother with predictions, or opinion pieces, or takes. The vast majority of the latter are produced for self-soothing reasons.
10
5
2
60
2,871
Glenn Stovall retweeted
kepano
@kepano19 Sep 2025
AI agents built into cloud apps will always be sub-par compared to state of the art agents that you can use with Obsidian. This is because your Obsidian data is in your control, in plain text formats that are ideal for LLMs to process. You can choose to run any of the best-in-class agents and AI tools: Claude, Gemini, OpenAI Codex, etc. You also have the choice to run local models and privacy-preserving options. Or you can use none of these and enjoy not seeing sparkly AI buttons everywhere. Remember that cloud-based note-taking apps are not end-to-end encrypted. This is inherently less secure, open to breaches, and allows companies to make your private thoughts part of their training set. Obsidian is not working on adding agents because we don't have to. We'll let the AI labs focus on that. We're 4 developers and our focus is on making great editing tools for plain text Markdown files that are always in your control.
AI agents built into cloud apps will always be sub-par compared to state of the art agents that you can use with Obsidian. This is because your Obsidian data is in your control, in plain text formats that are ideal for LLMs to process. You can choose to run any of the best-in-class agents and AI tools: Claude, Gemini, OpenAI Codex, etc. You also have the choice to run local models and privacy preserving options. Or you can use none of these and enjoy not seeing sparkly AI buttons everywhere. Remember that cloud-based note-taking apps are not end-to-end encrypted. This is inherently less secure, open to breaches, and allows companies to make your private thoughts part of their training set. Obsidian is not working on adding agents because we don't have to. We'll let the AI labs focus on that. We're 4 developers and our focus is on making great editing tools for plain text Markdown files that are always in your control.

ALT AI agents built into cloud apps will always be sub-par compared to state of the art agents that you can use with Obsidian. This is because your Obsidian data is in your control, in plain text formats that are ideal for LLMs to process. You can choose to run any of the best-in-class agents and AI tools: Claude, Gemini, OpenAI Codex, etc. You also have the choice to run local models and privacy preserving options. Or you can use none of these and enjoy not seeing sparkly AI buttons everywhere. Remember that cloud-based note-taking apps are not end-to-end encrypted. This is inherently less secure, open to breaches, and allows companies to make your private thoughts part of their training set. Obsidian is not working on adding agents because we don't have to. We'll let the AI labs focus on that. We're 4 developers and our focus is on making great editing tools for plain text Markdown files that are always in your control.

61
66
24
1,222
138,067
Last article of the year, how to drive real change in 2026
1
26
A resolution is a statement of a goal. Strategy is a framework that shapes decisions. Resolutions are rigid, strategies are flexible. Resolutions are narrow. Strategy is holistic.
1
19
Resolutions lack a system for dealing with changing contexts. A strategy helps you decide what you’re going to do, how to prioritize, and empowers you to make decisions with confidence. statetransition.co/p/this-ne…

This New Year's, try a strategy instead of a resolution

At the edges no. 18

statetransition.co
20
Duolingo exemplifies the duality of gamification. On the paid plan, they use it to encourage language learning. On the free plan, they use it to encourage upgrading to the paid plan
25
Load more