StrongDM | [Staff, Senior, Junior] AI Agent Engineer | San Francisco Bay Area (Palo Alto) | Full-Time | ONSITE | SW3.0
StrongDM applies deep tech to hard problems for demanding cybersecurity customers. Our embrace of large language models continues that tradition, achieving useful and reliable outputs from ambiguous and non-deterministic inputs.
Join me (Justin, co-founder & CTO) and our AI Agent team to help our global customers secure their most critical systems.
Ideally: if you've already decided you need to be working on the frontier of this technology wave & you're open to doing so in person at a physical whiteboard, e-mail me a few words to that effect ([email protected]).
Finally: on a personal note - a mix of awe, ambition, anxiety, and confusion are inevitable at this moment. Our small team has found a flow, and we're successfully metabolizing the daily changes in the gradient. Come on a run with us; see what we see.
StrongDM | [Staff, Senior, Junior] AI Agent Engineer | San Francisco Bay Area (Palo Alto) | Full-Time | ONSITE
StrongDM applies deep tech to hard problems for demanding cybersecurity customers. Our embrace of large language models continues that tradition, achieving useful and reliable outputs from ambiguous and non-deterministic inputs.
Join me (Justin, co-founder & CTO) and our newly-formed AI Agent team to help our global customers secure their most critical systems.
Ideally: if you've already decided you need to be working on the edge of this technology wave & you're open to doing so in person at a physical whiteboard, e-mail me a few words to that effect ([email protected]).
StrongDM | [Staff, Senior, Junior] AI Agent Engineer | San Francisco Bay Area (Palo Alto) | Full-Time | ONSITE
StrongDM applies deep tech to hard problems for demanding cybersecurity customers. Our embrace of large language models continues that tradition, achieving useful and reliable outputs from ambiguous and non-deterministic inputs.
Join me (Justin, co-founder & CTO) and our newly-formed AI Agent team to help our global customers secure their most critical systems.
Ideally: if you've already decided you need to be working on the edge of this technology wave & you're open to doing so in person at a physical whiteboard, e-mail me a few words to that effect ([email protected]).
StrongDM | [Staff, Senior, Junior] AI Agent Engineer | San Francisco Bay Area (Palo Alto) | Full-Time | ONSITE
StrongDM applies deep tech to hard problems for demanding cybersecurity customers. Our embrace of large language models continues that tradition, achieving useful and reliable outputs from ambiguous and non-deterministic inputs.
Join me (Justin, co-founder & CTO) and our newly-formed AI Agent team to help our global customers secure their most critical systems.
Ideally: if you've already decided you need to be working on the edge of this technology wave & you're open to doing so in person at a physical whiteboard, e-mail me a few words to that effect ([email protected]).
Burak - one wish I've had recently is for a "py data ecosystem compiler", specifically one which allows me to express structures and transformations in dbt and Ibis, but not rely on Python at runtime. [Go|Rust]+[DuckDB|chDB|DataFusion] for the runtime. Bruin seems very close to the mark! Following.
Sonnet is great, but also suggest exploiting custom instructions in the ChatGPT UI. Here's a snippet from mine:
Extremely concise, formal. As short as possible. Assume I am an industry expert in any topic we discuss. Answer assuming I have the highest level of intellect possible, and do not require explication regardless of the sophistication of the topic. In cases where one approach among many is superior, offer an opinionated argument in favor of that approach.
I've built a few games with my son over the years. The fun part for us was all about fast iteration, and then laughing at the bugs together.
There are some other recommendations here for how to approach 3d, and he is specifically asking for 3d -- but I want to put in one more pitch for 2d: the fun-to-tedium ratio can be much higher.
I wonder if you could spend some time prototyping some of his ideas in LÖVE https://love2d.org/ -- if you show him the smallest sketch of something working, he might have an idea about what to add next.
Many years ago, on a flight, we went from 0 to game before we landed (with no experience) using LÖVE.
On a computer, I'd paste in a corpus of some sort as a regular ChatGPT message - just because it's easier to accumulate a big string. Note with GPT4 Turbo and the recent UI upgrades, the context window is so large now that you can paste a sizable body of knowledge, possibly even as an attached file.
I'd then switch to the phone and retrieve the chat from History.
Here's an example prompt I just used to help my son prepare for a DMV written test:
```
I'm going to paste a large list of questions and answers and then switch to voice mode. Once I indicate that I'm ready, begin quizzing me on these questions. Feel free to rephrase slightly. My goal is to achieve complete retention of all of these questions through quizzing and spaced repetition. The questions are California DMV questions. I am preparing to take the written test.
1. *Q:* You may drive off of the paved roadway to pass another vehicle.
*A:* Under no circumstances.
2. *Q:* You are approaching a railroad crossing with no warning devices and are unable to see 400 feet down the tracks in one direction. The speed limit is...
*A:* 15 mph.
...
```
While walking the dog today, it talked me through some trade-offs between DBSCAN and isolation forests. Walking + verbalizing the problem is a very different and positive experience for me.
I've also used it several times on ~15-20min drives to memorize something I wanted to have available for immediate recall. I had it chunk & quiz me, and by the end of the drive I had it down pat. Fun use of drive time.
QR-powered home organization app! My family and friends use it constantly, but I never polished or promoted it further than that video :) If you're organizing your garage/shed/projects bench and want to give it a try, I'm happy to mail you a big stack of stickers!
Could be we're in a (short?) interregnum analogous to pre-Rails Ruby: there are lots of nascent frameworks, but the dominant one hasn't been born yet. FWIW - DIY is working well for me.