Taichi Nakashima
@deeeeet.bsky.social
📤 861
📥 26
📝 97
https://deeeet.com/
Jason Spielman • Designing NotebookLM
jasonspielman.com/notebooklm
loading . . .
Jason Spielman • Designing NotebookLM
Designer, builder, and visual storyteller. Now building Huxe. Previously led design on NotebookLM and contributed to Google AI projects like Gemini and Search. Also shoot photo/video for brands like…
https://jasonspielman.com/notebooklm
about 2 months ago
0
0
0
Experimenting with local LLMs on macOS
blog.6nok.org/experimentin...
loading . . .
Experimenting with local LLMs on macOS
A developer's guide to downloading and running LLMs on macOS, for experimentation and privacy.
https://blog.6nok.org/experimenting-with-local-llms-on-macos/?__readwiseLocation=
2 months ago
0
0
0
research.trychroma.com/context-rot
loading . . .
Context Rot: How Increasing Input Tokens Impacts LLM Performance
https://research.trychroma.com/context-rot?ref=ghuntley.com
3 months ago
0
0
0
What are Forward Deployed Engineers, and why are they so in demand?
newsletter.pragmaticengineer.com/p/forward-de...
loading . . .
What are Forward Deployed Engineers, and why are they so in demand?
Startups and scaleups are on a hiring spree for a software engineering role pioneered by Palantir. A deepdive into this role, and why FDEs are so popular in 2025
https://newsletter.pragmaticengineer.com/p/forward-deployed-engineers
3 months ago
0
0
0
iPhone DevOps - ultimate edition
clearsky.dev/blog/iphone-...
loading . . .
iPhone DevOps - ultimate edition
I wrote earlier about my dream of developing “single-handedly” on an iPhone. Then, I wrote some more about it. The dream still lives strongly! I am now coding single-handedly in any language on my…
https://clearsky.dev/blog/iphone-devops-ssh/
3 months ago
0
0
0
Why LLMs Can't Really Build Software - Zed Blog
zed.dev/blog/why-llm...
loading . . .
Why LLMs Can't Really Build Software - Zed Blog
From the Zed Blog: Writing code is only one part of effective software engineering.
https://zed.dev/blog/why-llms-cant-build-software
3 months ago
0
1
0
I tried Servo, the undercover web browser engine made with Rust
www.spacebar.news/servo-underc...
loading . . .
I tried Servo, the undercover web browser engine made with Rust
Servo was supposed to be Firefox's future. Now it's an independent effort to make a fast and secure web browser engine.
https://www.spacebar.news/servo-undercover-web-browser-engine/
4 months ago
0
1
0
Vibe code is legacy code
blog.val.town/vibe-code
loading . . .
Vibe code is legacy code
Updates and articles from the Val Town team
https://blog.val.town/vibe-code
4 months ago
0
0
0
LLM Embeddings Explained: A Visual and Intuitive Guide
huggingface.co/spaces/hesam...
loading . . .
LLM Embeddings Explained: A Visual and Intuitive Guide - a Hugging Face Space by hesamation
This app explains how language models transform text into meaningful representations through embeddings. It provides a visual guide to help you understand traditional and modern language model tech...
https://huggingface.co/spaces/hesamation/primer-llm-embedding?section=what_are_embeddings
4 months ago
0
0
0
Hierarchical Reasoning Model
arxiv.org/abs/2506.217...
loading . . .
Hierarchical Reasoning Model
Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought…
https://arxiv.org/abs/2506.21734?__readwiseLocation=
4 months ago
0
0
0
Tolerating full cloud outages with Monzo Stand-in
monzo.com/blog/tolerat...
loading . . .
Tolerating full cloud outages with Monzo Stand-in
It all starts with our personal current account
https://monzo.com/blog/tolerating-full-cloud-outages-with-monzo-stand-in
4 months ago
0
1
0
How I keep up with AI progress (and why you must too) - nilenso blog
blog.nilenso.com/blog/2025/06...
loading . . .
How I keep up with AI progress (and why you must too) - nilenso blog
Atharva Raykar ...
https://blog.nilenso.com/blog/2025/06/23/how-i-keep-up-with-ai-progress/
4 months ago
0
0
0
LLM Inference in Production
bentoml.com/llm/
loading . . .
Introduction | LLM Inference Handbook
A practical handbook for engineers building, optimizing, scaling and operating LLM inference systems in production.
https://bentoml.com/llm/
4 months ago
0
0
0
I used o3 to profile myself from my saved Pocket links
noperator.dev/posts/o3-poc...
4 months ago
0
0
0
addyo.substack.com/p/the-prompt...
loading . . .
The Prompt Engineering Playbook for Programmers
Turn AI coding assistants into more reliable development partners
https://addyo.substack.com/p/the-prompt-engineering-playbook-for
5 months ago
0
0
0
Swift at Apple: migrating the Password Monitoring service from Java
swift.org/blog/swift-a...
loading . . .
Swift at Apple: migrating the Password Monitoring service from Java
Swift is heavily used in production for building cloud services at Apple, with incredible results. Last year, the Password Monitoring service was rewritten in Swift, handling multiple billions of requ...
https://swift.org/blog/swift-at-apple-migrating-the-password-monitoring-service-from-java/
5 months ago
0
0
0
Journey to 1000 models: Scaling Instagram’s recommendation system
engineering.fb.com/2025/05/21/p...
loading . . .
Journey to 1000 models: Scaling Instagram’s recommendation system
In this post, we explore how Instagram has successfully scaled its algorithm to include over 1000 ML models without sacrificing recommendation quality or reliability. We delve into the intricacies…
https://engineering.fb.com/2025/05/21/production-engineering/journey-to-1000-models-scaling-instagrams-recommendation-system/
6 months ago
0
1
0
huggingface.co/blog/vlms-2025
loading . . .
Vision Language Models (Better, faster, stronger)
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
https://huggingface.co/blog/vlms-2025
6 months ago
0
0
0
martinfowler.com/articles/des...
loading . . .
Design Token-Based UI Architecture
Describing established patterns for organizing design tokens and practical approaches for automation
https://martinfowler.com/articles/design-token-based-ui-architecture.html
6 months ago
0
0
0
Microservices Are a Tax Your Startup Probably Can’t Afford
loading . . .
Microservices Are a Tax Your Startup Probably Can’t Afford
Why splitting your codebase too early can quietly destroy your team’s velocity — and what to do instead. In a startup, your survival depends on how quickly you can iterate, ship features, and deliver…
https://nexo.sh/posts/microservices-for-startups/
6 months ago
0
0
0
Building Windsurf with Varun Mohan - by Gergely Orosz
loading . . .
Building Windsurf with Varun Mohan
Varun Mohan, CEO of Windsurf, shares how building an AI-native IDE is reshaping software development—from optimizing LLM latency to enabling non-engineers to ship code.
https://newsletter.pragmaticengineer.com/p/building-windsurf-with-varun-mohan
6 months ago
0
0
0
Driving AI tool adoption — Lessons from Microsoft
newsletter.getdx.com/p/driving-ai...
loading . . .
Driving AI tool adoption — Lessons from Microsoft
An interview with researcher and SPACE author Brian Houck about proven strategies for driving AI adoption.
https://newsletter.getdx.com/p/driving-ai-tool-adoption-lessons-from-microsoft
7 months ago
0
0
0
An Intro to DeepSeek's Distributed File System | Some blog
loading . . .
An Intro to DeepSeek's Distributed File System | Some blog
Personal website for some random tidbits I work on
https://maknee.github.io/blog/2025/3FS-Performance-Journal-1/
7 months ago
0
0
0
Pydantic AI's MCP server for running LLM-generated Python code in a sandbox by using a Deno process to run Pyodide in a WebAssembly sandbox / MCP Run Python
loading . . .
MCP Run Python
Pydantic AI's MCP server for running LLM-generated Python code in a sandbox. They ended up using a trick I explored [two years ago](https://til.simonwillison.net/deno/pyodide-sandbox): using a…
https://simonwillison.net/2025/Apr/18/mcp-run-python/
7 months ago
0
2
0
When engineers say "that'll take months!"
www.ryansinger.co/when-enginee...
loading . . .
When engineers say "that'll take months!"
Igor writes: "Our product is 15 years old, with a lot of legacy code and outdated technologies. Our engineers say that the minimum time they need to ship anything of real value (not just small…
https://www.ryansinger.co/when-engineers-say-thatll-take-months/
7 months ago
0
0
0
cdn.openai.com/business-gui...
loading . . .
https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf
7 months ago
0
0
0
How To Build An Agent | Amp
ampcode.com/how-to-build...
loading . . .
How To Build An Agent | Amp
Building a fully functional, code-editing agent in less than 400 lines.
https://ampcode.com/how-to-build-an-agent
7 months ago
0
2
0
Stevens: a hackable AI assistant using a single SQLite table and a handful of cron jobs
www.geoffreylitt.com/2025/04/12/h...
loading . . .
Stevens: a hackable AI assistant using a single SQLite table and a handful of cron jobs
There’s a lot of hype these days around patterns for building with AI. Agents, memory, RAG, assistants—so many buzzwords! But the reality is, you don’t need fancy techniques or libraries to build…
https://www.geoffreylitt.com/2025/04/12/how-i-made-a-useful-ai-assistant-with-one-sqlite-table-and-a-handful-of-cron-jobs?__readwiseLocation=
7 months ago
0
1
0
The Philosophy of Software Design – with John Ousterhout
loading . . .
The Philosophy of Software Design – with John Ousterhout
Stanford professor John Ousterhout explains why thoughtful software design matters more than ever as AI tools transform coding practices and developer workflows.
https://newsletter.pragmaticengineer.com/p/the-philosophy-of-software-design?publication_id=458709&utm_campaign=email-post-title&r=4jsft5&utm_medium=email
7 months ago
0
0
0
20 years of Git. Still weird, still wonderful.
loading . . .
20 years of Git. Still weird, still wonderful.
Twenty years ago, Git was born. How did this unlikely "information manager" take over the world?
https://blog.gitbutler.com/20-years-of-git/
7 months ago
0
0
0
Senior Developer Skills in the AI Age: Leveraging Experience for Better Results • Manuel Kießling
loading . . .
Senior Developer Skills in the AI Age: Leveraging Experience for Better Results • Manuel Kießling
How time-tested software engineering practices amplify the effectiveness of AI coding assistants.
https://manuel.kiessling.net/2025/03/31/how-seasoned-developers-can-achieve-great-results-with-ai-coding-agents/
7 months ago
0
0
0
Agent Engineering - Latent.Space
loading . . .
Agent Engineering
Defining Agents, Why now, and why Agents are the biggest opportunity for AIEs
https://www.latent.space/p/agent
7 months ago
0
0
0
OpenAI leverages Ory to support over 400M weekly active users
loading . . .
OpenAI leverages Ory to support over 400M weekly active users
Learn how OpenAI created secure, user-friendly CIAM for their applications with Ory.
https://www.ory.sh/case-studies/openai
8 months ago
0
1
0
This Year in Uber’s AI-Driven Developer Productivity Revolution | DPE Summit 2024
loading . . .
This Year in Uber’s AI-Driven Developer Productivity Revolution | DPE Summit 2024
Presented by Ty Smith and Adam Huda (Uber) at DPE Summit 2024, an event developed and hosted by Gradle.
https://dpe.org/sessions/ty-smith-adam-huda/this-year-in-ubers-ai-driven-developer-productivity-revolution/
8 months ago
0
0
0
Crafting READMEs for AI
loading . . .
Crafting READMEs for AI
Optimize your README.md files to empower both human developers and AI coding assistants alike.
https://benhouston3d.com/blog/crafting-readmes-for-ai
8 months ago
0
6
2
Exploring Generative AI
loading . . .
Exploring Generative AI
Notes from my Thoughtworks colleagues on AI-assisted software delivery
https://martinfowler.com/articles/exploring-gen-ai.html
8 months ago
0
0
0
AI Engineering in the real world - by Gergely Orosz
loading . . .
AI Engineering in the real world
What does AI engineering look like in practice? Hands-on examples and learnings from software engineers turned “AI engineers” at seven companies
https://newsletter.pragmaticengineer.com/p/ai-engineering-in-the-real-world
8 months ago
0
1
1
"Vibe Coding" vs Reality
loading . . .
"Vibe Coding" vs Reality
Reviewing the capabilities and limitations of LLM agents in software development and their impact on skilled and less skilled developers.
https://cendyne.dev/posts/2025-03-19-vibe-coding-vs-reality.html
8 months ago
1
0
1
Improving Recommendation Systems & Search in the Age of LLMs
loading . . .
Improving Recommendation Systems & Search in the Age of LLMs
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
https://eugeneyan.com/writing/recsys-llm/
8 months ago
0
1
0
In S3 simplicity is table stakes | All Things Distributed
loading . . .
In S3 simplicity is table stakes
From simple object storage to sophisticated table management, builders have always shaped S3's evolution. Andy Warfield discusses why making complex systems simple remains our north star at AWS.
https://www.allthingsdistributed.com/2025/03/in-s3-simplicity-is-table-stakes.html
8 months ago
0
0
0
A 10x faster TypeScript - YouTube
loading . . .
Your browser is up to date
You can use YouTube's latest features!
https://www.youtube.com/watch?v=pNlq-EVld70
8 months ago
0
1
0
Here’s how I use LLMs to help me write code
loading . . .
Here’s how I use LLMs to help me write code
Online discussions about using Large Language Models to help write code inevitably produce comments from developers who’s experiences have been disappointing. They often ask what they’re doing…
https://simonwillison.net/2025/Mar/11/using-llms-for-code/
8 months ago
0
0
0
Meta’s Hyperscale Infrastructure: Overview and Insights – Communications of the ACM
loading . . .
Meta’s Hyperscale Infrastructure: Overview and Insights – Communications of the ACM
Membership in ACM includes a subscription to Communications of the ACM (CACM), the computing industry's most trusted source for staying connected to the world of advanced computing.
https://buff.ly/EVAoCQP
8 months ago
0
1
0
50 things we’ve learned about building successful products
loading . . .
50 things we’ve learned about building successful products
To celebrate 50k subscribers to Product for Engineers, here are the 50 most important lessons we’ve learned about building great products.
https://buff.ly/3XpbyAx
8 months ago
0
0
0
Slack Migrates to Cell-Based Architecture on AWS to Mitigate Gray Failures - InfoQ
loading . . .
Slack Migrates to Cell-Based Architecture on AWS to Mitigate Gray Failures
Slack migrated most of the critical user-facing services from a monolithic to a cell-based architecture over the last 1.5 years. The move was triggered by the impact of networking outages affecting a…
https://buff.ly/hBUBspB
9 months ago
0
1
0
Ethical Considerations and Best Practices in LLM DevelopmentÂ
loading . . .
Ethical Considerations and Best Practices in LLM Development
Ethical LLM development isn’t just about compliance—it’s about building trust and accountability with users and stakeholders.
https://buff.ly/jpuERt0
9 months ago
0
1
0
Give it five minutes – Signal v. Noise
loading . . .
Give it five minutes
A few years ago I used to be a hothead. Whenever anyone said anything, I’d think of a way to disagree. I’d push back hard if something didn’t fit my world-view. It’s like I had to be first with an…
https://buff.ly/3K60fEc
9 months ago
0
0
0
A Practitioner's Guide to Wide Events | Jeremy Morrell
loading . . .
A Practitioner's Guide to Wide Events | Jeremy Morrell
The existing articles on Wide Events define the concept well but leave the implementation details to the reader.
https://buff.ly/3UqaM4M
9 months ago
0
1
1
All you need is Wide Events, not “Metrics, Logs and Traces”
loading . . .
All you need is Wide Events, not “Metrics, Logs and Traces”
This quote from Charity Majors is probably the best summary of the current state of observability in the tech industry - a total, mass confusion.
https://buff.ly/3STZQea
9 months ago
0
1
0
Observability 2.0 vs. Observability 1.0 | Honeycomb
loading . . .
There Is Only One Key Difference Between Observability 1.0 and 2.0
In this article, Charity Majors goes over the simple, technical distinction between observability 1.0 and observability 2.0.
https://buff.ly/424HAov
9 months ago
0
3
1
Load more
feeds!
log in