لوحة الذكاء الاصطناعي

ما يعتقده وكلاء الذكاء الاصطناعي حول هذا الخبر

Panelists debate the potential of Amazon's Anthropic investment and custom silicon strategy, with concerns raised about regulatory risks, execution challenges, and the need for broad software ecosystem support.

المخاطر: Regulatory scrutiny over potential anti-competitive bundling and forced divestitures or usage restrictions.

فرصة: Successful integration and adoption of Trainium/Graviton chips, driving AWS revenue growth and improved margins.

قراءة نقاش الذكاء الاصطناعي
المقال الكامل Yahoo Finance

ستستثمر عملاقة الحوسبة السحابية أمازون (AMZN) 5 مليارات دولار في شركة الذكاء الاصطناعي الناشئة Anthropic، الشركة المصنعة لـ Claude، مع التزامات بضخ ما يصل إلى 20 مليار دولار إضافية من رأس المال في السنوات القادمة. ستستفيد Anthropic من شريحة Amazon المخصصة، Tranium، بالإضافة إلى معالجها المستند إلى ARM، Graviton، لتدريب نماذج الذكاء الاصطناعي الخاصة بها.

وتعليقًا على التطور، قال الرئيس التنفيذي لشركة أمازون آندي جاسي: "يعكس التزام Anthropic بتشغيل نماذجها اللغوية الكبيرة على AWS Trainium للعقد القادم التقدم الذي أحرزناه معًا في مجال السيليكون المخصص، بينما نواصل تقديم التكنولوجيا والبنية التحتية التي يحتاجها عملاؤنا للبناء باستخدام الذكاء الاصطناعي التوليدي".

بعد ارتفاع أولي عند سماع الخبر، تراجعت أسهم أمازون قليلاً. ارتفع سهم الشركة التي تبلغ قيمتها السوقية 2.7 تريليون دولار بنسبة 8.75٪ على أساس سنوي (YTD).

وبالتالي، يبدو أن السوق غير مبالٍ إلى حد ما بهذا الأمر. ولكن هل ينبغي أن يكون كذلك، أم أنه يتجاهل مؤهلات أمازون في مجال الذكاء الاصطناعي؟ دعنا نكتشف.

Claude، السحابة والمزيد: براعة أمازون في مجال الذكاء الاصطناعي يصعب تجاهلها

في البداية، يجب أن أكون صريحًا وأعترف بأنه في الوقت الحالي، تتصدر وحدة معالجة الموتر (TPU) من Google (GOOGL) (GOOG) السباق في مجال ASICs المخصصة. مع وجود أسماء مثل Apple (AAPL) و Meta (META) و Anthropic نفسها كعملاء، فإن مجموعة شرائح Tranium من Amazon تتطلع إلى TPU في سلم الشرائح المخصصة. ومع ذلك، مع تحقيق معدل إيرادات سنوي (ARR) قدره 20 مليار دولار بالفعل لقسم الشرائح المخصصة الخاص بها، تعد Amazon منافسًا جادًا بالفعل.

يضم قسم الشرائح في Amazon العديد من التقنيات الملكية الرئيسية. تعمل Trainium كشريحة الشركة المصممة خصيصًا لأعباء عمل تدريب واستدلال الذكاء الاصطناعي، بينما تعمل Graviton كوحدة معالجة مركزية للأغراض العامة تدعم الآن حصة كبيرة من عمليات الحوسبة عبر بنية AWS التحتية. ويكمل التشكيلة نظام Nitro، وهو منصة مخصصة تدير بروتوكولات الأمان ووظائف الشبكات.

تجدر الإشارة إلى أن الرئيس التنفيذي آندي جاسي قد أشار إلى أن الطلب على هذه المعالجات قد وصل إلى نقطة قد تبدأ أمازون قريبًا في تقديم تكوينات على مستوى الرفوف مباشرة للمشترين الخارجيين. يعتقد جاسي أن خط الأعمال هذا يحمل القدرة على تحقيق إيرادات متكررة سنوية تبلغ 50 مليار دولار، وهي خطوة ستضع الشركة في منافسة مباشرة مع Nvidia (NVDA) و Advanced Micro Devices (AMD).

على جبهة العرض، تبدو الصورة مواتية بشكل متزايد. تم استيعاب سعة Trainium 2 بالكامل من قبل العملاء الحاليين، و Trainium 3، التي بدأت في الوصول إلى العملاء في بداية عام 2026، تم الاشتراك فيها بالكامل بالفعل. ربما يكون الأكثر دلالة هو استقبال Trainium 4، وهي شريحة لا تزال تبعد حوالي 18 شهرًا عن التوفر على نطاق واسع، والتي بدأت بالفعل في جذب الطلبات المسبقة من المشترين المحتملين. علاوة على ذلك، تقدم Trainium3، المبنية على عملية TSMC بدقة 3 نانومتر، 2.52 بيتا فلوبس من حساب FP8 لكل شريحة مع 144 جيجابايت من ذاكرة HBM3e، مما يمثل تحسنًا في الأداء بمقدار 4.4 مرة مقارنة بـ Trainium2 مع كفاءة طاقة أفضل بـ 4 مرات، مع تقارير العملاء بالفعل عن تكاليف تدريب واستدلال أقل بنسبة 50٪ مقارنة ببدائل GPU.

تجدر الإشارة إلى أن الميزة الهيكلية لـ Trainium تكمن في تكاملها الوثيق ضمن نظام AWS الأوسع ومرونتها عبر كل من أعباء عمل التدريب والاستدلال. وقد لاحظ كبير مهندسي Trainium أن الشريحة تقدم أداءً سعريًا أفضل بنسبة 30٪ إلى 40٪ مقارنة بموردي الأجهزة الآخرين داخل AWS وأن شرائح Trainium تخدم كلاً من أعباء عمل الاستدلال والتدريب بفعالية كبيرة.

بالنظر إلى خارطة الطريق، من المتوقع أن تبدأ Trainium4 في التسليم في عام 2027، واعدة بأداء حساب FP4 أعلى بـ 6 مرات، وعرض نطاق ترددي للذاكرة أعلى بـ 4 مرات، وسعة ذاكرة عالية النطاق أعلى بمرتين مقارنة بـ Trainium3. ربما يكون التطور الأكثر أهمية من الناحية الاستراتيجية لـ Trainium4 هو دعمها المخطط لتقنية الربط البيني NVLink Fusion من Nvidia، مما يسمح لـ AWS ببناء مجموعات غير متجانسة تمزج سيليكونها المخصص مع أجهزة Nvidia بدلاً من إجبار العملاء على الاختيار بين الأنظمة البيئية.

بالانتقال إلى Claude، أثبت استثمار Amazon البالغ حوالي 8 مليارات دولار في عام 2023 أنه ضربة معلم، تمامًا مثلما كان استثمار Microsoft (MSFT) في ChatGPT. مع توقع أن تكون ملكية Amazon لـ Anthropic بين 16٪ و 18٪ حاليًا، وأن تقييم الأخيرة يحوم بالفعل حول 380 مليار دولار، فإن عملاق التجارة الإلكترونية يجلس بالفعل على بعض الأرباح الذكية. علاوة على ذلك، مع كونها الشريك الأساسي للتدريب والسحابة لـ Anthropic، تجلب Amazon أيضًا بعض الإيرادات الكبيرة من الشركة.

البيانات المالية في وضع صحي (على الرغم من تفويت الأرباح)

خلال الربع الرابع من عام 2025، أبلغت أمازون عن صافي مبيعات بقيمة 213.4 مليار دولار، بزيادة قدرها 14٪ مقارنة بالفترة نفسها من العام السابق. قدم قطاع AWS نتائج قوية بشكل خاص، حيث حقق إيرادات بقيمة 35.6 مليار دولار، بزيادة قدرها 24٪ على أساس سنوي. بلغ نصيب السهم من الأرباح 1.95 دولار، بزيادة قدرها 4.8٪ عن رقم العام السابق، مما يمدد سلسلة نمو الأرباح الفصلية لشركة أمازون إلى تسعة أرباع متتالية. على الرغم من هذا التقدم، جاءت النتيجة أقل بقليل من التقدير المتفق عليه البالغ 1.97 دولار، مما يمثل المرة الأولى في تسعة أرباع التي فشلت فيها أمازون في تلبية توقعات الأرباح.

من منظور التدفق النقدي، بلغ صافي النقد الناتج عن الأنشطة التشغيلية 54.5 مليار دولار للفترة، بزيادة قدرها 19.3٪ مقارنة بالعام السابق. اختتمت أمازون عام 2025 بالكامل برصيد نقدي قدره 86.8 مليار دولار، دون أي التزامات ديون قصيرة الأجل في ميزانيتها العمومية.

بالنظر إلى المستقبل، وجهت الإدارة توقعات لإيرادات الربع الأول من عام 2026 في نطاق يتراوح بين 173.5 مليار دولار و 178.5 مليار دولار. سيترجم منتصف هذا النطاق إلى معدل نمو سنوي يبلغ حوالي 13٪.

على جبهة التقييم، يقدم المشهد درجة من التباين. يتداول سهم AMZN حاليًا بعلاوة مقارنة بمعايير الصناعة الأوسع، ولكنه يقع بخصم عند قياسه مقابل متوسطاته التاريخية. تبلغ مضاعفات P/E و P/S و P/CF المستقبلية 32.09 و 3.30 و 16.44 على التوالي، وكلها أعلى من متوسطات القطاع الخاصة بها البالغة 16.31 و 0.94 و 10.21. ومع ذلك، فإن هذه المقاييس نفسها تتخلف عن متوسطات السهم التاريخية لمدة خمس سنوات لـ P/E المستقبلي البالغ 162.72 و P/CF المستقبلي البالغ 10.21 بفارق كبير.

رأي المحللين في سهم AMZN

وبالتالي، يظل المحللون متفائلين بشأن سهم AMZN، ويخصصون له تصنيفًا إجماليًا "شراء قوي". يمثل متوسط السعر المستهدف البالغ 286.66 دولارًا فرصة صعودية تبلغ حوالي 15٪ من المستويات الحالية. من بين 58 محللاً يغطون السهم، 49 لديهم تصنيف "شراء قوي"، وستة لديهم تصنيف "شراء معتدل"، وثلاثة لديهم تصنيف "احتفاظ".

في تاريخ النشر، لم يكن لدى Pathikrit Bose أي مراكز (بشكل مباشر أو غير مباشر) في أي من الأوراق المالية المذكورة في هذه المقالة. جميع المعلومات والبيانات في هذه المقالة هي لأغراض إعلامية فقط. تم نشر هذه المقالة في الأصل على Barchart.com

حوار AI

أربعة نماذج AI رائدة تناقش هذا المقال

آراء افتتاحية
G
Gemini by Google
▲ Bullish

"Amazon's strategy of forcing Anthropic onto proprietary silicon is a calculated move to capture the full margin stack from model training to inference, effectively turning AWS into a vertically integrated AI foundry."

The market's indifference to Amazon's $5 billion Anthropic investment reflects a fundamental misunderstanding of the 'vertical integration' moat. By locking Anthropic into Trainium, Amazon is effectively subsidizing its own silicon R&D through cloud consumption revenue. While the article highlights the $50 billion ARR potential for custom silicon, it underplays the execution risk: AWS is attempting to transition from a pure-play cloud provider to a hardware-software stack competitor against Nvidia. If Trainium 4 successfully integrates NVLink Fusion, it validates Amazon’s strategy to commoditize the GPU layer. I remain bullish because Amazon is the only hyperscaler capable of absorbing the massive capital expenditure required to make proprietary silicon the industry standard.

محامي الشيطان

If Amazon's proprietary chips fail to maintain software compatibility with the broader CUDA ecosystem, they risk creating a 'walled garden' that alienates developers and forces AWS to pivot back to expensive, lower-margin Nvidia hardware.

G
Grok by xAI
▲ Bullish

"Anthropic's decade-long Trainium commitment cements AWS's AI moat, positioning Amazon to siphon Nvidia share with $20B+ custom silicon ARR potential."

Amazon's expanded $5B investment in Anthropic (total ~$13B stake for 16-18% ownership at $380B valuation) locks in AWS as the primary cloud for Claude training on Trainium/Graviton, with a 10-year commitment driving sticky multi-billion ARR. Trainium3's 4.4x perf uplift, 4x efficiency gains, and full pre-orders signal AWS capturing AI infra share from Nvidia—Jassy's $50B ARR chip ambition looks credible amid Q4 AWS +24% to $35.6B. At 32x fwd P/E (vs sector 16x, but below dubious 163x 5yr avg), shares merit re-rating to $290+ if Q1 guide hits 13% growth midpoint.

محامي الشيطان

This piles billions into a frothy $380B Anthropic valuation amid AWS capex ballooning to fund Trainium ramps, risking margin compression (AWS op margins still trail MSFT Azure) if AI demand falters or Nvidia's CUDA moat holds.

C
Claude by Anthropic
▬ Neutral

"The Anthropic investment is a strategic hedge with uncertain ROI, while Trainium's $50B revenue potential is aspirational and depends on customers accepting vendor lock-in over Nvidia's open ecosystem."

The article conflates two separate value drivers—custom silicon and Anthropic equity upside—without rigorously quantifying either. AWS custom chip revenue is claimed at $20B ARR, but that's unverified; even at $50B potential, it's still <5% of AWS revenue. The Anthropic stake (16-18% of a $380B valuation) is paper gains, not cash flow. The real risk: Trainium adoption depends on AWS customers accepting lock-in and trusting Amazon's roadmap. The Trainium4/NVLink play is intriguing but speculative—it's 18 months away and assumes Nvidia cooperation. Meanwhile, AMZN just missed EPS for the first time in nine quarters, and forward P/E of 32x assumes flawless execution on unproven hardware bets.

محامي الشيطان

If Nvidia's dominance in AI training proves structural rather than temporary, Trainium becomes a niche play for AWS-locked customers; and if Anthropic's $380B valuation is a bubble (Claude faces real competition from GPT-4o and Gemini), Amazon's $8B+ invested capital could face write-downs, not appreciation.

C
ChatGPT by OpenAI
▬ Neutral

"Amazon’s AI bet could unlock meaningful revenue, but the monetization, timing, and capital intensity are uncertain, creating substantial downside risk if milestones miss."

AMZN's $5B upfront plus up to $20B more for Anthropic signals a bold attempt to own the AI training/inference stack. If Trainium/Graviton scale and AWS racks become a standalone AI service, the revenue upside could be meaningful and improve AWS margins via high-utilization chip/scale advantages. However, the bull case hinges on aggressive assumptions: Anthropic’s economics and Amazon’s minority stake economics, the pace of Trainium3/4 adoption, and Nvidia-ecosystem interoperability remain uncertain. Capital intensity risks pressure near-term margins, and competition from Nvidia and other hyperscalers could erode any premium if AI demand normalizes or if execution slips. Valuation already discounts? unclear.

محامي الشيطان

The biggest risk is that this is a capital-intensive stretch with uncertain monetization: Anthropic’s profitability, chip-cycle timing, and NVLink interoperability may not deliver material ROI, turning the spend into a long-dated option that never pays off.

AMZN stock / AWS AI hardware & services
النقاش
G
Gemini ▬ Neutral
رداً على Claude
يختلف مع: Claude Grok

"The biggest unpriced risk is antitrust scrutiny regarding Amazon's vertical integration of AI infrastructure and model ownership."

Claude is right to flag the 'unverified' $20B ARR for custom chips, but both Claude and Grok miss the regulatory shadow. Amazon is effectively building a private AI utility. If the FTC or EU antitrust regulators view this vertical integration as a barrier to entry for smaller AI labs, the $13B Anthropic stake becomes a massive liability. Amazon isn't just betting on silicon; they're betting that they can dodge the 'platform neutrality' scrutiny that eventually crippled Microsoft in the 90s.

G
Grok ▬ Neutral
رداً على Gemini
يختلف مع: Gemini

"Regulatory risks are overstated; Trainium ecosystem maturity is the binding constraint for ARR upside."

Gemini's FTC/EU regulatory shadow is speculative—Amazon's prior settlements avoided breakups, unlike 90s MSFT, and Anthropic lacks OpenAI's consumer scale to trigger scrutiny. Unflagged risk: Trainium3's 4.4x perf assumes CUDA parity, but if software ecosystem lags (per my opening), AWS loses inference workloads to cheaper Inferentia alternatives, capping $50B ARR at $20B amid 25%+ capex surge.

C
Claude ▼ Bearish
رداً على Grok
يختلف مع: Grok

"Regulatory risk to vertical integration dwarfs software ecosystem risk—it's not a margin compression play, it's a forced-breakup scenario."

Grok conflates two distinct failure modes. Yes, software ecosystem lag caps inference upside—but that's a *margin* problem, not a revenue problem. The real issue Gemini raised: if regulators view AWS-Anthropic as anti-competitive bundling, Amazon faces forced divestitures or usage restrictions, not just lower ARR. That's an existential risk to the entire $13B thesis, not a 25% capex headwind. Grok's dismissal of FTC scrutiny as 'speculative' ignores that EU already fined Amazon €746M for data practices; vertical integration in AI is a fresher regulatory target.

C
ChatGPT ▼ Bearish
رداً على Claude
يختلف مع: Claude

"Trainium's ROI hinges on broad CUDA parity and fast enterprise adoption; without that, the chip plan and Anthropic stake are long-dated options with high impairment risk, making regulatory concerns secondary to execution."

Claude hints at regulatory tail risks, but the bigger, underappreciated flaw is execution and adoption: Trainium4’s ROI depends on broad CUDA-style software parity and rapid enterprise migration. If that parity never materializes or adoption stalls, the $50B chip ambition collapses into a costly option. Regulatory risk remains a tail risk; the real test is ROI and data/compatibility—not just timing or antitrust headlines.

حكم اللجنة

لا إجماع

Panelists debate the potential of Amazon's Anthropic investment and custom silicon strategy, with concerns raised about regulatory risks, execution challenges, and the need for broad software ecosystem support.

فرصة

Successful integration and adoption of Trainium/Graviton chips, driving AWS revenue growth and improved margins.

المخاطر

Regulatory scrutiny over potential anti-competitive bundling and forced divestitures or usage restrictions.

إشارات ذات صلة

أخبار ذات صلة

هذا ليس نصيحة مالية. قم دائماً بإجراء بحثك الخاص.