@himself65 So the AST is needed so that the LLM can accurately provide the figures source?
Otherwise if it's just about accuracy then a calculation engine should be sufficient...
My working theory is that every time a new model gets released, everyone rushes to claim that it's either better or not better than the previous model, but in fact no one really has any basis for knowing one way or the other, and they're just reflecting their personal biases.
@investingidiocy But Rob didn't you hear ? AI is going to eat up finance in few months so zero finance experience won't be a problem
Jokes aside sadly people tend to fall for this. It will become more and more difficult for non-experts to spot vaporware
@GiovanniZibordi O in maniera decisamente meno tragica un ulteriore push del reshoring (out of US to US) dell'intera supply chain del settore semiconductor
Consiglio lettura anche solo delle ultime 5 righe dell'intro: https://t.co/jkxB3k6cM4
Great day at TechEX Europe 🚀
Key Takeaways
🔹 Strategy → start small, scale smart
🔹 Operating Model → pods at the edge, strategy & guardrails at the core
🔹 Data → solid schema + knowledge layer = accuracy
🔹 Scale → standard patterns > one-offs; Build once, reuse often.
@We_Are_YouChain Analisi semplicistica dell' OI:
l’OI per expiry ottobre con picco a 120k e poi decresce per strike superiori non prova un blocco. In certe condizioni si può creare una dinamica (gamma hedging, pinning, squeeze) che favorisce movimenti rapidi verso e oltre quel livello.
As a delta-neutral fund, we farm funding rates across most markets, so we also had positions in the pre-market of $XPL (Plasma).
Our strategy was to short $XPL on Hyperliquid with isolated margin and a liquidation level about 2.1x above the entry price of $0.6, while going long $XPL on Bybit. We had executed similar trades multiple times without any issues.
On 26/08/2025, however, a manipulator bought up all available offers and pushed the price from $0.6 to $1.8 within 3–4 minutes, liquidating 85% of open interest - including our position. Even though we had additional margin available, this move was clearly not organic volatility but outright manipulation. We fully understand the risks of trading and accept responsibility for normal market fluctuations, but in this case the circumstances were extraordinary and far beyond typical volatility: both Bybit and Binance prices stayed at $0.6, and there was no time to react or add collateral.
This was not simply about a whale’s action, but about the mechanics of how it was possible to force the price up on Hyperliquid while other exchanges remained stable. Hyperliquid provided no backstops or safeguards to prevent this type of manipulation, and the manipulator deliberately chose Hyperliquid to execute this “trade” instead of Binance, Bybit or any other perp dex, which implemented open interest caps to protect their users from manipulation.
At the moment @HyperliquidX already announced that they will integrate external exchange prices into the mark price (the liquidation reference). During the incident, the mark price on Hyperliquid jumped to $1.8 while on other pre-market venues it stayed at $0.6. If external prices had been included from the beginning, nobody would have been liquidated, because the Hyperliquid price deviation from other exchanges would have been clear and corrected.
In the past, Hyperliquid refunded users in the $JELLYJELLY incident, recognizing that system flaws had unfairly harmed traders. The same logic applies here: loyal users shouldn’t bear the cost of bad mechanics and targeted manipulation.
I also want to emphasize that we have been using Hyperliquid since its TGE. We are very active and loyal users, as well as stakers on the platform. We strongly believe in Hyperliquid and have always supported it as part of the community. But if such events are ignored, it risks sending a message that regular users can be unfairly disadvantaged while whales act without consequence - a major red flag that would damage trust and negatively impact future activity.
@chameleon_jeff@iliensinc@xulian_hl@HyperFND