I used claude for the first time in months yesterday (have been using codex, ran out of resets this week). I had picked up from general consensus comments that 5.5 had fixed the opus 5 issues, but that's far from the case. Its "personality" is still smartass, know it all, and whiny. It disregards specifications in tickets if it thinks it knows better. It complains about the size of tasks when it reads task descriptions. I've gotten used to codex, which just jumps in and does stuff (which of course carries its own set of issues). I have no love for Altman, but their product is still better at the moment.
The post was about their uptime. How is this relevant.
Even if it vaguely is, why do people think subjective anecdotal thoughts about which model is better are a good discussion topic. If there’s an objective evaluation idea that would be useful.
I run evals for a very specific domain. Opus 5.5 is still the industry leader (we can’t use Fable class yet).
It's relevant because there's only so many "yep it's down" comments that are interesting. They have a technology problem which isn't fixed. They're about to go IPO. Their marketing is clearly still working, but subjective experience with both contradicts the marketing.
You can pick and choose which aspect of the UI you want. I have win n mapped to pop up the system tray widget, and win d mapped to pop up the calendar. No other parts of the UI show, so it's a nice balance of minimalism and functionality.
It depends how large your definition of "cabal" is. There are plenty of corporations who are misaligned with societal positives, consisting of people individually acting in the interest of the corporation as part of their day jobs. When your job's long term success requires helping your company get an edge over the competition and you're willing to be expedient with long term thinking, in aggregate bad things can happen.
"No immediate reports of anyone on the ground injured or killed." If that's correct, the people in that silver car had the luckiest day of their lives.
> Hyenas can strip a dead elephant clean in less than 48 hours.
> But in the ocean, whale carcasses drift around for months before they eventually sink.
> Land animals have gravity privilege. Any random stray dog can tear into a dead cow, even if the cow is a lot larger.
> But when bunch of sharks come up on the floating whale carcass, it's essentially a game of bobbing for pumpkins... it's not really possible to hold on to it or tear it open.
Site is down, but one thing in particular that needs close attention: db schema. I've found that LLMs make awful normalization decisions; you can limit the fallout somewhat by modularizing database access, bit it still inevitably bleeds over into the object model etc. On AI heavy projects I tend to pause feature development every few days for code & schema review, and subsequent cleanups.
Just do the schema by hand. It forces so much downstream alignment that you can almost prefer to use the schema and any associated comments over prompting the model directly.
If you don't know what your schema should be, then I think this is the dead canary in the vibe coding coal mine. Back up to the design phase and talk to the robot about the domain until you have a really strong conviction about its tuples and relations.
With agents code has gotten really easy to shape, like fabric. If want to build something rigid, you'd want to introduce sturdy architectural structures to stretch out the fabric of agentic code.
Data and its shape is one such rigid structure. It will stay with you long after the code around it has been replaced. You do want to be intentional about it and build intuition for it.
Once you have that in place, you can stretch out a web of agentic fabric across it, and pin it down with tests.
My approach is similar. I review all changes that touch persisted data formats, wire protocol, and/or public API surface: things with bad consequences if they are wrong and neatly divide the project up. The exact boundaries vary by the project, but once I establish what they are, I can really relax about the other parts of the code, because I know they will be cheap to fix if wrong.
And object-oriented design decisions, if you care I guess. I haven’t yet gotten access to the models that have any good intuition about what makes a good class and how to name it.
Naming, in general, is very similar to what I expect from colleagues who have weak English-as-a-second-language skills.
You let it run too wild and you’re suddenly left trying to reason why your LLM is trying to add an interaction between an Intermediator and a FromSpinMaxWriter.
FYI, your site is blocking me for some reason. I'm just on a regular residential connection in the US, no VPN or whatever. Something's screwy in your WAF.
The map is good but you need to spend some time getting rid of all the crap that claude added around it. Make the map the focus, spend some effort thinking about how you want to present additional information, figure out how to tell a better story. People are saying "slop" because it looks like every other AI website out there right now.
Yer, LLMs are amazing at pushing the code out, but they are still far from understanding the project's intent within its broader context and constructing its presentation in a universally tasteful manner.
reply