Comment by tedggh
11 hours ago
I use both Claude and Codex and don’t see any meaningful difference between the two. My use case is modeling semi complex physical processes (energy and manufacturing) in code for simulations. I also have to do a good fair of automation via scripting in Python or PowerShell for manipulating data as well as legacy code analysis (C, Fortran, COBOL). Given I provide the models with the information and documentation they need, both perform very similarly. I recently did a full codebase review (for design patterns and vulnerabilities) and both Codex and Fable agreed 100% about the most critical findings. I do very little front end development, although some of my automation scripts have TUIs and again no problem with either Claude or Codex generating them for me. At this point I go with the less expensive, which seems to be Codex. With the $100 plan I rarely hit the limits. With Claude I max out my plan in about 4-6 hours of work.
Did you find much of a difference between Fable and Opus?
Yes. Fable is much more organized and consistent at taking small bites of the (sorry) apple when solving a problem. Specifically I'm talking about a machine learning problem I'd been working on for awhile with Opus and it was (and is, again) constantly stating that all the signal is exploited, everything is now overfit, etc, etc, etc. The first day I pointed Fable at the situation I got a 10% improvement by paying attention to the little details that Opus instead took slightly negative results and extrapolated to "fully exploited". I've had to drop back, again, to forcing Opus to explain what it's looked at and the detail it has quietly assumed away.
It's like the difference to talking to two smartest kids in a class, but one really belongs a grade higher - and the other hasn't learned yet to ask the questions that encourage it to dig in that little bit more for the additional multi-order effects.
Had a very similar experience. Opus went "look, t-sne shows your features are neatly clustered" (it didn't) and left it at that. Fable didn't fully explore the problem/data, but it did go much further, implementing models to check for correlations and adjust feature clusters. Opus was able to finish the job after Fable was cut, but required much prodding (doing exactly what you described: pointing it towards things that look off and asking it, are you sure that's all there is to this?).
I have used Fable only once to do an in depth codebase review of a complex system. I asked it to flag deviations from a particular design and also compile a list of vulnerabilities. It took about 15-20 minutes. The result was very similar to Codex for the most critical findings, different suggestions on how to address them but it found exactly the same critical issues as Codex. This is still not a good test to evaluate Fable. But my feeling is that the latest models are all pretty good and now it comes down to your personal setup and workflow, that’s where you can get the productivity gains IMO. It’s like picking between MacOS or Windows as development environment. For some Windows sucks and for a some is the opposite, but both groups of people can be equally productive if they know their environments well and know how to go around their respective limitations.
I constantly hit safety blocks in Fable (I’m trying to write secure software, which is equivalent to finding security holes, so banned).
I didn’t use it on big enough tasks to notice any improvement.
I had been hitting plan limits pretty regularly, but fixed it by changing my workflow. That also increased the success rate of claude by an order of magnitude.