> which failed to drive chrome so it wrote its own chrome driver protocol server
This is one of the things I hate the most. Super complicated workarounds which take loads of time (and sometimes money) for even the simplest problems. Human would pause and ask. I would blame harness, not the model though.
It obviously is? See above. Or do you not feel the clarification is important? AI being able to solve things no human bothered to try is great, but it is very different from AI solving things humans tried to solve and failed. And the latter is what pops to mind seeing these titles.
Are we in an age where no one even bothers to open the product pages they generate? The first subtitle with the font color almost matching the background. Or it's even worse that a human looked at it and said "yep, that's OK"?
I'm viewing the site on lightmode, clicked one of the #links which scrolled down the page, when I scrolled back up all the sections lost their content and were unusable.
I've never seen someone fail a static page like this. And from a huge company like Cloudflare too..
People are really bad at acknowledging a mistake so they rather double down. It's way past anything rational, it's a cult. Doesn't matter what the leader/party does, it's always okay.
There's been a huge step up in basically everything going from intel to apple silicon. It's not a comparable hardware in any sense, and as such, it really does feel like it became a paperweight? I know I never wanted to see an intel macbook ever again the moment I tried M1. It's maybe hard to comprehend how different it is if you haven't used both. And at the same time I'm happy with my x86 desktop for 10+ years. Only thing that really improved in that span was storage.
So I wouldn't say this applies globally to apple users/products, but the post-intel era is a special case. If nothing else, they are helping the environment by not feeding that (literally) hot garbage with more electricity.
Smartphones are worse computing devices than laptops or desktops. Smartphones are also the most widely-used computing devices in the world, even by people sat at home with a better computing device on the other side of the room. History suggests worse just doesn't matter in the face of convenience.
(not op) It cannot be used to develop applications. Every application needs to be secure in some way, and any such mention in a review triggers Fable's upsell feature.
Agreed. I was trying to get it to review some auth refactoring in my app recently, and it appeared to find some vulnerabilities. as it was aggregating the results it was flagged and restarted the whole process with Opus 4.8 and all of my usage credits were gone.
Anthropic told me to use their `security-review` tool - as this was the exact scenario the tool is for - and it still got flagged.
I never actually managed to use fable successfully even once on a pretty standard mvc/microservice app.. It would always find the endpoint permission checks and revert to opus 4.8.
I also had glm 5.3 flash fix an issue that opus 5 could not solve. glm took 4 times as long and a sub-agent tried to cheat (sleep; echo ...), but in the end it actually solved the issue. opus 5 never figured it out.
I think the safeguards might be cooking the anthropic models.
I've been testing Fable 5.1 for about 6 hours between last night and this morning and it's performing pretty good overall, including tackling a previous IT sec audit I had ticketed, and completely analysing the codebase looking for vulnerabilities, generating a comprehensive report and splitting it into tickets. So far so good on that front.
Weird. I'm using it to do a bunch of work on something that manages security rules, with a bunch of sample data with spooky scary fixtures all over with "Mimikatz" and "CobaltStrike Beacon" and "Crowdstrike EDR" type stuff everywhere, including work to harden my system, and I've never been downgraded.
The OP doesn't appear to know what they are talking about. Fable can absolutely be used to develop applications. It's just that for security stuff I use Opus 5. Which is fine for most use cases.
This is one of the things I hate the most. Super complicated workarounds which take loads of time (and sometimes money) for even the simplest problems. Human would pause and ask. I would blame harness, not the model though.
reply