Skip to main content
Back

Anthropic Opus Advisor cuts agent costs 12% with auto-escalation

OpenAI's new $100 plan, Anthropic's Claude can now run scripts in background, Perplexity adds Plaid API.

April 10, 2026 4 min read

Hey,

Your daily briefing is ready. You can finally take a break from the AI firehose.

Our algos spent the night splitting signal from noise and pulled the top news, models, papers, and repos.

Here’s the must-read:

Together with:
Sponsor Logo
Summary

Read time: 4 min 36 sec

Top News

▸ Anthropic enables smaller models to escalate tasks to Opus on demand

Lambda

▸ Increase MFU beyond 60% by fixing memory and parallelism inefficiencies

Top News

▸ OpenAI adds $100 Pro plan for sustained high-effort coding sessions with Codex

Fuel iX by TELUS Digital

▸ Learn how to defend LLMs against prompt injection attacks effectively

Top Paper

▸ Meta debuts Neural Computer that learns computation from interaction data

Signals

▸ Anthropic equips Claude to run background scripts and wake on events
▸ Perplexity expands Computer with Plaid for financial analysis and tools
▸ Cursor enhances PRs with agent-generated demos and visual artifacts
▸ Augment Code announces a 90-minute AI coding challenge with live reveal
▸ Google introduces ConvApparel dataset to measure realism gap in simulators
Author photo
Today's Author
Lior Alexander. Founder of AlphaSignal and former ML Engineer. Previously built ML systems at Iguazio, Guesty, Enphase, Mila.
Top News
Anthropic introduces an advisor tool that lets smaller models call Opus only when needed during agent execution
33,539 Likes
Grok 4 Fast Benchmark

Anthropic adds the advisor tool to the Claude Platform to simplify a common agent pattern.

You run Claude Sonnet or Claude Haiku as the main agent, and bring in Claude Opus only for harder decisions. This setup keeps most execution at lower cost while still using a stronger model when reasoning becomes difficult.

How it works

The executor model runs the task end-to-end and calls the advisor when needed.

  • Executor handles tools, steps through tasks, and produces final outputs directly
  • Advisor reads shared context and returns a plan or correction, then exits
  • Advisor does not call tools or generate user-visible responses during execution
  • Entire interaction runs inside a single API request without external orchestration

Results and performance

Anthropic reports gains across benchmarks with lower cost per task.

  • SWE-bench Multilingual increases by 2.7 points over Sonnet alone
  • Cost per task reduces by 11.9% compared to Sonnet-only execution
  • Haiku improves from 19.7% to 41.2% on BrowseComp with advisor enabled
  • Haiku setup remains 85% cheaper than Sonnet for comparable workloads

How to use it

You add the advisor tool directly in your API call.

  • Define advisor_20260301 with Opus as the advisor model
  • Set max_uses to control how often the advisor gets invoked
  • Send your task through /v1/messages and let the executor decide escalation
  • Monitor separate token usage for advisor and executor in the response
Try advisor
Presented by Lambda
How to push Model FLOPS Utilization past 60%
alpha_signal_image_1

Most large-scale training runs operate at 35-45% Model FLOPS Utilization (MFU). You're paying for twice the compute you're using.

Lambda's engineers benchmarked Llama 3.1 models from 8B to 405B on NVIDIA Blackwell GPUs and traced efficiency loss to its root causes:

  • Memory overhead

  • Parallelism strategy

  • Serialized communication

The result: a reproducible framework that pushed MFU past 60% (25%+ improvement vs. industry benchmark) with no changes to model architecture.

Get the guide
partner with us
Top News
OpenAI announces a $100/month ChatGPT Pro tier with higher Codex limits for long coding sessions
16,349 Likes
Grok 4 Fast Benchmark

OpenAI updates ChatGPT Plus and Pro plans to support increased Codex usage. The new Pro tier costs $100/month and provides higher limits for longer, high-effort coding sessions.

A limited-time promotion increases Pro Codex usage to 10× Plus capacity through May 31.

Codex Usage Changes

OpenAI adjusts how Codex usage is allocated across subscription tiers.

  • Plus shifts toward consistent weekly usage instead of concentrated single-day session limits
  • Existing Plus promotion ends, with usage rebalanced for more frequent but shorter sessions
  • Pro tier supports longer uninterrupted sessions designed for extended coding workflows
  • Changes align usage patterns with observed demand for sustained development sessions

Pro Tier Capabilities

Pro expands model access, limits, and system capacity compared to Plus.

  • Includes access to GPT-5.4 Pro reasoning model with higher compute allocation
  • Supports larger context windows, up to roughly 400K tokens for reasoning tasks
  • Provides maximum Codex task capacity for multi-step workflows and larger codebases
  • Maintains unlimited model usage within defined abuse guardrails

Plan Positioning

Each plan now targets a different Codex usage pattern.

  • Plus remains priced at $20 for steady daily usage across coding tasks
  • Pro acts as a higher tier for users with sustained or intensive workloads
  • Upgrade path focuses on increased usage limits rather than new core features
  • Pricing structure reflects differences in session length and compute allocation
Explore pro plan
Presented by Fuel iX by TELUS Digital
Can your LLM withstand a prompt injection attack?
alpha_signal_image_2

We tested 24 leading GenAI models for vulnerabilities. All 24 failed, with attack success rates up to 64%. Every model demonstrated exploitable flaws that turn AI into an attack vector.

Download our report for security profiles on all 24 models and strategies to secure your AI stack.

Access the report
partner with us
Top Paper
Meta presents Neural Computer, a model that runs computation, memory, and I/O inside one learned system
1,836 Stars
Grok 4 Fast Benchmark

Meta AI proposes a shift from models that use computers to models that act as computers. Instead of calling APIs or tools, the model executes tasks directly from learned behavior.

The prototype trains on screen recordings and reproduces parts of real desktop and terminal workflows.

How it works

The model learns full interaction loops from recorded computer usage.

  • Trains on sequences of pixels, cursor movements, and keyboard inputs
  • Predicts next screen state and action at each step in sequence
  • Encodes logic and control flow directly in model weights
  • Treats UI interactions as data instead of fixed program interfaces

Core idea 

The paper frames this as a shift in where system responsibilities live.

  • Moves execution logic from external software stack into model runtime
  • Removes need for toolchains, APIs, and explicit program orchestration layers
  • Positions model as both controller and executor of computational processes
  • Distinguishes approach from memory-augmented models like NTM and DNC

Key findings and limitations

The prototype exposes clear gaps in reliability and abstraction.

  • Fails on multi-step reasoning tasks with dependencies across steps
  • Shows unstable memory across longer interaction sequences
  • Does not form reusable abstractions from learned behaviors
  • Generalization drops outside training distribution of interface patterns
Read the paper
Signals
1 Anthropic announces Monitor tool which lets Claude run background scripts and wake on events 4,901 Likes
2 Perplexity integrates Plaid to connect bank accounts, credit cards, and loans for unified financial tracking 6,632 Likes
3 Cursor enables agents to attach demos and screenshots to pull requests for easier review 1,532 Likes
4 Augment Code hosts Vibe Code Cup, a live AI coding competition with 90-minute build window 1,419 Likes
5 Google proposes ConvApparel to evaluate and improve realism of simulated human conversations in AI systems 1,225 Likes
At Alpha Signal, our mission is to build a sharp, engaged community focused on AI, machine learning, and cutting-edge language models, helping over 200,000 developers stay informed and ahead. We’re passionate about curating the best in AI, from top research and trending technical blogs to expert insights and tailored job opportunities. We keep you connected to the breakthroughs and discussions that matter, so you can stay in the loop without endless searching. We also work closely with partners who value the future of AI, including employers and advertisers who want to reach an audience as passionate about AI as we are.

Our partnerships are based on shared values of ethics, responsibility, and a commitment to building a better world through technology.Privacy is a priority at Alpha Signal. Our Privacy Policy clearly explains how we collect, store, and use your personal and non-personal information. By using our website, you accept these terms, which you can review on our website. This policy applies across all Alpha Signal pages, outlining your rights and how to contact us if you want to adjust the use of your information. We’re based in the United States. By using our site, you agree to be governed by U.S. laws.
Looking to promote your company, product, service, or event to 250,000+ AI developers?
Work with us