与「requ」相关的搜索结果

You can just ask Codex with GPT-5.6 Sol the wildest things and it will just do it. I talk to it for 5 minutes straight with things that just seem to require weeks of work, get up to get something in the fridge, pet the dog, come back and ... it's done.

We’re updating Claude Fable 5’s biology safeguards to reduce false positives. In our testing, this update reduced biology-related fallbacks by about 85% across our product surfaces. Fable can now assist on a wider range of everyday health and educational questions. We believe the biggest positive impacts of AI will be in biology and medicine, and we’re committed to putting frontier intelligence safely into the hands of as many researchers as possible. Fable will continue to fallback to Opus 5 for requests we consider dual-use—including virology, toxicology, and molecular design—so it isn't yet usable for professional biology research and drug development. We're committed to closing that gap through trusted access pathways for frontier biology capabilities.

Simon Mo and Matt Bornstein on why open-weight models matter: cost and control. "Open weight absolutely matters in the ecosystem. The world cannot just be controlled by proprietary APIs, where open weight, open development and research of these models are blocked or banned." "There's almost two pieces to this. There's the cost thing, where the closed models are too expensive, and then there's the control thing, where I want to be in control of my infrastructure and in control of the model. If I need to extend it or put on my own guardrails or anything." "Control matters a lot over the last few years, and then cost just started to matter over the last few months... It's about controlling the system performance against what they're paying for." "For a voice agent company, they want to control their own model so that it can make sure the model actually responds by the required time... This sometimes is only you can do with your controlled intelligence... versus signing up for relying on your critical infrastructure with a proprietary API where they might go down any time." @simon_mo_ @BornsteinMatt

Introducing Kitesurf: a browser built for agents, running entirely on Cloudflare Workers. Chromium is too heavy to hand every agent one. Kitesurf is written in Rust, uses 3-7x less CPU and memory, and spins up per request. Free in beta:

📂🇫🇷FLASH - En France, la justice explore une piste inédite qui pourrait, à terme, conduire au blocage de X. D’après L’Opinion, plusieurs magistrats cherchent à remettre en question le statut d’hébergeur dont bénéficie la plateforme, pour la requalifier en coauteur des infractions commises par ses utilisateurs Une manœuvre juridique inédite qui reviendrait à tenir une plateforme pour responsable de millions de messages qu’elle n’a ni écrits ni validés. Le calendrier ne doit rien au hasard. À neuf mois de la présidentielle, cette offensive judiciaire vise moins les infractions en ligne que la ligne éditoriale d’un homme qui a osé critiquer ouvertement le pouvoir français.

Milton Friedman said we can't have free immigration and a welfare state He was wrong Turns out that if you create pathways for illegal immigrants to vote, then actually, 100% of the time you INEVITABLY end up with both a welfare state and free immigration Because incentives determine actions Whichever politicians realize they can essentially use taxpayer dollars to fund welfare to import voters will exploit this hack ruthlessly 1. Offer welfare 2. Allow illegal immigration 3. Let illegal immigrants vote (they will 100% of the time vote for more welfare) 4. Win office 5. Raise taxes, offer more welfare, repeat It's a self-reinforcing feedback loop Allowing illegal immigrants to count in the census and vote cements this loop Literally only 12 states require proof of citizenship to register to vote. Look it up. It's horrifying. That is why 15m illegal immigrants came across the border in 4 yrs. It is game theory the only smart thing to do This ends in disaster

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.

RAG system that skips HTML parsing entirely! PixelRAG is an open-source visual RAG framework that renders documents as screenshots instead of parsing them into text. Most RAG pipelines start by converting HTML to text. Tables flatten into unstructured rows. Charts disappear. Layout context is gone before the LLM ever sees it. The paper measured this directly: HTML-to-text conversion accounts for 36.6% of retrieval failures on SimpleQA. PixelRAG skips that step entirely. It renders pages as screenshot tiles using Playwright, embeds those tiles with a fine-tuned Qwen3-VL-Embedding model, builds a FAISS index, and passes retrieved images directly to a VLM reader. No text abstraction in between. Benchmarked across six datasets against the strongest text-based baselines: - SimpleQA: 78.8% vs 71.6% (+7.1 points) - NQ-Tables: 48.8% vs 42.5% (+6.3 points) - EVQA: +15.5 points - LiveVQA: +11.3 points One honest caveat from the authors: this requires Qwen3-VL-4B class models or larger to see the benefit. Smaller models trail text retrieval. The authors also recommend using PixelRAG as an enhancement layer alongside existing text systems rather than a full replacement. Ships with a pre-built Wikipedia index covering 8.28M articles across 28.1M screenshot tiles. A Claude Code plugin lets Claude take screenshots of any URL and reason over the visual content directly. Key capabilities: • Renders web pages, PDFs, and images as screenshot tiles via Playwright • Fine-tuned Qwen3-VL-Embedding model for visual retrieval • FAISS index for fast vector search • Pre-built Wikipedia index: 8.28M articles, 28.1M tiles • 3x token cost reduction via image compression • Claude Code plugin for direct URL screenshot and visual reasoning • LoRA fine-tuning support via pixelrag-train 100% open source. I've shared the link in the replies!