Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

charlesazam.com

Post reply on HN
Print view View original

51–60 of 134 posts

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

#51

Post by hungryhobbit »

brap wrote: post #36
swader999 wrote: post #12

Earlier quoted context omitted.

On Claude if you start with that, it won't stop until it achieves or exhausts your prompt. It feels like "here's your mission, go do it". I use it a few times a week.

> won't stop until it achieves or exhausts your prompt This is overselling it. In all implementations of this that I’ve seen, a more correct phrasing is “won’t stop until it pinky-promises it achieved your goal”. It usually relies on something like a hook that refuses to let the agent stop unless it includes a “promise sentinel”, which is basically the model having to include “I swear I’m done” in the response (usual…

The key thing is that normally Claude grades Claude's work, so you do get a"pinky promise, as all of Claude's training bias tells it to plunge ahead (even if that means "fixing" a test by commenting it out).

With /goal, a different Claude instance evaluates the goal. This is the robust version you described, and such an "adversarial Claude's" approach, with or without/goal, is exactly how you avoid pinky promises (from one Claude).

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

#52

Post by 9dev »

swader999 wrote: post #12
tantalor wrote: post #10

What is /goal?

On Claude if you start with that, it won't stop until it achieves or exhausts your prompt. It feels like "here's your mission, go do it". I use it a few times a week.

I'm way too afraid of a "paperclip problem"-style target overfitting to use it really; how could I even describe a goal so well it doesn't sacrifice other things that are important to me? Like, if my goal is to make an endpoint faster, will it create an over-engineered mess out of the clearly readable code I have to reach that goal?

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

#53

Post by robwwilliams »

beefsack wrote: post #32
Androider wrote: post #30

Earlier quoted context omitted.

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 find…

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…

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.

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

#54

Post by hungryhobbit »

jascha_eng wrote: post #38
swader999 wrote: post #33

Earlier quoted context omitted.

It's useful for things where it just needs to get through to completion. Long running tasks. I walk away and expect it to be done without pausing for input.

Can you give an example? And more curious about what you do with the resulting code afterwards I imagine its gonna be a big chunk then?

I feel like "do X untill tests are green" is sort of the prototypical /goal case.

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

#55

Post by tony_cannistra »

brookst wrote: post #26
jswny wrote: post #19

Earlier quoted context omitted.

Unfortunately I’ve used Claude and GPT models for a long time in a variety of harnesses and I agree with you and I think it’s the compaction. For some reason, codex compaction is like black magic. I’ve never felt like I can just one one continuous thread with other models, Claude I carefully curate when I compact

Compacting at all is a mistake. With 1m context window there is no reason for a single task to require compaction. Much better to spend tokens breaking the task into chunks, documenting and storing them durably, then executing each one in clean context and just /clear after. It’s a similar concept to compaction, just planned in advance. Much much more effective, and doesn’t burn tokens and time (“wall-clock”, Claude)…

This is the way.

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

#56

Post by robwwilliams »

IceDane wrote: post #22
Tenoke wrote: post #17

Claude seems to forget what you tell it in very long work sessions (things that take weeks to develop), no matter how many times you tell it which part is extra important. I dont use goal (I guess I should), but presumably it makes it actually remember the most important instruction. I believe this here is about shorter sessions where the issue doesn't crop up as much.

Stop using compaction. Stop treating sessions as something you keep alive for weeks. Set up a proper workflow for handing off work and start handing off well before maximum context is hit. It's less efficient, slower and more costly to constantly be sitting at high context and compaction is just not good.

There is no one-size-fits-all, even for programming.

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

#58

Post by sreekanth850 »

Anthropic is losing bigtime against Open AI in coding space. I was using Claude code upto last march. Not an enterprise customer, but a responsible AI user where i don't over spend and use basic plan to manage repository with 400Kloc all together. We sell to local government and a team of 3. Claude code was super slow, never able to fix issues properly.(Despite with proper test cases, observability, documentation and layered architecture). After moving to codex, life has been much easy and free form usage anxiety. Now managing entire things with 2 codex plus account per team member. Its high time anthropic should stop scare mongering and build efficient models. Everyone doesn't need Fable. People need models that solve problems efficiently.

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

#59

Post by gmac »

sreekanth850 wrote: post #58

Anthropic is losing bigtime against Open AI in coding space. I was using Claude code upto last march. Not an enterprise customer, but a responsible AI user where i don't over spend and use basic plan to manage repository with 400Kloc all together. We sell to local government and a team of 3. Claude code was super slow, never able to fix issues properly.(Despite with proper test cases, observability, documentation and…

I've found Opus 4.8 pretty amazing, and Codex a bit meh. YMMV?

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

#60

Post by IceDane »

robwwilliams wrote: post #56
IceDane wrote: post #22

Earlier quoted context omitted.

Stop using compaction. Stop treating sessions as something you keep alive for weeks. Set up a proper workflow for handing off work and start handing off well before maximum context is hit. It's less efficient, slower and more costly to constantly be sitting at high context and compaction is just not good.

There is no one-size-fits-all, even for programming.

There's a good way and a bad way to use tools. My suggestions were based on my extensive usage of the tools in question.
Post reply on HN