Hey folks,

I’ve been using Fable quite a bit since it came back (but not for long…) and I’ve barely used it to do any building. I like Anthropic’s models mostly for their thinking, they’re resourceful, creative and can connect things I often can’t put my finger on.

So Fable’s been a bit of a therapist/thinking partner this past week. But it feels slightly different this time. It could be me, but it has shown me a bunch of Opus-like traits in how it’s talking or thinking. And it’s not because my prompts are being routed to Opus (I checked).

I’m excited to see GPT 5.6 come out, I think this week, to see if they’ve finally cracked the creativity/thinking vibe I’m after. Codex is a materially better product than Claude Code (or Cowork). And it’s super fast.

As usual, I’m using a square peg for a round hole - a coding agent with a coding brain for creative thinking and brainstorming. But I do change the system prompt of Claude Code to a simpler one that is much faster and much less steered.

I’m wanting a harness that can still build but is less of a developer at heart, and more something to really spar with me on creative thinking. I sometimes flit to plain Claude for different perspectives, but that doesn’t seem to cut it either.

I’ve tried skills, prompts, and harnesses but nothing seems to get me what I want. Which is something I keep thinking through when I want to make something…what do I actually want?! Today that question comes up for me a lot, and I keep convincing myself I’ll only know when I see it, so I need to stay ‘in the work’ before it’ll present itself.

But equally, this could be AI having an impact on me - if anything can be generated at any moment, just cycle through until you see what you want. Just keep spinning that wheel.

Seems healthy? 😅

Ben’s Bites is brought to you by Adobe Firefly^356†

Adobe Firefly^356† expands agentic capabilities with: brand kit creation (describe your style, brand name, and color palette and let it go to work), short product video creation, Quick Cut (auto-assemble video footage into a polished cut), storyboards (visualize and sequence ideas before production).

Headlines

• Today is the last day of Fable being available in your Claude subscriptions (atleast for now). You will have to buy usage credits for using Fable starting tomorrow. So everyone has a guide to get the max out of this one day:

  • Use Fable to find your unknowns⁹⁰⁸ - Thariq (from Anthropic)

  • Let Fable use its judgement⁵¹¹ - Simon Willison

  I’ve mostly used a single long chat with Fable this entire week. The way it uses memory, compaction, and writing to files is amazing. I’m making it use codex and droid as subagents A LOT. So much that I’m running out on my Codex usage faster than my Claude Code usage. — Keshav

  Theo’s video⁶⁰⁰ on how he has used Fable is a good watch to reimagine how you should use the newer generation of AI models, because remember, GPT-5.6-Sol will likely become accessible this week. You can expect similar performance/behaviour from that one.

• The Information reported that OpenAI has found a way to cut its inference cost in half²³⁷ and already tested it on logged-out ChatGPT users. Does this mean it can reduce API costs of their latest models too? Not sure, but I hope it is. The last major price cut we had was about a year ago, when OpenAI reduced the cost of o3 by 80%.

• GPT-Realtime-2.1-mini²⁰⁹ - new model in the OpenAI API that can take in video and output audio while doing reasoning and tool calls.

• MIRA is a playable world model²⁹¹ trained on 10k hours of Rocket League-style gameplay. It feels like you’re actually playing the game on low-graphics with janky controls.

• New interpretability research from Anthropic²³¹ - Claude uses a global workspace to activate a bunch of concepts that don’t appear in the output or the chain of thought but affect its work. The researchers are comparing it to unconscious thoughts.

My feed

• OpenScience³²⁶ is an open-source Claude Science alternative. Works with multiple models and 250+ skills.

• You can run /cd in Claude Code¹⁸⁹ to move a running session to another folder without restarting.

• The Making of Claude Code²⁵⁹ - short history from the team and early users.

• integrations.sh³²⁸ - catalogue of product MCPs, APIs, CLIs, and auth steps for agents.

• Taste Skill⁴⁰⁸ + Impeccable³³¹ - design skills for agents that keep UIs from looking generic.

• Boring Computers²⁹³ - spin up a real computer for an agent, then destroy it.

• Chromeless³⁰⁴ - MacOS browser without chrome for clean screenshots and recordings.

• Vercel MCP and CLI can discover and fetch agent traces¹⁸⁰ from sessions with Eve, their own agent framework.

• Types of loops and how to use them³⁸¹ - turn-based prompts, /goal, /loop, /schedule and proactive routines.

• exe.dev²⁰¹ now lets you connect your ChatGPT subscription to their terminal agent.

• Dayflow³³⁴ logs your screen activity and creates an automatic work journal based on what you’ve spent your time on in a day.

• PersonalOS³⁴⁹ - 300k-token life context pack from iMessage, notes, docs and app exports. (prompt to do it for yourself²⁰⁹)

• Headroom²⁶³ - Mac menu bar app for Claude/Codex usage and spend during Fable week.

  ---

  Afters

  im releasing all my agent skills to the public this is hundreds of hours of trial & error every single global .agents skill i have go grab it. it's free.

  @DavidOndrej1⁴⁸⁷

  https://t.co/D6DjGcUFZI

  @bayeslord²⁵⁶

  If you wanna level up as an AI builder, binge watch the talks from these 3 conferences (all freshly wrapped). You can literally learn from the best in the field from the comfort of your home. - AI Engineer @aiDotEngineer youtube.com/@aiDotEngineer - Cursor Compile @cursor_ai

  @zarazhangrui⁴²⁸

  Have a little writing app I'm cooking that's designed just for my workflow. As you zoom out, every card flips to a one line summary so you can quickly scan and eval the argument one level up. Using Ollama local models to make these so they're quick and free. So simple, so useful.

  @Mappletons³²⁰

Memory cost and capacity are significant issues for AI accelerators. Unlike game rendering, model inference can have a deterministic memory access pattern. You don’t need “random access memory” at all for model weights, and you could tolerate cold-start latencies in the multiple

@ID_AA_Carmack¹⁷⁵

I went to Miami to chat with @thdxr, co-founder of OpenCode. We talked about the future of software engineering, coding agents, and why open source matters more now than ever. Timestamps: 0:00 Intro 5:30 Miami vs San Francisco tech scene 15:05 OpenCode origin story, scaling

@Madisonkanna¹⁹⁶

• Find me on X¹³⁴, Linkedin¹²⁷, or YouTube¹¹⁶

• Read about me¹²⁷ and Ben’s Bites

• 📷 thumbnail via @keshavatearth¹¹⁷

* sponsors who make this newsletter possible :)

Wanna partner with us for the next quarter?

Email us at shanice@bensbites.com¹¹⁵ or k@bensbites.com¹¹²