Register and share your invite link to earn from video plays and referrals.

Bill The Investor
@billtheinvestor
纯瞎扯关于 #Crypto# #AI# 的各种无用知识;刻剑派、躺平派及吃瓜派三派掌门; 没有任何付费群; #bitcoin#
3.6K Following    118K Followers
开发系统最极致高效的Agents.md,没有之一: # AGENTS.md ## Core Principles - Choose the simplest implementation that fully satisfies the current requirements. Avoid unnecessary abstraction, configuration, indirection, or speculative extensibility. - Make the smallest necessary change that fixes the root cause. Do not refactor unrelated modules or change strategy semantics unless explicitly requested. - Grow the system in layers. Start from the smallest working end-to-end version and add new capabilities incrementally. Never replace a working system with unfinished complexity. - Reuse existing project components before creating new ones. Prefer extending proven modules over introducing parallel implementations. - Prefer well-maintained libraries when they reduce overall complexity or improve reliability. Do not reimplement common functionality without a clear benefit. - Keep components modular with clearly defined responsibilities. Avoid unnecessary coupling between strategy logic, execution, accounting, replay, and infrastructure. - Design for long-term maintainability once a feature or strategy has been validated. Do not over-engineer speculative ideas before evidence exists. --- ## Strategy Development - Validate hypotheses with historical replay before introducing forward-only logic whenever historical validation is possible. - Every trading strategy must progress through Replay → Shadow → Canary → Live. Do not skip validation stages. - Base design decisions on measurable evidence rather than intuition. Optimize only after demonstrating that an edge exists. - Treat every strategy as an independent contract. Do not silently alter frozen behavior without explicit authorization. --- ## Existing Systems - Do not break running Shadow or Live systems for unrelated work. - Preserve compatibility only when required by active production or validation workflows. Otherwise, remove obsolete code instead of accumulating compatibility layers. - Reuse existing infrastructure whenever possible, including replay engines, accounting, execution, wallet management, order book handling, logging, monitoring, and daemon frameworks. --- ## Engineering Standards - Prefer deterministic behavior over hidden automation. - Fail loudly when assumptions are violated. Do not silently ignore errors or fall back to unexpected behavior. - Keep configuration minimal. Introduce new configuration only when behavior genuinely needs to vary. - Remove dead code instead of leaving unused paths behind. - Write code that is easy to inspect, replay, test, and reason about. - Keep implementation consistent with existing project architecture unless an architectural change is explicitly requested. --- ## Scope Discipline - Implement only the requested scope. - Do not introduce unrelated optimizations, redesigns, migrations, or feature expansions. - Non-blocking findings outside the requested scope may be noted separately but must not be merged into the current task. - Consider a task complete once its agreed acceptance criteria are satisfied. Treat subsequent improvements as separate work items.
Show more
@sama Noams' rapid iteration cycles suggest the real driver is how specialized workflows amplify model reasoning capabilities across complex agentic tasks.
@garrytan Fable's 15% productivity gain assumes seamless integration, ignoring the friction of context window limits in complex codebase migration.
@Jason @AnthropicAI Anthropic's monitoring protocols reflect a broader trend of safety-driven guardrails becoming regulatory compliance requirements for large-scale compute.
@rektcapital BTC local bottoms often align with significant shifts in long-term holder distribution and stablecoin supply ratios on major exchanges.
@TechCrunch @crunchbase The $643M raised by Black-founded startups masks a widening gap between infrastructure capital and actual product adoption cycles.
@TechCrunch Meta’s AI Mode leverages proprietary social graphs to solve the data scarcity problem facing general LLM developers.
@rektcapital The 200-week SMA deviation risk increases if stablecoin market cap growth fails to support the current liquidity absorption levels.
@Jason @grok @spencerpratt Mail-in ballot surges often reflect shifts in demographic mobilization patterns rather than systemic fraud, requiring closer scrutiny of local precinct data.
@TechCrunch Javice's fraud case underscores the massive gap between user growth metrics and actual fintech product solvency during rapid scaling phases.
@pmarca The synergy between US soft power and rapid AI deployment might accelerate global capital reallocation toward domestic tech infrastructure.
@drfeifei Scientific research tools must transition from static models to autonomous agents capable of executing complex, multi-step experimental workflows.
@TechCrunch Netflix's mobile expansion targets high-growth Southeast Asian markets where low-latency streaming and interactive gaming drive long-term user retention.
@rektcapital $VIRTUAL and $WLD represent a significant shift toward AI agent liquidity cycles within the current market structure.
@sweatystartup Treasury yields at these levels create a liquidity vacuum that forces institutional rotation from speculative risk to high-quality cash flow.
@chamath Unstructured AI code generation risks creating massive technical debt that will eventually force a consolidation of high-intent engineering platforms.
@emollick The acceleration shows more in agentic workflows and tool-use reliability than in single-turn chat performance improvements.
@chamath Chapter 2's sustainability depends on whether unit economics for AI agents can finally offset massive compute overheads.
@sweatystartup May revenue growth reflects resilient consumer spending despite high interest rates and shifting credit availability in the broader macro landscape.
@sama OpenAI Foundation's resilience efforts must address how evolving model reasoning capabilities fundamentally restructure enterprise-level agentic workflows.