GPT-6 Astra vs Claude Fable for Knowledge Work: My Experience

Both Are Intelligent Enough for My Work

I love Fable and Astra. For the research, proposals, planning, and consulting delivery I do, both are intelligent enough for me.

What I want next is the same level of intelligence, cheaper and faster. I do not feel much need for a smarter model for this work. The returns are diminishing for me.

I still have things I want improved: following through on an agreed action, keeping track of decisions, and writing without the extra AI prose. But I can already work through complicated ideas with these models and produce something I want to put my name on.

My first weekend with GPT-6 Astra in Codex Desktop has been encouraging because I like it just as much as Fable for this work, and I can use a lot more of it.

Fable’s Usage Limits Keep Getting in My Way

On my Premium Claude for Teams seat, Fable is limited to half of my total weekly usage. In practice, I burn through that allowance in one or two days of what I consider light usage. I cannot get through half a workweek.

A typical session getting a proposal to where I want it can eat $60 to $100 in credits. For my workflow, that is not sustainable.

Even while I have usage left, I find myself worrying about spending it. Should I save Fable for something harder? Is this conversation worth the credits? How much work do I still have this week?

I want to think about the proposal.

A Weekend With Astra

I started using GPT-6 Astra in Codex Desktop on Friday afternoon. I worked through Saturday. As of Sunday, September 6, I still had 33% left and two banked resets remaining.

That is on my $200 ChatGPT Pro account, which I expense through work. These are my account experience and usage figures from this weekend, not a controlled cost comparison or a promise about anyone else’s limits.

For the knowledge work I am doing, Astra feels equal to Fable in intelligence. It also produces much less of the writing I call Claude-speak.

Before Astra, I was trying to make Opus 5 work for this. I spent too much time correcting the tone and trying to get the quality I wanted. Fable and Astra have been much easier for me to work with.

My current recommendation is Astra on Medium reasoning. That is what I have been using for this work. My recommendation comes from this early experience, not a systematic comparison of every setting.

The practical difference is that I can keep working without being afraid that another round of questions will use up the model I need.

I Still Prefer Working in Claude for Teams Ecosystem

I miss Claude Cowork. I prefer its interface to Codex Desktop. I prefer Claude Artifacts to ChatGPT Sites. Sharing work with my team is easier in Claude for Teams because everyone is already there.

I wrote previously about Zero Defect and how I review AI-generated business work. Making plugins for Codex has felt clunkier and more error-prone to me than making them for Claude. I expect OpenAI will catch up there.

Even my grill-me workflow takes extra effort in Codex Desktop. I want it to ask me a question and wait until I answer before moving on. I have had to effectively trick it into keeping the turn open while I think through my response. That is another reason I prefer the Claude Cowork interface for this kind of back-and-forth.

So I still have plenty of reasons to prefer the Claude environment. The limits are what keep getting in the way. Astra gives me a level of quality I am happy with and enough room to use it.

What I Mean by Knowledge Work

This weekend’s work was consulting delivery. I was taking meeting notes, a signed statement of work, client questions, existing architecture material, and research, then turning them into recommendations and deliverables.

The output lives in a client delivery hub: documents, decisions, tasks, references, and interactive examples. Some recommendations also need a small proof of concept so we can distinguish what sounds feasible from what we have actually demonstrated.

There is code involved, but the central work is deciding what to recommend, why it fits, what we promised, and what remains unresolved.

I have opinions. I also have questions I cannot answer yet. I want the model to research those questions, explain the options, challenge my assumptions, and help me develop a position I understand well enough to defend.

Research Has to Be Allowed to Disagree

In one exchange, I suspected that most MCP documentation focused on installation rather than explaining available tools. I asked Astra to research it.

It came back with counterexamples. Its first pass found several vendors publishing tool catalogs, and it explicitly said the sample did not establish what most sites do.

That was useful. I had a hypothesis, and the research gave me reasons to reconsider it.

My eventual recommendation was still opinionated: emphasize setup and useful workflows for the audience we were serving. But that recommendation needed its own justification. It could not rest on an unsupported claim that everyone else only documents installation.

That is the relationship I want with the research. My opinions should survive being questioned, or change because I learned something.

The Model Can Invent Your Position

The mistakes in this conversation were not limited to factual claims.

Astra turned part of a client discussion into an extra task that had not actually been requested. I challenged it and asked for a quoted, cited origin for every task. It acknowledged that it had over-interpreted the discussion and removed the duplicate work.

It also attributed a client’s architecture diagram to me. I corrected that. Who proposed something matters, especially when the document is going back to the client.

A plausible recommendation can make its way into a polished document before I have agreed with it. Then it looks like my position.

That is what I mean when I say I need to catch the model hallucinating opinions that are not mine. Thinking through the decision is my job. Putting my name on the output should mean I understand it and have made that decision myself.

Pause When You Do Not Understand the Question

I start with a hypothesis or an opinion. The model can research it, present options and tradeoffs, and challenge me. I have changed my opinions several times working with both Fable and Astra, and I am learning a lot from the process.

In one architecture discussion, I asked Astra to explain the options piece by piece. I did not understand them well enough to choose. We needed more examples, research, and discussion before I could form my own recommendation.

I wrote about this on LinkedIn on Friday: when you are using the /grill-me skill and reach a question you do not fully understand, pause. Ask the agent to explain the concepts in a way that makes sense to you.

I like using Claude Artifacts or ChatGPT Sites to see a concept explained visually with animations and diagrams. Maybe you learn better with a podcast or a video. Ask for the explanation that helps you understand.

Sometimes I need to know what others in the industry are choosing and why. Have they written about it in a blog or posted about it on X? Ask the agent to research those examples and the tradeoffs, then bring that evidence back to the decision.

Never blindly accept the recommended option or say “whatever is best” when you do not understand the question. That is outsourcing your thinking to AI. Don’t be a meat-proxy.

Yes, I Am Babysitting It

I have seen people on X describe getting great results while supervising Astra and feeling frustrated when they let it run on its own. Those are anecdotes, but I recognize the experience.

For this kind of work, I want to stay involved.

Reviewing a proposed decision, rejecting extra scope, asking for better evidence, and correcting a misleading phrase are worthwhile uses of my time. They are part of producing work I can stand behind.

There is also friction I want fixed. During this task, I had to ask whether research was still happening. It was not. At another point, I had to prompt it to continue an interview. I also spent time reconciling inconsistent task and document statuses.

Those interruptions do not make the work better. Once we have agreed on an action, I want it executed and verified. I should not have to keep reminding the agent to continue.

There is a fair distinction in my own prompts, too. If I ask “Thoughts?” about changing a page, an answer discussing the change is reasonable. Following that with “Do it” is me moving from discussion to execution. I cannot count every two-step exchange as an execution failure.

Less Claude-Speak Helps

Here is the kind of sentence I am tired of:

You were half right, and the half you were right about matters more.

Just explain what was right and what needs correcting.

I find myself removing much less of this with Astra. It still adds unnecessary material sometimes. In the delivery work, I had to remove commentary about our drafting process from client-facing pages and bring examples back to what I had actually asked for.

But overall, I spend less time fighting the voice. That matters when the output is supposed to sound like me.

How I Want to Use It

My goal is to produce research-backed consulting work that reflects my judgment, with Astra handling the investigation, drafting, and execution under clear direction.

The workflow I am taking from this weekend is:

Start with the actual source material. Supply the scope, notes, client questions, and existing work. Keep client requests, my recommendations, and the model’s suggestions distinguishable.
Research a specific question. Ask for evidence that could change my mind. Keep the supporting research available without turning every client document into a research dump.
Work through decisions I do not understand yet. Ask for concrete examples and tradeoffs, then decide one piece at a time. A recommended answer is not my approval.
Give it a bounded action. Once the direction is settled, name the document or deliverable to update and what finished means. Let it carry out the work.
Review the result for meaning. Check the facts, ownership, scope, implied promises, and whether the recommendation is actually mine. Check that related tasks and statuses agree.

I like both models. I still prefer much of the Claude experience, and Fable gives me the quality I want. Astra is giving me comparable quality for this work, less Claude-speak, and more room to keep going.

More intelligence would have to make a practical difference to my work for me to care. Right now, I would get more value from this level of intelligence being cheaper, faster, and available for more of my working week.

Anyone else feeling the same? How are Astra and Fable comparing for your workflows?

If you or your team feel left behind and unsure about what to do, you are not alone. My team and I at Elios are here to help. Let’s talk.