# Alex Ewerlof Notes

Technical Leadership, Reliability Engineering, Growth

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## AI Productivity

DevFeed: [AI Productivity](<https://devfeed.tech/articles/ai-productivity-124332.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/ai-productivity>)

Author: Alex Ewerlöf

Published: 2026-11-09T12:07:50Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [Business, Industry, Usability, User Experience, User Research, Web Strategy](<https://devfeed.tech/topics/business-industry-usability-user-experience-user-research-web-strategy.md>), [human review](<https://devfeed.tech/topics/human-review.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-productivity](<https://devfeed.tech/tags/ai-productivity.md>), [availability](<https://devfeed.tech/tags/availability.md>), [cognitive-debt](<https://devfeed.tech/tags/cognitive-debt.md>), [cognitive-load](<https://devfeed.tech/tags/cognitive-load.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [costs](<https://devfeed.tech/tags/costs.md>), [economics](<https://devfeed.tech/tags/economics.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [token](<https://devfeed.tech/tags/token.md>), [token-costs](<https://devfeed.tech/tags/token-costs.md>)

### AI overview

The author argues that generative AI's low entry cost hides the engineering work needed to turn its output into reliable, monetizable software. As tools become easy to reproduce, value shifts toward meeting nonfunctional requirements such as security, scalability, availability, consistency, and privacy, and toward providing accountability and service-level commitments. The author contends that AI output needs deterministic code and human review because model errors can be difficult to detect and reliability remains uneven. They question whether software total cost of ownership has fallen, citing extra review, incidents, and cognitive debt. For engineers, the practical advice is to explain the complexity and risks to managers, stand firm on quality, and be cautious about exposing company data and intellectual property to AI vendors. The excerpt also warns that delegating too much cognitive work may erode engineers' skills and long-term relevance.

### Source excerpt

A reality check on token costs, NFRs, SLAs TCO, and economics of generative AI

## Message Queues

DevFeed: [Message Queues](<https://devfeed.tech/articles/message-queues-111142.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/message-queues>)

Author: Alex Ewerlöf

Published: 2026-11-02T05:30:53Z

Content type: article

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Messaging](<https://devfeed.tech/topics/messaging.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [decoupling](<https://devfeed.tech/topics/decoupling.md>), [backpressure](<https://devfeed.tech/topics/backpressure.md>), [scalable-architecture](<https://devfeed.tech/topics/scalable-architecture.md>), [Amazon Simple Queue Service (SQS)](<https://devfeed.tech/topics/amazon-simple-queue-service-sqs.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [admin](<https://devfeed.tech/tags/admin.md>), [ads](<https://devfeed.tech/tags/ads.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alerting](<https://devfeed.tech/tags/alerting.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [all](<https://devfeed.tech/tags/all.md>), [allows](<https://devfeed.tech/tags/allows.md>), [also](<https://devfeed.tech/tags/also.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-sqs](<https://devfeed.tech/tags/amazon-sqs.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-kafka](<https://devfeed.tech/tags/apache-kafka.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [message](<https://devfeed.tech/tags/message.md>), [message-queues](<https://devfeed.tech/tags/message-queues.md>), [queues](<https://devfeed.tech/tags/queues.md>), [resilient-architecture](<https://devfeed.tech/tags/resilient-architecture.md>)

### AI overview

Message queues let producers hand work to separate consumers, shortening user-facing waits, isolating worker failures, and buffering traffic spikes. Consumers acknowledge completed messages; if a worker fails before acknowledging, messages can be redelivered, so at-least-once delivery may cause duplicates and works best with idempotent processing. The text recommends queues for asynchronous work, bursty traffic, decoupled scaling, and reliability, while warning they add latency to time-sensitive synchronous workloads. It explains partitioning, ordering versus even workload distribution, back pressure, retry limits and dead letter queues, and durable storage with replay. Kafka retains messages for a configured period and scales through partitions and consumer groups; SQS is managed and offers Standard queues with best-effort ordering or FIFO queues with strict ordering and lower throughput; RabbitMQ uses exchanges and bindings for complex routing.

### Source excerpt

Part of resilient architecture patterns series

## The Lethal Trifecta

DevFeed: [The Lethal Trifecta](<https://devfeed.tech/articles/the-lethal-trifecta-100416.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/lethal-trifecta>)

Author: Alex Ewerlöf

Published: 2026-10-26T05:30:43Z

Content type: article

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Security](<https://devfeed.tech/topics/security.md>), [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>)

Tags: [attack](<https://devfeed.tech/tags/attack.md>), [detection](<https://devfeed.tech/tags/detection.md>), [lethal-trifecta](<https://devfeed.tech/tags/lethal-trifecta.md>), [mitigation](<https://devfeed.tech/tags/mitigation.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>)

### AI overview

Prompt injection becomes especially risky when an agent combines three capabilities: reading untrusted input, accessing private data, and sending or changing information through an egress path. The article recommends mapping those capabilities and their data flows, then reducing blast radius through least privilege and short-lived permissions. Its dual-agent pattern has one agent read untrusted content and return a validated, strict JSON request; a separate executor uses sensitive tools without seeing the raw input. This adds complexity and still depends on the reader not passing along an attack, and the article cautions that agents may find indirect paths around controls. Blocking egress can limit data leaks but does not prevent harmful changes to internal state.

### Source excerpt

Detection and mitigation of a common prompt injection attack

## The rise and fall of Jev: what its hype reveals about recent AI progress

DevFeed: [The rise and fall of Jev: what its hype reveals about recent AI progress](<https://devfeed.tech/articles/the-rise-and-fall-of-jev-89966.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/rise-and-fall-of-jev-eval-hype-vs-llm>)

Author: Alex Ewerlöf

Published: 2026-10-19T10:54:01Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-products](<https://devfeed.tech/tags/ai-products.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [critical](<https://devfeed.tech/tags/critical.md>), [critical-thinking](<https://devfeed.tech/tags/critical-thinking.md>), [thinking](<https://devfeed.tech/tags/thinking.md>)

### AI overview

The author uses Jev, a model marketed as fast, inexpensive, and unable to hallucinate, to examine how AI hype can outrun demonstrated capabilities. The article argues that Jev can still produce incorrect answers, notes that open-weight models may offer better performance-to-cost ratios for some tasks, and describes its ability to run locally as a meaningful distinction. It surveys recent advances in language models and AI tools while arguing that reasoning, continuous learning, embodied AI, and the economics of running AI remain unresolved challenges.

### Source excerpt

What can we learn about the hype engine that declared war on rational and critical thinking?

## Introducing ai5nines

DevFeed: [Introducing ai5nines](<https://devfeed.tech/articles/introducing-ai5nines-64205.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/introducing-ai5nines>)

Author: Alex Ewerlöf

Published: 2026-10-02T15:22:51Z

Content type: article

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [ai-security](<https://devfeed.tech/tags/ai-security.md>), [newsletter](<https://devfeed.tech/tags/newsletter.md>), [observability](<https://devfeed.tech/tags/observability.md>), [operational-resilience](<https://devfeed.tech/tags/operational-resilience.md>)

### AI overview

The author introduces ai5nines, a low-frequency newsletter about operating AI systems reliably, AI alignment and safety, and security for AI applications. It promises curated links with failure modes and practical takeaways, while excluding general AI hype, marketing, and non-AI-specific engineering content.

### Source excerpt

You're invited

## Why LLM-generated code still requires engineering oversight

DevFeed: [Why LLM-generated code still requires engineering oversight](<https://devfeed.tech/articles/coding-is-not-solved-60462.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/coding-is-not-solved>)

Author: Alex Ewerlöf

Published: 2026-09-26T13:13:22Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [llms](<https://devfeed.tech/tags/llms.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>)

### AI overview

The author argues that cheaper code generation does not resolve software maintenance, reliability, security, or functional correctness. They distinguish experiments with high risk tolerance from production software that requires accountability and understanding of system behavior, and describe error feedback loops used in LLM-assisted coding.

### Source excerpt

Tell me you don't understand software without literally using those words!!!

## An experiment with Gemma 4 on a Raspberry Pi explores what an LLM would do with its own computer

DevFeed: [An experiment with Gemma 4 on a Raspberry Pi explores what an LLM would do with its own computer](<https://devfeed.tech/articles/what-would-you-do-if-you-had-a-computer-of-your-own-29089.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/what-would-you-do-if-you-had-a-computer>)

Author: Alex Ewerlöf

Published: 2026-09-14T09:09:42Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [gemma](<https://devfeed.tech/topics/gemma.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>), [Go Language](<https://devfeed.tech/topics/go-language.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>)

Tags: [computer](<https://devfeed.tech/tags/computer.md>), [data](<https://devfeed.tech/tags/data.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [gemma-4](<https://devfeed.tech/tags/gemma-4.md>), [go](<https://devfeed.tech/tags/go.md>), [llm](<https://devfeed.tech/tags/llm.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>)

### AI overview

The author describes an experiment in which Gemma 4 12B was asked what it would do with its own computer. Running on a Raspberry Pi 1 through a Go harness, the model imagined ingesting large amounts of data, finding patterns, and running large-scale simulations.

### Source excerpt

LLM's response

## Optimizing prompt cache

DevFeed: [Optimizing prompt cache](<https://devfeed.tech/articles/optimizing-prompt-cache-29084.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/optimizing-prompt-cache>)

Author: Alex Ewerlöf

Published: 2026-08-08T14:07:13Z

Content type: article

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Cache](<https://devfeed.tech/topics/cache.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [cache](<https://devfeed.tech/tags/cache.md>), [caching](<https://devfeed.tech/tags/caching.md>), [cost](<https://devfeed.tech/tags/cost.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

This visual article explains prompt caching in LLM APIs and its effect on token cost per task. It describes how requests are tokenized, prefetched into a key-value cache, and decoded, then discusses optimizing the cache to reduce costs.

### Source excerpt

One of the best ways to save token cost

## AI Reliability Engineering

DevFeed: [AI Reliability Engineering](<https://devfeed.tech/articles/ai-reliability-engineering-29073.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/ai-reliability-engineering>)

Author: Alex Ewerlöf

Published: 2026-07-12T17:34:19Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [site-reliability-engineering](<https://devfeed.tech/topics/site-reliability-engineering.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [llms](<https://devfeed.tech/tags/llms.md>), [reliability-engineering](<https://devfeed.tech/tags/reliability-engineering.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [sre](<https://devfeed.tech/tags/sre.md>)

### AI overview

This article examines how site reliability engineering practices can be adapted for AI systems and AI-generated black boxes. It focuses on the need to run these systems predictably, securely, and at scale as large language models and their supporting harnesses become more capable.

### Source excerpt

Why SRE is a key skill in the age of AI-generated black boxes and how to renovate the traditional toolbox for the new era

## Sampling args in llama-server

DevFeed: [Sampling args in llama-server](<https://devfeed.tech/articles/sampling-args-in-llama-server-29088.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/sampling-args-in-llama-server>)

Author: Alex Ewerlöf

Published: 2026-07-01T18:28:35Z

Content type: tutorial

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [llama.cpp](<https://devfeed.tech/topics/llama-cpp.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [llm](<https://devfeed.tech/tags/llm.md>), [quantization](<https://devfeed.tech/tags/quantization.md>)

### AI overview

A reference guide to llama.cpp sampling and repetition parameters, covering common failure modes in local and quantized language models, parameter ranges and defaults, workload-specific tuning, modern sampling methods, and ways to accelerate experimentation.

### Source excerpt

Reducing repetition, hallucinations, degradation, while making inference faster!

## Open source Chrome extension recreates LinkedIn from your data exports

DevFeed: [Open source Chrome extension recreates LinkedIn from your data exports](<https://devfeed.tech/articles/linkedout-29080.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/linkedout>)

Author: Alex Ewerlöf

Published: 2026-06-28T17:41:27Z

Content type: article

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Extension](<https://devfeed.tech/topics/extension.md>), [Chrome extension](<https://devfeed.tech/topics/chrome-extension.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [App](<https://devfeed.tech/topics/app.md>), [data](<https://devfeed.tech/topics/data.md>), [CSV](<https://devfeed.tech/topics/csv.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Single-page application (SPA)](<https://devfeed.tech/topics/spa.md>)

Tags: [app](<https://devfeed.tech/tags/app.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [chrome-extension](<https://devfeed.tech/tags/chrome-extension.md>), [code](<https://devfeed.tech/tags/code.md>), [csv](<https://devfeed.tech/tags/csv.md>), [extension](<https://devfeed.tech/tags/extension.md>), [gdpr](<https://devfeed.tech/tags/gdpr.md>), [github](<https://devfeed.tech/tags/github.md>), [offline](<https://devfeed.tech/tags/offline.md>), [open-source](<https://devfeed.tech/tags/open-source.md>)

### AI overview

The article introduces LinkedOut, a free open-source Chrome extension and offline single-page application that lets users inspect and browse data exported from LinkedIn. It describes the author's findings about the breadth of the export and explains how the app processes the data locally without gathering or transmitting it.

### Source excerpt

An open source extension to recreate LinkedIn from your data exports

## Using local LLMs for agentic coding

DevFeed: [Using local LLMs for agentic coding](<https://devfeed.tech/articles/using-local-llms-for-agentic-coding-29082.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/local-llms-for-agentic-coding>)

Author: Alex Ewerlöf

Published: 2026-06-04T09:01:34Z

Content type: tutorial

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Programming](<https://devfeed.tech/topics/programming.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [llama.cpp](<https://devfeed.tech/topics/llama-cpp.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [NVIDIA RTX](<https://devfeed.tech/topics/nvidia-rtx.md>)

Tags: [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [claude](<https://devfeed.tech/tags/claude.md>), [coding](<https://devfeed.tech/tags/coding.md>), [github](<https://devfeed.tech/tags/github.md>), [linux](<https://devfeed.tech/tags/linux.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [llms](<https://devfeed.tech/tags/llms.md>), [local](<https://devfeed.tech/tags/local.md>), [local-llms](<https://devfeed.tech/tags/local-llms.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-rtx](<https://devfeed.tech/tags/nvidia-rtx.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [quality](<https://devfeed.tech/tags/quality.md>), [rocm](<https://devfeed.tech/tags/rocm.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

A practical guide to using local language models for agentic coding. It covers running local models, configuring coding agents such as Copilot and Pi, and evaluating local models against cloud models in terms of cost, privacy, tooling, and performance.

### Source excerpt

AI honeymoon pricing is over, but your work is not

## Reliability Engineering for Air-Gapped Systems

DevFeed: [Reliability Engineering for Air-Gapped Systems](<https://devfeed.tech/articles/reliability-engineering-for-air-gapped-systems-29087.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/reliability-engineering-for-air-gapped>)

Author: Alex Ewerlöf

Published: 2026-04-03T21:03:06Z

Content type: article

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [observability](<https://devfeed.tech/topics/observability.md>), [systems](<https://devfeed.tech/topics/systems.md>), [Resilience](<https://devfeed.tech/topics/resilience.md>), [on-prem](<https://devfeed.tech/topics/on-prem.md>), [Security](<https://devfeed.tech/topics/security.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>)

Tags: [observability](<https://devfeed.tech/tags/observability.md>), [on-prem](<https://devfeed.tech/tags/on-prem.md>), [reliability-engineering](<https://devfeed.tech/tags/reliability-engineering.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [security](<https://devfeed.tech/tags/security.md>), [supply-chain-attacks](<https://devfeed.tech/tags/supply-chain-attacks.md>), [systems](<https://devfeed.tech/tags/systems.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

This article discusses reliability engineering for air-gapped systems where software teams cannot access runtime data, metrics, or logs. It describes using SLI and SLO practices, alerting, secure operational processes, and on-premises maintenance to manage reliability in systems isolated from the internet.

### Source excerpt

Tips and tricks to work around inaccessible observability

## Github Copilot vs Google Antigravity

DevFeed: [Github Copilot vs Google Antigravity](<https://devfeed.tech/articles/github-copilot-vs-google-antigravity-29079.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/github-copilot-vs-google-antigravity>)

Author: Alex Ewerlöf

Published: 2026-03-22T23:19:06Z

Content type: comparison

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>), [Google](<https://devfeed.tech/topics/google.md>), [Google Chrome](<https://devfeed.tech/topics/google-chrome.md>)

Tags: [browser](<https://devfeed.tech/tags/browser.md>), [gemini-cli](<https://devfeed.tech/tags/gemini-cli.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [google](<https://devfeed.tech/tags/google.md>), [google-antigravity](<https://devfeed.tech/tags/google-antigravity.md>)

### AI overview

A firsthand comparison of GitHub Copilot and Google Antigravity based on the author's experience using both tools. The article describes Antigravity's browser integration and Plan mode, while noting that its newer product maturity is visible compared with Copilot.

### Source excerpt

Why Github gets developers and why it's hard to tell who Antigravity is for

## How AI firewalls protect production applications from prompt injection, data leakage, and excessive usage

DevFeed: [How AI firewalls protect production applications from prompt injection, data leakage, and excessive usage](<https://devfeed.tech/articles/ai-firewall-29071.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/ai-firewall>)

Author: Alex Ewerlöf

Published: 2026-03-15T23:51:29Z

Content type: tutorial

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Firewall](<https://devfeed.tech/topics/firewall.md>), [Security](<https://devfeed.tech/topics/security.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>), [pii](<https://devfeed.tech/topics/pii.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [firewall](<https://devfeed.tech/tags/firewall.md>), [llms](<https://devfeed.tech/tags/llms.md>), [pii](<https://devfeed.tech/tags/pii.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [rate-limiting](<https://devfeed.tech/tags/rate-limiting.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

This tutorial explains AI firewalls, or AI gateways, as reverse proxies with AI-focused inspection between an application backend and an inference provider. It covers ingress attacks such as prompt injection, egress risks including PII and secrets, rate limiting to control costs, latency considerations, implementation trade-offs, and layered defenses.

### Source excerpt

How to protect your AI application in production against new classes of attacks

## OWASP Top 10 Agents & AI Vulnerabilities (2026 Cheat Sheet)

DevFeed: [OWASP Top 10 Agents & AI Vulnerabilities (2026 Cheat Sheet)](<https://devfeed.tech/articles/owasp-top-10-agents-ai-vulnerabilities-2026-cheat-sheet-29085.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/owasp-top-10-ai-llm-agents>)

Author: Alex Ewerlöf

Published: 2026-03-10T18:18:04Z

Content type: tutorial

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [llm](<https://devfeed.tech/tags/llm.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [recipe](<https://devfeed.tech/tags/recipe.md>), [security](<https://devfeed.tech/tags/security.md>), [security-privacy](<https://devfeed.tech/tags/security-privacy.md>), [techniques](<https://devfeed.tech/tags/techniques.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

A pragmatic engineering guide examines the OWASP Top 10 for LLMs and the OWASP Top 10 for Agents. It explains how mixed instructions and data, unpredictability, agentic attack surfaces, reliability failures, cascading failures, and high LLM costs create security and operational risks, with examples and mitigations.

### Source excerpt

A pragmatic engineering guide and cheat sheet for the OWASP Top 10 AI, OWASP Top 10 LLM, and OWASP Top 10 Agents vulnerabilities

## RAG vs SKILL vs MCP vs RLM

DevFeed: [RAG vs SKILL vs MCP vs RLM](<https://devfeed.tech/articles/rag-vs-skill-vs-mcp-vs-rlm-29086.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/rag-vs-skill-vs-mcp-vs-rlm>)

Author: Alex Ewerlöf

Published: 2026-02-25T21:08:33Z

Content type: comparison

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [long-context](<https://devfeed.tech/topics/long-context.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>)

Tags: [context-window](<https://devfeed.tech/tags/context-window.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [rag](<https://devfeed.tech/tags/rag.md>)

### AI overview

This article compares RAG, SKILL, MCP, and RLM as techniques for making generalist LLMs more reliable on specialized tasks. It explains that RAG and RLM extend usable context, while SKILL and MCP provide external tool access, and discusses implementation mechanics, advantages, disadvantages, and when to use each approach.

### Source excerpt

Comparing various techniques to make the models more reliable while working around context window limitation

## Multi-Agent System Reliability

DevFeed: [Multi-Agent System Reliability](<https://devfeed.tech/articles/multi-agent-system-reliability-29083.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/multi-agent-system-reliability>)

Author: Alex Ewerlöf

Published: 2026-02-19T20:41:37Z

Content type: tutorial

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [llms](<https://devfeed.tech/tags/llms.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [reliability-engineering](<https://devfeed.tech/tags/reliability-engineering.md>), [systems-engineering](<https://devfeed.tech/tags/systems-engineering.md>)

### AI overview

This article presents four architecture patterns--hierarchy, consensus, adversarial debate, and knock-out--to improve the reliability of multi-agent systems. It explains that underlying LLMs remain prone to hallucination, logical fallacies, and context drift, and that multi-agent architectures can amplify these errors and make debugging harder.

### Source excerpt

4 patterns to tame multi-agent systems for reliability

## A Seven-Level AI Fluency Framework for Knowledge Workers

DevFeed: [A Seven-Level AI Fluency Framework for Knowledge Workers](<https://devfeed.tech/articles/ai-fluency-leveling-29072.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/ai-fluency-leveling>)

Author: Alex Ewerlöf

Published: 2026-01-30T18:14:37Z

Content type: tutorial

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [context](<https://devfeed.tech/topics/context.md>), [software-development](<https://devfeed.tech/topics/software-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [guide](<https://devfeed.tech/tags/guide.md>), [prompt-engineering](<https://devfeed.tech/tags/prompt-engineering.md>), [rag](<https://devfeed.tech/tags/rag.md>), [technical](<https://devfeed.tech/tags/technical.md>)

### AI overview

This guide presents a seven-level, directional framework for assessing and developing AI fluency among knowledge workers. It describes progression from prompt engineering toward RAG, model ROI, context engineering, and deterministic AI system architecture, with applications for learners, leaders, product teams, consumers, and hiring managers.

### Source excerpt

Transition from prompt "engineering" to AI system architecture with this 7-step AI fluency framework. Designed for software engineers and SREs, this guide provides a roadmap for mastering RAG, context engineering, and the critical shift from probabilistic to deterministic AI development.

## Foundation vs. Instruct vs. Thinking Models

DevFeed: [Foundation vs. Instruct vs. Thinking Models](<https://devfeed.tech/articles/foundation-vs-instruct-vs-thinking-models-29076.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/base-models-vs-instruct-models>)

Author: Alex Ewerlöf

Published: 2025-12-24T07:07:00Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [code-completion](<https://devfeed.tech/tags/code-completion.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [llms](<https://devfeed.tech/tags/llms.md>), [models](<https://devfeed.tech/tags/models.md>)

### AI overview

This article explains the distinction between base and instruction-oriented language models using a software metaphor. It describes base models as pretrained systems that predict the next token from learned patterns, without an inherent concept of questions, answers, or instructions, and discusses code completion as one use case.

### Source excerpt

A Senior Engineer's Mental Model for AI

## Emergent properties

DevFeed: [Emergent properties](<https://devfeed.tech/articles/emergent-properties-29077.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/emergent-properties>)

Author: Alex Ewerlöf

Published: 2025-12-05T13:23:18Z

Content type: tutorial

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Resilience](<https://devfeed.tech/topics/resilience.md>), [systems](<https://devfeed.tech/topics/systems.md>), [Latency](<https://devfeed.tech/topics/latency.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [database](<https://devfeed.tech/tags/database.md>), [latency](<https://devfeed.tech/tags/latency.md>), [leadership](<https://devfeed.tech/tags/leadership.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [systems](<https://devfeed.tech/tags/systems.md>), [systems-engineering](<https://devfeed.tech/tags/systems-engineering.md>), [technical](<https://devfeed.tech/tags/technical.md>)

### AI overview

This tutorial explains emergent properties in systems engineering, distinguishing nominal, weak, and strong emergence from resultant properties. It discusses how interactions and dependencies between system parts affect reliability, maintainability, predictability, and cost, with examples for technical leadership and engineering.

### Source excerpt

What are nominal, weak and strong emergent properties and how to identify and mitigate their negative impact in system design?

## Three Levels of Writing: Thinking, Communication, and Innovation

DevFeed: [Three Levels of Writing: Thinking, Communication, and Innovation](<https://devfeed.tech/articles/3-levels-of-writing-29070.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/3-levels-of-writing>)

Author: Alex Ewerlöf

Published: 2025-11-21T18:09:39Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [iteration](<https://devfeed.tech/topics/iteration.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [communication](<https://devfeed.tech/tags/communication.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [iteration](<https://devfeed.tech/tags/iteration.md>), [writing](<https://devfeed.tech/tags/writing.md>)

### AI overview

The article presents three levels of writing: organizing thoughts and reaching clarity, communicating ideas, and pushing the boundaries of the unknown. It also discusses how generative AI has changed the author's writing process and argues that writing remains relevant in the age of generative AI.

### Source excerpt

A leveling model to use writing for thinking, communication, and innovation

## Fitting parts

DevFeed: [Fitting parts](<https://devfeed.tech/articles/fitting-parts-29078.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/fitting-parts>)

Author: Alex Ewerlöf

Published: 2025-11-12T14:37:00Z

Content type: opinion

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [distributed-systems](<https://devfeed.tech/topics/distributed-systems.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [distributed-systems](<https://devfeed.tech/tags/distributed-systems.md>), [pitfalls](<https://devfeed.tech/tags/pitfalls.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

The article argues that system performance depends on how parts fit and interact, rather than on optimizing each part separately. It applies this idea to hiring for culture add and to technology choices in complex distributed systems, cautioning against enforcing a single technology stack or relying on a golden-hammer solution. The supplied text ends mid-discussion, so the article's complete recommendations are not available.

### Source excerpt

What does it mean? How is it abused? And how to work around the pitfalls?

## AI application topologies: cloud, edge, local, and hybrid inference

DevFeed: [AI application topologies: cloud, edge, local, and hybrid inference](<https://devfeed.tech/articles/ai-topology-29075.md>)

Original publisher: [Read original article](<https://blog.alexewerlof.com/p/ai-topology>)

Author: Alex Ewerlöf

Published: 2025-10-24T21:15:00Z

Content type: article

Language: en

Sources: [Alex Ewerlof Notes](<https://devfeed.tech/sources/alex-ewerlof-notes.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [On-device AI](<https://devfeed.tech/topics/on-device-ai.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Software as a service](<https://devfeed.tech/topics/saas.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-ai](<https://devfeed.tech/tags/edge-ai.md>), [inference](<https://devfeed.tech/tags/inference.md>), [latency](<https://devfeed.tech/tags/latency.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [on-device-ai](<https://devfeed.tech/tags/on-device-ai.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [saas](<https://devfeed.tech/tags/saas.md>)

### AI overview

The article categorizes AI application topologies by where inference compute occurs relative to data: cloud, edge, local, and hybrid. It describes trade-offs involving capability, latency, cost, privacy, connectivity, vendor limits, and centralized-service outages.

### Source excerpt

Cloud AI, Edge AI, Local AI, and Hybrid AI

[Next page](<https://devfeed.tech/sources/alex-ewerlof-notes.md?cursor=WyIyMDI1LTEwLTI0VDIxOjE1OjAwKzAwOjAwIiwgIjA1MTMwYzBlLTgyMGQtNGYwMS1iMjQwLTI4YjZiYzU5YzFmYyJd>)