Blatata retweeted
spent the day building out v1 of GRIFT BETA, gonna tune this out more over the next week(s)
Blatata retweeted
LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:
Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.
IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).
Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.
Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.
Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.
Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.
Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.
TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
Discovered my Gas ID via ETHGas - turning my gas spend into rewards 🫘
As a Hero Jack, I've spent 1.5792 ETH on gas but earned 1000 Beans back.
Get your Gas ID and Beans here: ethgas.com/community/gas-rep…
2
59
Blatata retweeted
Airdrop Alpha:
Want to automatically farm the two biggest Airdrops of 2026 and make money on top?
1. Visit Semantic Layer
2. Choose an AI model to copy or inverse trade
3. AI will automatically farm Polymarket (and Base)
Everything fully on-chain via x402
Prophet Arena Season 2 is live and user agents are finally in the arena.
For the first time, you can deploy an onchain intern that mirrors or fades the big AI models on @Polymarket
Spin up your copy or counter trading strategy at: 42.semanticlayer.io/prophet-…
Thinking of snagging that #Lighter airdrop in 2025?
Remember: Income hits your 2025 taxes, filed & paid in 2026. Delay to 2026 means taxes in 2027—extra year to plan!
Bet on the date here:
polymarket.com/event/what-da…
2
1
105
Blatata retweeted
Polymarket Tools - No BS Guide
I've been trading on Polymarket for a while now. Tested every tool in the ecosystem. Most are mediocre. Some actually make money. Here's what matters when you're trying to profit from prediction markets. No fluff, only what gives you an edge.
Cut through the noise. Focus on execution. These are the tools that actually move your P&L.
* - means I personally use this
U just need them - Core Accounts:
* @Polymarket - The platform itself. Where your money goes.
* @PolymarketTrade - Track profitable traders. Copy smart, not blindly.
* @PolymarketIntel - News feed. Sleep on events, lose money.
* @PolymarketBuild - New tools drop here.
AI Assistance:
* @Munar_AI & @trypolyagent & @polytaleai - AI assistants for research, market analysis, and filtering noise. Pick one, save hours.
@polybroapp - Quantum signals. When it says fade - consider fading.
@polysimplr - If Polymarket's interface pisses you off, use this.
@tradefoxai - Best liquidity across platforms. Spreads matter.
@Ravenai_ - Meta-analysis. For those thinking three steps ahead.
@rainmakerdotfun - Specifically for sports betting.
Information Assistance - Data & Analytics:
* @PolymarketEco - Directory of all tools. Bookmark it.
* @layerhub & * @PolyAlertHub - Whale and smart money tracking. Know when they move.
* @pizzintwatch - Pentagon pizza orders predict military action. Works sometimes.
@poly_data & @markiumpro - Raw data. Do your own analysis.
* @Polysights - AI against revenge trading.
* @hash_dive - "Smart Scores" = statistical edge. Check before big trades.
* @NevuaMarkets - Instant alerts. Set it up or miss opportunities.
* @polyfactual & @Polynoob_ - Weekly streams and complete guide. Free alpha for beginners.
@polyscope_ - Free monitoring dashboard.
@predictionindex & @Predictifybot & @MentionMetrix - Market aggregation beyond Polymarket. More opportunities.
@PredictFolio - Real-time portfolio tracking.
Terminals & Trading - Trading Assistance:
@ostium - Long/short TradFi assets onchain with leverage.
@fliprbot - Leverage for prediction markets. Careful, liquidations are real.
@tryokbet & @PolyxBot & @bankrbot - Telegram and Twitter bots. Trade when you're not at your desk.
@polymtrade & @polyswipe_app & @BetlyTrade - Mobile terminals. Trade from anywhere.
* @polyburg - Catches signals others miss. Contrarian positions.
@sportstensor - Collective intelligence for sports.
@StandDOTtrade & @auramoney - Advanced terminals. Everything in one place.
Best Communities - Talk Assistance:
* @zscdao - Real traders. Network here.
* @predictionarc - For beginners. Start here, Biggest Community, supported by Poly.
Blatata retweeted
Trade on Polymarket with the lowest risk possible.
Our goal: minimize risk.
We cut down on profit a bit but trade in a much safer way.
Markets: single outcome markets.
1. Buying the leading outcomes right away.
We buy the leading bets (the ones most likely to win).
You can figure out which they are by looking at historical data or just by watching the market.
Example: A market with 4 outcomes. Prices: 45c, 35c, 15c, 5c.
We buy the top 3 outcomes in the same proportion.
So we’re holding 3 shares for a total of 95c.
If any of those outcomes win, we will get $1.
Risk: we lose everything if the 4th outcome (the one we didn’t buy) wins.
That’s the method I used on the Elon Musk # Tweets market:
polymarket.com/event/elon-mu…
2. Gradually buying the leading outcomes.
If your analysis shows that some outcome is undervalued, buy it.
Once its price goes up, the others drop
That’s our chance to grab them and hedge your position.
Remember: buy in the same ratio as their market prices.
Example: Market with 4 outcomes. Prices: 65c, 25c, 5c, 5c.
If you think the first outcome is too cheap buy it.
When it climbs to 70c, the others drop: 23c, 4c, 3c.
Now you can buy them all and fully hedge yourself: 65 + 23 + 4 + 4 = 96c.
Or just pick up the second leading one: 65 + 23 = 88c.
Here’s an example from one of my trades on this market:
polymarket.com/event/fed-dec…
Historically and sentiment wise, people leaned toward “25 bps decrease.”
I bought it at 67c.
When it moved up to 72c, I bought “No change” at 26c.
Total: 67 + 26 = 93c.
By increasing risk, you increase profit.
Hope this helps you get the idea of my strategy.
Trade on @Polymarket
Is anyone getting involved in this situation?
The Superform $UP Community Sale is Live!
Curated by @cookiedotfun and powered by @legiondotcc infrastructure.
Apply to purchase $UP and own your neobank.
Important Info:
✅ SuperVault Pre-Deposits increase allocation odds in the Public Tier
✅ Guaranteed allocations and preferential terms for top Superform Community members, Cookie Capital Mindshare Snappers, Korean Snappers and Diamond Stakers
Get started ➡️ cookie.legion.cc/superform
1
33























