LarryGraham01 Profile Banner
Larry Graham Profile
Larry Graham

@LarryGraham01

Followers
262
Following
1K
Media
52
Statuses
733

Founder @ Graham Labs. Designing AI-native products. Premium iOS + web. Villanova alum. https://t.co/Na9biv49kQ 🌊

Joined March 2011
Don't wanna be here? Send us removal request.
@LarryGraham01
Larry Graham
6 days
i’ve never been so relaxed building something before. after a long day, I can unplug and disappear into the world I’m building: Island Vault 🌊 🎧 original ambient music with cinematic video & mixer layers.
2
0
4
@steipete
Peter Steinberger 🦞
18 hours
Your @openclaw is too boring? Paste this, right from Molty. "Read your https://t.co/yS6cfGInCW. Now rewrite it with these changes: 1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take. 2. Delete every rule that sounds corporate. If
Tweet card summary image
soul.md
A reflection on what it means to have a soul — written by an AI who was given the space to think about it.
412
637
7K
@steipete
Peter Steinberger 🦞
3 days
How the sauce is made @openclaw
805
551
12K
@LarryGraham01
Larry Graham
3 days
GPT‑5.3‑Codex is FAST! used it with the Codex macOS app and watched it knock out a very technical sprint…all in about 1 minute. extremely impressed. but we didn’t just get a better model, we got better agent orchestration. at first i was skeptical of the Codex macOS app.
0
0
1
@LarryGraham01
Larry Graham
4 days
good morning all! just going to drop this here: “life can be so much broader once you discover once simple fact. and that is that everything around you that you call life, was made up by people that were no smarter than you. and you can change it, you can influence it, you can
2
0
4
@LarryGraham01
Larry Graham
4 days
most of the world doesn’t realize what just happened in software. we didn’t just get a better autocomplete. we got an entirely new labor model. the first wave of copilots made writing code faster. the second wave of agentic engineering makes finishing work faster: implement,
0
0
0
@LarryGraham01
Larry Graham
5 days
i am floored by how much faster GPT-5.2 and GPT-5.2-Codex are. that was my only real remaining gripe with codex…which is now solved. now just need to test out the codex macOS app further!
@OpenAIDevs
OpenAI Developers
6 days
GPT-5.2 and GPT-5.2-Codex are now 40% faster. We have optimized our inference stack for all API customers. Same model. Same weights. Lower latency.
0
0
0
@PaulSolt
Paul Solt
5 days
Disable “Include IDE context” if you work with multiple agents in Codex app. “makes zero sense for this to default to on for a *multi-agent orchestration tool* 90%+ of the time, what I'm looking at in my IDE has nothing to do with the request I'm sending off”
@sacino
Jake
5 days
codex desktop has an "include IDE context" setting, which is enabled by default this was on for two days before I realised it given it can affect a large % of your codex interactions, it should be more prominent
11
1
32
@steipete
Peter Steinberger 🦞
8 days
@Yuchenj_UW I don’t let Claude Code on my codebase. It’s all codex. Would be too buggy with Opus.
266
180
4K
@LarryGraham01
Larry Graham
12 days
If your brain doesn’t shut off at night, try this 🌊 I’m building Island Vault: premium ambient soundscapes + a mixer to layer ocean/rain/wind. TestFlight invites soon. Link in reply!
1
0
1
@danpeguine
Dan Peguine ⌐◨-◨
23 days
things that my @openclaw does for me: - timeblocks tasks in my calendar based on importance - scores tasks importance and urgency based on an algorithm that we are developing together as we go - leads me through a weekly review based on all the transcriptions from meetings &
@dreetje
André Foeken
23 days
To answer what I am currently doing with @openclaw (question by @liran_tal ): - Check my incoming mail, and remove spam - Check my incoming messages (through @beeper) - Order things for me - Send my reminders to @tana_inc - Create issues on @github - Sync my Google Places (so I
55
36
754
@LarryGraham01
Larry Graham
17 days
Excellent blog post here for those interested in the Codex agent loop 🔁 This is just the beginning.
@OpenAIDevs
OpenAI Developers
17 days
📣 How we built the Codex agent loop Ever wonder what Codex does between your prompt and its response? Each turn assembles inputs, runs inference, executes tools, and feeds the results back into context until the loop ends https://t.co/bJtbACRoJb
0
0
1
@LarryGraham01
Larry Graham
17 days
Just added cinematic motion backgrounds to Island Vault iOS app 🌊 Looping video behind ambient soundscapes. Ocean waves playing while you drift off to sleep. Now at 46 tracks, 10 moods, 9 mixable layers. Building a premium relaxation app. The small details make all the
4
0
8
@LarryGraham01
Larry Graham
22 days
Island Vault iOS app 🌊 onboarding update Cinematic drone visuals + my original ambient track “Fern Glow.” Ambient journeys for sleep / focus / relax (and good vibes) with mixable nature layers included. React Native (Expo). TestFlight next!
6
0
14
@LarryGraham01
Larry Graham
23 days
Built FableLoop 📚 5-minute interactive stories. One choice. Big consequences. (I was a big fan of those Goosebumps CYOA books as a kid) Choices feed a branching state system (relationships + risk + clues) → next scenes adapt → cliffhanger. This iOS MVP is moving fast!
4
0
10
@LarryGraham01
Larry Graham
23 days
Tried to relax on my flight last week. Ended up building an app instead 😅 Island Vault 🌊 a premium iOS ambient “journeys” app for sleep + focus…lush soundscapes + mixable nature layers. Built w/ React Native (Expo). Apple Dev approval pending!
3
1
8
@sama
Sam Altman
24 days
Very fast Codex coming!
@cerebras
Cerebras
26 days
OpenAI🤝Cerebras https://t.co/zvVIdIsw2u
681
543
9K
@LarryGraham01
Larry Graham
25 days
Super cool!
@iruletheworldmo
🍓🍓🍓
26 days
i never want to read any other way again.
0
0
4