Luke Van Seters
@lvanseters
Followers
2K
Following
4K
Media
33
Statuses
245
Giving people more @agency
Joined March 2012
Excited to share @agency - a better way for companies to care for their customers We've raised $12M from @Sequoia, and HubSpot founder @bhalligan is joining our board Hear more from my co-founder @eliast below covered by @MTemkin @TechCrunch
25
6
126
Today, we’re announcing Antimetal’s $20M Series A. Writing code is no longer the hard part. Maintaining it is. We’re automating everything that happens after you deploy. We have 60 spots available. Reply for early access.
359
125
2K
my friend @eliast is in his 40's, looks like he's in his 20's, and has the energy of a teenager... and we @sequoia are delighted to be in business with him for the third time! @MTemkin does a nice job of capturing what he's up to here: https://t.co/vLlMAWHqhr
techcrunch.com
Elias Torres has achieved a lot for somebody who immigrated to the U.S. from Nicaragua at 17 without knowing any English. He served as a VP of engineering
3
7
123
Today’s the day. Introducing my new company, @Agency — backed by @Sequoia and Hubspot Ventures; with my friend and mentor @BHalligan on the Board. Enjoyed getting to talk with @MTemkin @TechCrunch about what we’re building. https://t.co/OXKpM5XNY9
agency.inc
Agency uses AI to turn customer management into your fastest source of growth.
51
36
391
We're hiring a small, exceptional team of mostly engineers. Send me a DM to learn more https://t.co/3HtwCuM5C7
techcrunch.com
Elias Torres has achieved a lot for somebody who immigrated to the U.S. from Nicaragua at 17 without knowing any English. He served as a VP of engineering
0
0
4
Fun fact for keyboard maxis You can push your key repeat faster than the system settings limit on OSX defaults write -g InitialKeyRepeat -int 10 defaults write -g KeyRepeat -int 1 (Requires a restart)
1
0
6
LLMs keep advancing, but unlocking their potential requires better, novel UX. Artifacts is a perfect example for how small usability shifts can yield outsized value.
1
1
7
A slow Postgres query on launch day can be a nightmare scenario that jeopardizes your AI application. Learn @lvanseters effectively managed a launch day outage for https://t.co/3f50BfHDc4 when a huge spike in traffic, coupled with unexpected queries caused Postgres to peg to
2
3
10
Shout out to @htormey for being a great host! Lots of fun things we talked about: - Getting known-good SQL from LLMs - Speeding up LLM calls (got a 10X speedup on zelma) - Vector DB tradeoffs - Self-hosting - Constrained grammar generations - A DB war story - and more!
Thinking about building an AI powered app to explore a large data set? Want to know the pro's & con's of using pgvector over a dedicated vector store? Interested in hearing tips for reducing LLM latency? If so checkout my interview with @lvanseters about how he built Zelma.
0
2
6
At the dentist today they told me I’ve started grinding my teeth And the hygienist goes “in general - we’ve noticed a huge increase in people grinding their teeth since after COVID” Is this a known trend? She said like 80% of people she sees now are grind their teeth
8
0
4
Idk about the feature, but I like the idea of mimicking a call You always see people demo voice features yelling into their phone and having it yell back - which makes no sense in public Taking it like a call feels like an obvious answer hiding in plain sight
Introducing ☎️ CALL ARC, a brand new way to get an answer on the go. Say you’re walking to the train and you’ve got a quick question. Just raise Arc Search to your ear and ask it!
1
1
8
Instructor js has support for @GroqInc out of the box - I just threw up a few examples and added explicit validation for models and modes. 1.1.2 just published
1
2
4
Sources: What's next for AI agentic workflows ft. Andrew Ng of AI Fund https://t.co/CGKryrZJGj Gorilla: Large Language Model Connected with Massive APIs
0
0
0
It seems GPT-3.5 is at least as good or better than GPT-4 for many "agentic" tasks Left is a talk from Andrew Ng - shows looped LLM approaches on HumanEval (coding) with 3.5 barely edging out 4 Right is from Gorilla - an LLM tool use paper (up to the left is better)
1
2
8
OpenAI shared a customer story for our work with @ProfEmilyOster to build Zelma. Her team painstakingly gathered and cleaned all historical US grade school test results. So to make the data accessible, we built an LLM-powered app where users can explore the data just by asking.
1
4
14