Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal help?

Re:Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal... by Androider on Saturday July 18, 2026 @10:02AM (#48958249)

Quality degrades long before you hit compaction, compaction is the "Next gas station, 100 miles" sign but you're already in the middle of nowhere.

You don't need to go down the rabbit hole of crazy workflows, but to avoid slop:

- Break down the work into tasks

- New context. Create a plan for one task.

- New context. Implement the plan.

- New context. /code-review the implementation

- New context. Fix the review findings.

- Repeat for next task.

I do this with Fable 5, and the quality is consistently quite good. If the context goes over 50%, the quality will become crap and you end up with 4 duplicates of the same thing across the codebase. Letting a current session review its own work is like asking a student to grade their own paper.

[ Parent | on HN ]

Re:Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal... by beefsack on Saturday July 18, 2026 @10:18AM (#48958398)

For the vast majority of models I've worked with, 150k tokens of context seems like some magic spot. If you can stay under it then the session will stay on track and the agent won't start getting forgetful and weird.

Just like with real work, it's valuable to break down big tasks into small tasks that you can knock over in a single session. When a session does start getting too big, you just need to ask the agent to reply with a comprehensive handover report and paste it into a new session.

[ Parent | on HN ]

Re:Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal... by robwwilliams on Saturday July 18, 2026 @11:52AM (#48959207)

For my quirky workflows I need 100K even to prep Opus 4.8 or higher to begin good work. Not programming, but a complex synthetic architecture for implementing more attentional autonomy for machines.

[ Parent | on HN ]