The Deep Feed

01 — Ben Davis · Video

GPT-5.5 is the best model ever made (but there's a catch)

From Ben Davis

By Ben Davis · 3 min read

Editor's note: Selected for relevance to deep work, technology, attention, or better thinking.

I know I'm late to this one, but still wanted to talk about it. GPT-5.5 is really really good, but it's also a little weird...

Thank you Railway for sponsoring! Check them out at: https://davis7.link/railway

SOURCES https://developers.openai.com/api/docs/guides/prompt-guidance https://x.com/0xSero/status/2048744545853030690 https://x.com/davis7/status/2048239401059434710 https://x.com/davis7/status/2048235547366457452 https://x.com/davis7/status/2048232268808990890 https://x.com/threepointone/status/2049545657866674665 https://x.com/badlogicgames/status/2048444292562026713 https://models.davis7.sh/

My X, Discord, and more: https://davis7.sh/

Key Takeaway

Read this with one question in mind: what would I change in my work tomorrow if I took this seriously?

02 — Jimmy The Giant · Video

The EVIL War on the NHS

From Jimmy The Giant

By Jimmy The Giant · 3 min read

Editor's note: Selected for relevance to deep work, technology, attention, or better thinking.

Stop Big Tech spying on your Emails!: http://proton.me/jimmythegiant

Today we explore the complete history of the NHS from its inception to now and we track the continuous war to destroy it. From Churchill, BMA, Thatcher, to Palantir and Kier Starmer

👉 Subscribe for more content https://www.youtube.com/jimmythegiant?sub_confirmation=1

👉Support on Patreon https://www.patreon.com/JimmyTheGiant

🎵 My Music is now on Spotify! 🎵 https://open.spotify.com/artist/18FePoDgXxMD8cADCHHbuD

Instagram @JimmythegiantUK

Discord: https://discord.gg/suZC9G8akF

Key Takeaway

Read this with one question in mind: what would I change in my work tomorrow if I took this seriously?

03 — Fireship · Video

732 bytes of Python just borked every Linux machine on earth…

From Fireship

By Fireship · 3 min read

Editor's note: Selected for relevance to deep work, technology, attention, or better thinking.

CodeRabbit's new Slack Agent lets you manage your team's agentic workflow right in Slack - https://coderabbit.link/fireship-agent

A 100% reliable logic flaw was discovered in the Linux kernel and an AI tool wrote an exploit for it that affects every Linux machine updated since 2017. Let's look at the technical details behind the vulnerability and what to do if you're affected...

#coding #programming #linux #python

Want more Fireship?

🗞️ Newsletter: https://bytes.dev 🧠 Courses: https://fireship.dev

Key Takeaway

Read this with one question in mind: what would I change in my work tomorrow if I took this seriously?

04 — AI Dot Engineer · Video

Demand-Driven Context: A Methodology for Coherent Knowledge Bases Through Agent Failure

From AI Dot Engineer

By AI Dot Engineer · 3 min read

Editor's note: Selected for relevance to deep work, technology, attention, or better thinking.

Enterprise teams spend a lot of time trying to guess what AI agents need to know. This workshop flips that around. Instead of curating context top-down, Raj Navakoti shows how to build a demand-driven context base by giving agents real problems, watching where they fail, and using those failures to reveal exactly what knowledge is missing.

Using practical exercises and real examples from IKEA Digital, the session walks through how to grow a knowledge base problem by problem, structure it in Markdown, and use agents with different roles and reasoning boundaries against the same shared context. If you're building enterprise AI systems and want a more grounded way to create useful context, this is a strong practical framework.

Speaker info: - https://www.linkedin.com/in/raj-navakoti-529880b1/

Timestamps: 0:00 - Introduction and speaker background 2:47 - The situation: Analogy to the movie Memento and AI's memory constraints 3:55 - Evolution of AI: From prompt engineering to deep agents 4:33 - Enterprise AI challenge: Why productivity isn't moving 5:33 - The problem: Green (general), Orange (taught), and Red (institutional/tribal) knowledge 10:11 - The Monolith: Why institutional knowledge is often outdated or missing 11:24 - Solution introduction: Demand-driven context 13:05 - The "Pull" strategy: Learning by doing vs. pushing information 14:48 - The agent lifecycle: Problem to discovery to documentation 17:46 - Demo introduction: Using a framework for context management 19:1

Key Takeaway

Read this with one question in mind: what would I change in my work tomorrow if I took this seriously?