I had never used @ExaAILabs until 30 minutes ago. I saw @jasonlk's post, created a free account in 30 seconds, and connected it to @Muse.
In minutes it pulled state and federal DUI and crash fatality data and built charts. (I'm in the alcohol monitoring space.)
👉 California DUI arrests: 366,834 in 1990 → 124,141 in 2019. Down 66%.
👉 In 2024, 912 of California's 3,876 road deaths were in crashes where a driver was at .15 BAC or higher -- nearly 2x the legal limit.
Pretty incredible to have vast source data paired with an AI agent.
Our agents use a LOT of Exa
For us, it just covers all the gaps. The gaps all the APIs and enrichment services we use for our agents don't cover.
It's relatively cheap, so we basically run it unmetered (like Jev now, too)
Something cheap enough to run unmetered 24x7 = something really big
Especially if your agents use it all day and night long. As our agents do.
We got the Bambu P2S for my son's 9th birthday this past June and it's been great so far.
Somehow we printed a sweet collapsible sword. The mini castle is a small test print of our much bigger 'vibe-manufactured' castle; we used Opus 5.5 and only a prompt to create the printable file.
Today I installed Grok @bot. First impressions:
- I really like it.
- It's fast.
- It goes above and beyond the call of duty on most answers in a way that felt different from other AI platforms.
As background, I use @claudeai Fable 5 with Cowork nearly every day for business (Team) and/or personal use and love it. I have @openclaw. I'm not a software engineer but I hacked around with Claude Code enough to build cited.co (hobby project).
To test Grok @bot I asked it to analyze my performance in yesterday's Double Dipsea trail run in Marin. It not only pulled my results, but pulled full results for all 421 finishers - names, ages, splits, hometowns, etc.
From there it told me things about my performance that I would have never known:
- how rare negative splits are across the field (faster second half race time vs first half): only 4% of runners ran a faster second half in the race than their first half.
- how many people I passed in the second half (42).
I didn't ask for charts but it made great charts! In fact my prompts were basic, short, and generic. Grok @bot outperformed expectations by a mile.
Impressed by the comprehensive Dipsea analysis, I spun up a 'CEO Advisor' bot. It pulled so much public data about BACtrack so quickly that I thought it somehow had access to private data; no, it was just really good and fast at incorporating public data into answers. It then recommended making a key hire for one of our divisions, had me sign into my LinkedIn account through a virtual Chrome browser, and then identified 10 great candidates. Not bad candidates, high quality, great candidates with directly related experience. It was fast!
I didn't want to get excited by a new AI platform but I am. Nice work @bot team.
Really impressed with the frontier Gemini models, have been excited to test @googlegemma locally on an iPhone 17 Pro. Maybe I should be asking more logic and summary questions instead of fact questions though....?
Fingers and toes used to be AI’s achilles heel. From my experience, creating words and phrases in an image has improved dramatically but is still an obvious weak point.
It’s always good to have ChatGPT review its own work. Here’s the next prompt:
“How realistic are the features described in the chat above in numbers 1 through 3? Carefully check the biomechanics and physics assumptions in 1-3 and provide a short, expert analysis.”
Output:
4/5
