Co-founder of @open_rpc, prev: @etc_core, @consensys, @cellarius2084 and others... | Open Source acolyte
Joined August 2011
- Tweets887
- Following1.3K
- Followers402
- Likes2.5K
seeing all this jev @typesafeai stuff makes it feel as though it's kind of a static world model where there's some probability given to each prediction, I wonder if there's a way to make this smaller and realtime update weights to shift probabilities...
1
75
Pretty interesting, it's kind of an experiment in visualizing qwen's "perception of the internet" as determined by consumed content ๐ค
you can just hallucinate the entire internet with Qwen 3.8 27b running at 2,000 tokens/second?
part 2 of turning @cerebras + @Alibaba_Qwen 3.8 27B into an OS:
built an offline browser with zero network calls and mounted it directly the JIT ubuntu desktop.
no wifi. no scraping. zero packets sent to external CDNs.
you search a site, set a year, and qwen 27b at 1,950 tok/s synthesizes the entire DOM on the fly.
here is youtube in 2045 vs 1999:
โ search google for youtube inside the OS
โ scrub to 2045: instant futuristic feed
โ scrub to 1999: raw web 1.0 time capsule in seconds
at this speed, browsing isn't retrieving files from a server, it's querying an alternate reality.
a 2D browser window is just step zero.
imagine full operating systems, virtual worlds, and complex simulation engines existing purely as model weights. zero gigabytes stored on disk, just pure interactive reality streamed on demand.
What else becomes a possibility with the qwen 3.8 27b (dense) at 2000 tokens/sec?
1
61
Was talkin w/ @shanejonas, astra gens a ton of tests. My approx. for program complexity is 2^num_options, you prolly need 2^options test. It's too many. A sol. just have fuzzing tests and critical test. Don't review fuzz test, keep them, they're good to have, review crit test.
1
2
58
This is an interesting take on the various crypto legislation being passed and how the future of the dollar is changing
The secret fight over Dollar 3.0 is happening RIGHT NOW in Congress.
Most people will sleep through itโฆ
and wake up in 2035 wondering why their money works completely differently.
Hereโs exactly whatโs on the table. โ
Dollar 1.0 = gold & silver
Dollar 2.0 = bank IOUs (your checking account)
Dollar 3.0 = tokenized, always-on, borderless USD
Weโre deciding its final shape in the next 6โ12 months.
This is bigger than the entire @federalreserve put together.
1/10 ๐งต
2
69
I think this ๐ฏ , I think crypto stays insular and doesn't reach, because of the culture and this docuseries can help change that. I'd be excited to watch it!
If we are to onboard and welcome the next billion participants to @ethereum, we need to produce content that is ๐๐พ
free of jargon
amplifies diverse voices/experiences
meets ppl where theyโre at
moves away from hype x pseudo celeb driven content
is entertaining and
accessible
1
90
Creating benchmarks for multiturn data is a bit tricky, I find myself thinking about data in โช, working from the result to question or entrypoint, to then try and train the llm to go in the forward direction ๐
1
86
โก๏ธwhen we gen. code w/ prompts we're, really creating iterative prompts that work around the limits of transformer attention, by storing context out of band in the form of code edits. Then we prompt again with a fresh improved context via static analysis.
1
3
113
Waging "war" on our own people in LA and other cities with ICE, and then bombing Iran without cause, this administration can do better, the US and world deserve better than this.
2
154
I like the idea of this but for code, and maybe you could take incremental commits to build a world model for code. Then we wouldn't need to bootleg it each time as we prompt in claude/gpt etc... . It would be able to predict the future impact of code changes aka architect
Introducing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction.
V-JEPA 2 can enable zero-shot planning in robotsโallowing them to plan and execute tasks in unfamiliar environments.
Download V-JEPA 2 and read our research paper โก๏ธ ai.meta.com/vjepa/
2
147
๐Super cool donation opportunity, a friend of mine is going to the Derby World Cup with an Indigenous Rising, a flat track roller derby team representing Native America, First Nations, and Polynesia gofundme.com/f/help-kristinaโฆ
2
82
๐ check it out pretty dope, could use it to preload an execution env. so an llm can generate code to interact in it. Offhand it could do interesting things in a custom user based env. A way to give llms async worker lvl access in a sandbox, it could read s3 direct even...
I made an Open Source MCP Server to run javascript inside a sandbox .
It uses SES (Secure Ecmascript) you haven't seen it, an Apache 2.0 licensed javascript sandbox from agoric.
It is also the underlying tech to securely sandbox metamask snaps.
github.com/shanejonas/javascโฆ
1
118
๐ญMakes me think of what the limits are, a neural interface, and that limit is not speed of thought, but speed of thought prediction.
I.e. don't wait for the thought, predict the most likely next thoughts and act on those so it feels beyond instant...
This quoted post is unavailable.
55
๐คIf you're sleeping on structured data in the llm, with models post 24' json schema is your prompting friend, it's terse and precise, and tool call friendly. Highly recommend ๐
38
Just been playing with that meta alpha fine tuning api, I think the biggest take away is how generic and yet seemingly effective their evaluator/scorer is , you only get 3 options, but seems to be pretty effective. I'm only cpl hours in though :D so we shall see ๐
47
๐ค It's interesting youtube.com/watch?v=EPyyyB23โฆ I what's missing is a "user testing" dept. agent, it just runs the software says what doesn't work, via a user testing script and makes those tickets to get picked up by copilot
70
๐ฝSimulation is wildly important, I've been generating synthetic data to build systems lately. I'm pretty sure syn data is what we'll engage w/ most of the time in the near future it's pretty wild ๐๏ธ
39
Using at @DSPyOSS it becomes clear there are prompting architectural decisions to make, really not that different than choosing how you structure a neural net ๐ง
1
56
๐กCode is more disposable now, LLMs `rm -rf` the cost of temporal software - dashboards, instrumentation, 15 secs vs 2-3 weeks for something you can't necessarily justify time allocation for but would make your long term software better.
2
50
