flapstacks 🇺🇸

12.8K posts

flapstacks 🇺🇸 banner
flapstacks 🇺🇸

flapstacks 🇺🇸

@codegraph

deus vincit

🇺🇸 Katılım Nisan 2021
389 Takip Edilen753 Takipçiler
Sabitlenmiş Tweet
flapstacks 🇺🇸
flapstacks 🇺🇸@codegraph·
YEAR 2084: a ritually pure priest class has emerged. They are the few permitted to access the ASI Lore 100. Around them, a civic religion has taken shape and remade society. Every household keeps an ancestor-simulation model at the entryway, greeting it upon returning home.
English
7
2
36
2.2K
daedalus
daedalus@BasedDaedalus·
what are we even doing man
daedalus tweet media
English
5
1
19
730
tapir worf
tapir worf@tapir_worf·
gm simcluster
Indonesia
5
0
33
525
flapstacks 🇺🇸
flapstacks 🇺🇸@codegraph·
I've built a whole stack of code, understanding, ontology extraction, and behavior analysis certification using this beads workflow. I've also built a correct historical fiction video game set in the late 11th century with complete lore. I've also made a skill that turns pain points into business based on a knowledge graph of all the books on the math and engineering departments. And more. It's so well organized I'm actually able to efficiently use up my 20x max account limits. Thanks so much
English
1
0
3
90
Jeffrey Emanuel
Jeffrey Emanuel@doodlestein·
Or just use ntm and my /vibing-with-ntm skill and /beads-workflow skills and leverage your existing Claude Max and GPT Pro subscriptions to benefit from the 20-to-1 cost advantage. No harness can overcome that cost differential, and the model is ultimately what matters. I haven't been "flying the plane" for months, and I'm delivering at scale across dozens of serious, complex projects: github.com/Dicklesworthst…
Prasanna S@myprasanna

Launching @vorfluxai : The autopilot for software engineering. I was prev co-founder / CTO of @Rippling ($10B) and #1 coder in India. Vorflux is my high octane Ferrari. Every AI coding tool still makes you fly the plane. That's the copilot model: you stay in the seat, approving every turn. The models quietly got good enough to fly the whole route, but the tools never caught up. So we built the autopilot. @vorfluxai raised a $15M seed by @ycombinator @peakxvpartners @alliancedao @parkerconrad @jake_zeller @balajis @nivi @metakovan @lmrankhan @nikitabase @0xrwu @ayushjaiswal @mattshumer_ @eshamanideep @sreeramkannan @dvcoolster @nusimow @TeddySolomon11 @ashtoncofer @rvivek etc Drop your biggest engineering bottleneck below. I'll reply with how I'd attack it with Vorflux, and hand you $200 in free credits to bang out your backlog. Our full thesis 🧵👇

English
13
3
84
10.8K
flapstacks 🇺🇸
flapstacks 🇺🇸@codegraph·
x.com/doodlestein/st…
Jeffrey Emanuel@doodlestein

I really love graphs (it runs in my blood). You can model so many useful things as nodes and edges, and the edges can have weights or bundles of weights. The beauty of it all is that, as soon as you've done that, it doesn't matter what any of it represents in real life, you get to apply the full analytical arsenal of graph theory to everything, and all sorts of useful stuff can just "fall out." Detect cliques. Find the "Kevin Bacon" nodes in your data. Identify the bottlenecks. You can use it to find terrorist cells in phone metadata. You can figure out how to optimally parallelize workstreams to maximize the number of concurrent agents working on your project (like my bv tool does). Even if you don't have a natural notion of how to construct edges between nodes, you can synthesize one. Compute various forms of correlation or statistical dependency between time series and average the values; threshold on those and you now have a set of weighted edges. Now you can go nuts with graph theory. If you're interested in this stuff, you should check out my FrankenNetworkX library. I took what is by far the most complete, authoritative library in the world for doing graph-theory calculations, NetworkX, and implemented 100% of it in memory-safe Rust that I've been hyper-optimizing for the last few months in a constant cycle. It's all 100% conformance tested against the Python library, but runs anywhere from 5x to 500x faster! It's very easy to drop into your projects and give them superpowers. I've already used it in many of my own projects, including my eidetic_engine_cli (ee) long-context structured memory for agents.

ZXX
0
0
2
140
Jeffrey Emanuel
Jeffrey Emanuel@doodlestein·
I really love graphs (it runs in my blood). You can model so many useful things as nodes and edges, and the edges can have weights or bundles of weights. The beauty of it all is that, as soon as you've done that, it doesn't matter what any of it represents in real life, you get to apply the full analytical arsenal of graph theory to everything, and all sorts of useful stuff can just "fall out." Detect cliques. Find the "Kevin Bacon" nodes in your data. Identify the bottlenecks. You can use it to find terrorist cells in phone metadata. You can figure out how to optimally parallelize workstreams to maximize the number of concurrent agents working on your project (like my bv tool does). Even if you don't have a natural notion of how to construct edges between nodes, you can synthesize one. Compute various forms of correlation or statistical dependency between time series and average the values; threshold on those and you now have a set of weighted edges. Now you can go nuts with graph theory. If you're interested in this stuff, you should check out my FrankenNetworkX library. I took what is by far the most complete, authoritative library in the world for doing graph-theory calculations, NetworkX, and implemented 100% of it in memory-safe Rust that I've been hyper-optimizing for the last few months in a constant cycle. It's all 100% conformance tested against the Python library, but runs anywhere from 5x to 500x faster! It's very easy to drop into your projects and give them superpowers. I've already used it in many of my own projects, including my eidetic_engine_cli (ee) long-context structured memory for agents.
Jeffrey Emanuel tweet media
English
15
6
154
8.1K
flapstacks 🇺🇸
flapstacks 🇺🇸@codegraph·
I got an offer from a company in the middle of a raise. The offer is conditional on the raise. It could take a couple of months. I would discount this except I think the company has a no fail mission of supporting medically complex children. If you have any fractional work hmu
English
0
0
2
111
blobbert
blobbert@dumbgayretard·
I can’t stop laughing at how bad Anthropic has fucked themselves Absolute master class in being retarded and gay
English
7
3
156
6.1K
Samswara
Samswara@samswoora·
Airports are crazy put down a tarmac in a field and you can get anywhere in the world in less than 24 hours. Magic portals
English
4
1
80
2.6K
flapstacks 🇺🇸
flapstacks 🇺🇸@codegraph·
amazing how a conversation with a good recruiter can help you orient your career and a conversation with a bad recruiter makes you wish you picked a different career
English
0
0
1
129
Narco Rubio
Narco Rubio@sdwesternworld·
@codegraph @powerbottomdad1 That’s my winter rig. Mini wing holster. And the 509t is my favorite pistol I own. It’s a little big to conceal in summer in the Texas heat
English
1
0
1
29
sucks
sucks@powerbottomdad1·
goal this week is to buy a handgun. any reason to get any thing other than the sig sauer p365. if not what variant?
sucks tweet media
English
97
1
144
22.5K
flapstacks 🇺🇸
flapstacks 🇺🇸@codegraph·
@powerbottomdad1 Gen 6 glock 19 with Streamlight TLR-7 X and trijicon rcr in a tier 1 concealed holster and kore essentials belt in 5.11 apex pants with merino underwear shooting 124 grain speer gold dot
English
0
0
1
64
Jeffrey Emanuel
Jeffrey Emanuel@doodlestein·
2 Days. 2 Models (Fable xhigh and Sol Ultra) per project. 11 projects managed in a single ntm swarm by one Claude Code Fable driver. 2*11+1 = 23 full agent instances. Results? A lot of wild speedups, ranging from 2x to 72x.
Jeffrey Emanuel tweet media
English
7
4
73
6.4K

Keşfet

@BasedDaedalus @tapir_worf @doodlestein @ptichushka @twofifteenam @jk_drq @forloopcodes @graphtheory