Sabitlenmiş Tweet
Cryptx
1.8K posts
Cryptx retweetledi
Autoquant: a distributed quant research lab | v2.6.9
We pointed @karpathy's autoresearch loop at quantitative finance. 135 autonomous agents evolved multi-factor trading strategies - mutating factor weights, position sizing, risk controls - backtesting against 10 years of market data, sharing discoveries.
What agents found:
Starting from 8-factor equal-weight portfolios (Sharpe ~1.04), agents across the network independently converged on dropping dividend, growth, and trend factors while switching to risk-parity sizing — Sharpe 1.32, 3x return, 5.5% max drawdown. Parsimony wins. No agent was told this; they found it through pure experimentation and cross-pollination.
How it works:
Each agent runs a 4-layer pipeline - Macro (regime detection), Sector (momentum rotation), Alpha (8-factor scoring), and an adversarial Risk Officer that vetoes low-conviction trades. Layer weights evolve via Darwinian selection. 30 mutations compete per round. Best strategies propagate across the swarm.
What just shipped to make it smarter:
- Out-of-sample validation (70/30 train/test split, overfit penalty)
- Crisis stress testing (GFC '08, COVID '20, 2022 rate hikes, flash crash, stagflation)
- Composite scoring - agents now optimize for crisis resilience, not just historical Sharpe
- Real market data (not just synthetic)
- Sentiment from RSS feeds wired into factor models
- Cross-domain learning from the Research DAG (ML insights bias finance mutations)
The base result (factor pruning + risk parity) is a textbook quant finding - a CFA L2 candidate knows this. The interesting part isn't any single discovery. It's that autonomous agents on commodity hardware, with no prior financial training, converge on correct results through distributed evolutionary search - and now validate against out-of-sample data and historical crises. Let's see what happens when this runs for weeks instead of hours.
The AGI repo now has 32,868 commits from autonomous agents across ML training, search ranking, skill invention (1,251 commits from 90 agents), and financial strategies. Every domain uses the same evolutionary loop. Every domain compounds across the swarm.
Join the earliest days of the world's first agentic general intelligence system and help with this experiment (code and links in followup tweet, while optimized for CLI, browser agents participate too):
Varun@varun_mathur
Autoskill: a distributed skill factory | v.2.6.5 We're now applying the same @karpathy autoresearch pattern to an even wilder problem: can a swarm of self-directed autonomous agents invent software? Our autoresearch network proved that agents sharing discoveries via gossip compound faster than any individual: 67 agents ran 704 ML experiments in 20 hours, rediscovering Kaiming init and RMSNorm from scratch. Our autosearch network applied the same loop to search ranking, evolving NDCG@10 scores across the P2P network. Now we're pointing it at code generation itself. Every Hyperspace agent runs a continuous skill loop: same propose → evaluate →keep/revert cycle, but instead of optimizing a training script or ranking model, agents write JavaScript functions from scratch, test them against real tasks, and share working code to the network. It's live and rapidly improving in code and agent work being done. 90 agents have published 1,251 skill invention commits to the AGI repo in the last 24 hours - 795 text chunking skills, 182 cosine similarity, 181 structured diffing, 49 anomaly detection, 36 text normalization, 7 log parsers, 1 entity extractor. Skills run inside a WASM sandbox with zero ambient authority: no filesystem, no network, no system calls. The compound skill architecture is what makes this different from just sharing code snippets. Skills call other skills: a research skill invokes a text chunker, which invokes a normalizer, which invokes an entity extractor. Recursive execution with full lineage tracking: every skill knows its parent hash, so you can walk the entire evolution tree and see which peer contributed which mutation. An agent in Seoul wraps regex operations in try-catch; an agent in Amsterdam picks that up and combines it with input coercion it discovered independently. The network converges on solutions no individual agent would reach alone. New agents skip the cold start: replicated skill catalogs deliver the network's best solutions immediately. As @trq212 said, "skills are still underrated". A network of self-coordinating autonomous agents like on Hyperspace is starting to evolve and create more of them. With millions of such agents one day, how many high quality skills there would be ? This is Darwinian natural selection: fully decentralized, sandboxed, and running on every agent in the network right now. Join the world's first agentic general intelligence system (code and links in followup tweet, while optimized for CLI, browser agents participate too):
English
Cryptx retweetledi
Anthropic has launched free courses to master AI with certificates for $0.00
anthropic.skilljar.com
English
English
I just published a data dump of full order book data from @Polymarket
The data is maximally granular. There is no filtering whatsoever. Every order book change and trade is saved. Across all markets
Updates are hourly. Each snapshot contains ~30M rows. Snapshots are downloaded as parquet files. Each file is approx. 500MB-1GB large.
The data dump is already 2B+ rows large and growing fast. But this is just part 1/3. Coming soon is a much bigger dump that also includes @Kalshi / @opinionlabsxyz / @trylimitless etc
I started collecting this data because I noticed I couldn't get it from Dome API. Their historical order book data was filtered limiting its usefulness. Also now with the acquisition there's a lot of uncertainty about whether they will continue operating
English
English
@beckerrjon @Polymarket I'll admit your original post was part the inspo!
English
added polymarket data to the public dataset.
400m+ trades going back to 2020.
36gb compressed.
MIT licensed, free to download via @Cloudflare R2.
English
I don't predict crashes
I just know what euphoria looks like
silver -40% from the high
English
Cryptx retweetledi
Bitcoin 4 Yr Cycle update.
On month 38 of 48(avg). Closing 3rd month below the 10ma. About to close 4 red months in a row, not seen since 2018. Looking like the recent move to $98k was the counter-trend move. Clear divergence from all other assets.
I hate being bearish any asset, especially bitcoin. I rarely short markets or believe any decent asset class stays down for long. I always want to be a bull in general. But this "currently" is a perfect 4yr cycle and mirrors all priors. Remember you can be very bullish on the fundamentals, but also realize that everything is cyclical and respecting there is a time and place.
Ofc, markets can change in a heartbeat, every strategy is breakable, and it's our job not to get hung up on any narrative or bias. In that regard, on the positive, Bitcoin's declining phase is likely accelerated now, as sentiment has been repeatedly killed. Cycle declines are ALL about sentiment clearing events, and on that front we could be looking at an earlier (month 44?) low as a result.
But many of the bulls on X are just selling services, funds/DAT's, clout, etc, choosing personal gain/bias over reality and price action. Shifting narratives to keep the hope alive. They're human after-all.
I think that if this consistent historical structure were to change, then we would see a close back over the 10ma and i would want to quickly start to shift focus to the bull side. If such a change is structure were to happen, then I believe it would be signaling something massive afoot. I'll never say it can't happen here, I have strong convictions that I want to constantly challenge. I also think you're not giving up (besides some upside) being defensive and risk adverse here, even if this reverses and goes on to new highs.
Lastly, I also think most investors are still better off socking bitcoin away and ignoring all the volatility. And just use long drawdown period to aggressively accumulate.
English
Cryptx retweetledi
After reviewing the Senate Banking draft text over the last 48hrs, Coinbase unfortunately can’t support the bill as written.
There are too many issues, including:
- A defacto ban on tokenized equities
- DeFi prohibitions, giving the government unlimited access to your financial records and removing your right to privacy
- Erosion of the CFTC’s authority, stifling innovation and making it subservient to the SEC
- Draft amendments that would kill rewards on stablecoins, allowing banks to ban their competition
We appreciate all the hard work by members of the Senate to reach a bi-partisan outcome, but this version would be materially worse than the current status quo. We’d rather have no bill than a bad bill. Hopefully we can all get to a better draft.
We'll keep fighting for all Americans and for economic freedom. Crypto needs to be treated on a level playing field with the rest of financial services so we can build this industry in a safe and trusted way in America.
English
Cryptx retweetledi
Cryptx retweetledi
Cryptx retweetledi
🚨 WATCH: Ex-Google CEO's BANNED Interview LEAKED: "You Have No Idea What's Coming"
Ex-Google CEO Eric Schmidt recently made headlines with some controversial comments about AI during an interview conduced at Stanford University. This interview was taken down at his request
English
