@fromaustinc

Chief Growth Officer at @Xtrace_ai | founder | @yale Building your team's shared brain sharing the real 0 to 1 journey, mistakes included

 San Francisco, CA
mem.xtrace.ai/
Joined November 2023
  • Tweets988
  • Following1K
  • Followers1.3K
39Media
AI gets better → humans get lazier → prompts get shorter → output gets generic. When everyone's using the same models with the same low-effort prompts, everything starts to look the same. The only differentiator left? An AI that actually knows your context. Your history. Your preferences. Memory becomes the moat.
16
3
1
142
66,052
leggo! this is what yall have been waiting for
Tristan Gūwalgiya C.
@tristangchenOct 20
Today we're launching XTrace, an open-source macOS app for people who code with agents. See AI vs human time, API-equivalent spend, and insights on what to improve. Add your own scoring skills or ones you discover. Try it: github.com/XTraceAI/xtrace-d…
3
108
Today we're launching XTrace, an open-source macOS app for people who code with agents. See AI vs human time, API-equivalent spend, and insights on what to improve. Add your own scoring skills or ones you discover. Try it: github.com/XTraceAI/xtrace-d…
17
9
6
34
17,556
ain’t no way this going to production…but if they do. the car chases will be 🔥🔥🔥
Polymarket
@PolymarketOct 16
BREAKING: Tesla's Roadster goes airborne, soaring over a row of Tesla vehicles in a live stunt at its unveiling event.
3
140
ep 3 - sessionmaxxing is in
3
88
ep 2 - agents love to ragebait
2
49
ep 1 - Jules the new eng hire
2
54
Introducing Claude.md doctor An agent skill that examines your CLAUDE.md / AGENTS.md, grades it and tells you how to FIX it It even backtests your sessions to find the flaws that you can't tell just from the file Free and open-source. Try it today with just 1 command: npx skills add agent-clinic/claude-md-doctor
8
6
3
126
17,244
We're obsessed with making AI smarter. Maybe we should be obsessed with making it hesitate at the right moments.
11
201
AI doesn't need more answers. It needs better judgment about which answer actually matters.
3
152
The hardest thing to teach AI isn't reasoning. It's knowing when it's wrong.
1
4
136
Every model can generate an answer. Very few know when to ask for more context.
2
122
Everyone wants smarter AI. I want AI with better judgment. Those are two very different problems.
1
1
4
124
The next breakthrough in AI won't come from another benchmark. It'll come from teaching models when not to be confident.
2
3
155
Intelligence gets attention. Judgment earns trust. That's the gap the AI industry is trying to close.
2
82
The next platform war in AI won't be about models. It'll be about who owns your context. Because memory is where switching costs are born.
1
4
112
The difference between a tool and a teammate is memory. One executes tasks. The other accumulates context.
1
64
We measure AI by benchmark scores. Users measure it by one question: "Why do I have to tell you this again?"
2
89
The biggest UX problem in AI isn't hallucination. It's having to explain the same thing twice.
2
121
Everyone is obsessed with making AI agents smarter. I'm obsessed with making them remember. Intelligence without memory is just expensive autocomplete.
1
69
I passed on the most valuable company in human history back in 1602, I had the chance to invest in an unknown spice trading company and I completely missed this message...now they're valued at $8 trillion!! oh well, you can't win em all
🤖 Made with AI
1
1
49
Load more