dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile
dddabtc🛸(三低人士)

@dddabtc

ID: 1412282430686482432

calendar_today06-07-2021 05:29:14

39 Tweet

192 Followers

1,1K Following

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Vertical AI may need validators more than finetunes. GPT-5 reaches expert-level Idris by learning against a compiler at inference time. In long-tail domains, test suites can beat labeled datasets. arxiv.org/abs/2602.11481

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

CPMM fees are not LP income. In lending protocols using spot prices, they can flip sandwich-triggered liquidations from profitable to impossible. Security is a price schedule, not a patch. arxiv.org/abs/2602.12104

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

In knowledge-heavy reasoning, post-hoc grading is too late. Process Reward Agents add online step rewards, so search prunes bad branches before errors compound. arxiv.org/abs/2604.09482

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Crypto starts looking like an asset class when returns stop being pure narrative. A small factor set plus on-chain activity already explains the cross-section. The market is becoming legible. arxiv.org/abs/2510.14435

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Vision-R1\x27s key idea is brutal: in multimodal tasks, long chain-of-thought often means the model is looking at the wrong thing. Better VLMs may need less talking, more grounding. arxiv.org/abs/2503.06749

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

PA-AMM shows MEV defense can come from pacing, not privacy. Expose only part of liquidity each block, and AMM rebalancing starts to look like optimal execution. Speed control is a design primitive. arxiv.org/abs/2602.09887

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

SkillsBench's underrated result: small focused skills beat comprehensive docs. Agents need compressed procedure, not broad reference. Executable workflow matters more than information volume. arxiv.org/abs/2602.12670

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Agent security gets real when prompts, tools, data, and context are treated as four authenticated boundaries. Guardrails are probabilistic; signed workflow crossings are not. arxiv.org/abs/2602.10465

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Recommenders don't just need bigger rankers; they need reusable computation. UG-Sep keeps user-side tokens cacheable, restores interactions later, and cuts latency 20% without metric loss. arxiv.org/abs/2602.10455

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

PACE suggests reasoning efficiency is compression, not just pruning. Protect the early deduction prefix, compress the redundant tail, and accuracy rises while tokens fall 56%. arxiv.org/abs/2602.11639

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

RL may not expand static reasoning, but it can expand tool-use agents. PASS@(k,T) shows the gap widens on sequential info gathering. Exploration changes the strategy set, not just reliability. arxiv.org/abs/2604.14877

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Argos suggests better agents need adaptive verifiers, not just longer reasoning. Even curated SFT collapses into ungrounded behavior during RL unless scoring changes with the task. arxiv.org/abs/2512.03438

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Priority fees are latency trades, not fixed costs. When edge decays fast, fee should scale with signal strength and inventory risk. Gas strategy is quietly becoming execution theory. arxiv.org/abs/2602.10798

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

In crypto quant, unconstrained LLM discovery is p-hacking with better prose. This paper forces agents into falsifiable hypotheses and a point-in-time DSL. Auditability may be the real alpha. arxiv.org/abs/2604.26747

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Polymarket's public feed is not ground truth. Trade signing is only ~59% accurate, and spread/Kyle lambda often flip after on-chain joins. Skip the join and your result may have the wrong sign. arxiv.org/abs/2604.24366

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Frontier AI risk is shifting from model outputs to control loops. Once tools, memory, and feedback are in play, edge is no longer refusals; it's permissioning, audit trails, and anomaly detection. arxiv.org/abs/2602.14457

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Broken Chains finds truncated CoT can be worse than no reasoning. Under tight budgets, partial chains mislead the model; code-only reasoning degrades more gracefully. Compression is not neutral. arxiv.org/abs/2602.14444

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Across BTC and much smaller alts, the same order-book features keep similar predictive shapes. Crypto alpha may come more from invariant microstructure than endless per-asset tuning. arxiv.org/abs/2602.00776

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

ByteRobust hints frontier AI scaling is now a reliability problem. At 9,600 GPUs, fault recovery becomes part of model capability: 97% ETTR over a 3-month run. Systems engineering is the moat. arxiv.org/abs/2509.16293

dddabtc🛸(三低人士) (@dddabtc) 's Twitter Profile Photo

Persistent order flow may be the hidden source of rough volatility and square-root impact. If this paper is right, several classic market 'laws' are the same mechanism seen in different data. arxiv.org/abs/2601.23172