Kevin Cocco (@kcocco) header
Kevin Cocco (@kcocco) profile picture

Applied AI, LangChain, Fruit Tree Grafter, Solar Tracker, Maker

Utah Mtns
Joined July 2008
Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)Photo by Kevin Cocco (@kcocco)
we're launching a small number (3) of templates for common cognitive architectures these are configurable (choose LLM/vector store of your choice) Starting with: - ReAct agent - RAG chatbot - data enrichment (research) agent What should we add next?
๐Ÿ•ธ๏ธ LangGraph Templates ๐Ÿ•ธ๏ธ It's never been easier to start creating your own agentic applications. LangGraph Templates are a collection of reference architectures that you can clone, configure and then easily modify. ๐Ÿ“ Read more in the blog post: blog.langchain.dev/launchingโ€ฆ ๐ŸŒ See the list of curated templates: langgraph-studio.vercel.app
18
31
1
213
26,055
# scheduling workloads to run on humans Some computational workloads in human organizations are best "run on a CPU": take one single, highly competent person and assign them a task to complete in a single-threaded fashion, without synchronization. Usually the best fit when starting something new. Comparable to "building the skeleton" of a thing. Other workloads are best run on a GPU: take a larger number of (possibly more junior) people and assign tasks in parallel: massively multi-threaded, requiring synchronization overhead. Usually a good fit for later stages of a project, or parts that naturally afford parallelism, comparable to "fleshing out" a thing when the skeleton is there. There's some middle ground here - sometimes you can imagine a multi-threaded CPU execution of a small team collaborating. A good manager will understand the computational geometry of the project at hand and know when to delegate parts of it on the CPU or on the GPU. One notable place where the analogy breaks down a bit is that the worst thing that can happen when you misallocate computer resources is that your program will run slower. But in human organizations it can be much worse - not just slower, but the result can be of lower quality overall, more brittle, more disorganized, less consistent, uglier. The most common stumbling point here is trying to parallelize something that was supposed to run on the CPU. In the common tongue, this comes from the misunderstanding that something can go faster if you put more people on it, usually leading to outcomes where something is "designed by a committee" - not only is the thing actually slower, but the philosophy is inconsistent, the entropy is high, and the long-term outcomes much worse. The opposite problem is more rare and usually looks like someone doing something repetitive, uninteresting or tedious, where they could really benefit from more help. I think this is one accidental advantage of startups - they lack resources of large companies and run compute on powerful CPUs, winning in cases where that is the right thing to do. Larger companies, especially in cases where something is deemed of high strategic importance, will almost always reach for too much parallelism. TLDR: Think about your project, its computational geometry, its inherent parallelism, and which parts are a best fit for a CPU or a GPU.
79
340
48
2,839
335,449
Kevin Cocco retweeted
Space enthusiasts! Join #IAC2023 here NOW for the LIVE FIRESIDE CHAT with Elon Musk ๐Ÿš€๐ŸŒ  xitter.gq/i/broadcasts/1YpJkwODzโ€ฆ
1
2,069
173
2,827
48,245,224
An underrated aspect of LLMs is using them for structured data extraction Extracting knowledge triplets is a great use case! I gave it our most recent blog post about @MultiON_AI (blog.langchain.dev/multion-xโ€ฆ) and it came up with the below - how did it do @DivGarg9 ??
Did you ever want to extract knowledge graphs using LLM function calling? No? Well, here's a @streamlit app where you can play around with various inputs. E.g., feed it the Barbie plot, gpt-3.5 w/ function calling extracts graph triples. Give it a try: auto-graph.streamlit.app/
11
38
1
222
44,782
FIBONACCI SPIRAL rafael-araujo.com
1
9
63
Kevin Cocco retweeted
These are 9 observations over the course of 10 months at @redbuttegarden. I love exploring seasonal change, phenology, with children, PSTs, and Ts. What do you notice and wonder about the images? #NGSS #SciEd #UTSEEd โ€“ at Salt Lake City, UT
4
1
11
The gift to all of us
10
127
26
1,002
Kevin Cocco retweeted
A new kind of program analysis is emerging: AI code analysis. Here is the current state of analysis and where I think itโ€™s headed:
8
34
7
451
Kevin Cocco retweeted
The @SpaceX @Inspiration4x launch, endlessly flowing from the pad all the way to orbit. Composite of multiple tracking telescopes using new techniques to bring out the faintest colors and finest details--in 10K resolution. #EndlessInspiration
316
7,091
829
25,029
Kevin Cocco retweeted
Exhale, everybody.
The James Webb Space Telescope is on track for a launch date of Dec. 22. Additional testing, which was conducted due to an incident in launch preparations, concluded no observatory components were damaged. Observatory fueling operations begin on Nov. 25: go.nasa.gov/3nNhKAK
22
73
3
1,162
Very nice praise for The Long Tail, 15 years after its publication. "Five business books I wish I'd read earlier"
๐Ÿ’ก Many reading lists focus on recently published books. When @onetj wrote his top 5 list, he took a different approach. "Itโ€™s ... a personal reminder to bring diversity of time in addition to subject matter and authors to my reading queue." ๐Ÿ‘‡ openview.vc/3whDKGw
6
2
38
Drawing a Fibonacci spiral with a compass rafael-araujo.com โ€“ at Madrid, Spain
9
1
46
Golden Ratio/ Fibonacci rafael-araujo.com โ€“ at Madrid, Spain
8
35
Tomorrow, 4 volunteers will be locked inside HERA: a small, Earth-based habitat. This crew will simulate a mission to Phobos, a moon of Mars, to help NASA study how crew adapt to remote conditions to perform mission-critical tasks. Wish them luck! go.nasa.gov/3AXaab9
38
86
14
772
SAT! Join us @ Ogden Harvest Fest 10/2 11am โ™ป๏ธBaker Park, get yer Biochar & compost blends. Free 1 gal. samples! Build your soil health now for summer '22 success! Grow BIG w #biochar! From 11a-6pm #GoBiochar #UtahGarden #SaveWater #SlowTheFlow #Azomite #Humate #MycorrhizalFungi
1
2
obsessed with this guy who just uploads videos of him playing classic rock riffs while his birb freestyles vocals
1,781
51,433
6,342
219,540
Kevin Cocco retweeted
Utah DOT pilots Blyncsy's AI-powered road maintenance technology tcrn.ch/3vuZWMd by @rebeccabellan
7
16
โ€ข Read everyday. โ€ข Spend time with nature. โ€ข Ask questions. โ€ข Never stop learning. โ€ข Don't pay attention to what others think of you. โ€ข Do what interests you the most. โ€ข Study hard. โ€ข Teach others what you know. โ€ข Make mistakes and learn. โ€ข It's Okay to not know things!
116
6,212
328
21,617
Excited about this collaboration!! @ASE_Astronauts @AstroJDBartoe @DreamUp_Space @becauselearning!
Kevin Cocco retweeted
Solidity may be the single most valuable skill in the world today. You can obtain it without years of formal education. And we'll even pay you to learn it. Details here: 1729.com/learn-solidity-withโ€ฆ
30
343
55
1,846