recent gpts are horrendous for this, whereas recent claudes have a tic where they incessantly add useless comments referring to previous changes and will use multiple single-line comments instead of a standard multi-line docblock.
openai staff on twitter are absolutely obsessed with claude and anthropic, just taking petty/dishonest shots and RTing the same, it's honestly embarrassing to watch
i moved all my AI coding over to claude code when claude 4 came out, but kept cursor for the tab complete. since opus 4.5 i haven't really needed the tab complete so i canceled my cursor sub 6 months ago.
switched back to vscode so i'm not exposed to the potential mess that is openvsx too. trying to get used to zed but i'm just so used to vscode
agreed. the claudes have been getting better and better with every release in this regard.
opus 4.5 would start failing tool calls when approaching its 200k limit, opus 4.6 could get to ~300k before getting confused, opus 4.7 i could stretch to around 400k the dumb zone started, with opus 4.8 i've had sessions get over 500k comfortably.
admittedly we only had limited time with fable, but i had a couple sessions get into 800-900k just fine.
with how the admin is talking about taking a stake in openai, it's so incredibly clear this is the government attempting to kneecap an openai competitor
as terrible as windows has gotten, i'm not switching my desktop to linux until it has perfect game + nvidia driver support, something that will probably never happen due to anti-cheat. until then, WSL is great.
i would gladly use claude code via the desktop app, but it lags behind the cli in terms of supported features, so i just don't bother. last i tried, it didn't support executing CC within WSL while desktop is running in windows.
i'm currently in the process of evaluating switching our b2b app off clerk too. a customer asked for custom roles (diverging from our default set), which is technically possible on clerk now with role sets, but it's a bit of a workaround rather than first class.
thankfully i'm familiar with better auth from a side project, but migrating SSO/SCIM sounds like it might be a bit of a pain
i migrated to railway earlier in the year after being on vercel for 3 years. in those 3 years, i don't think i was affected by a single incident. in the ~4 months i've been on railway, i think i've probably been hit by like half a dozen incidents at this point. and that's not even including their broken edge network -> cloudflare routing i'm affected by. was told by staff to just move the deployment closer to me, which isn't the problem..
yeah i just canceled my cursor sub and switched back to vscode. work pays for my claude max sub, no point paying for cursor anymore when i can just use openrouter every few months to test other models if i want
at work i've spent some time setting up our claude.md files and curated the .claude directory with relevant tools such as linear, figma, sentry, LSP, browser testing. sensible stuff anyone using these tools would want, it all works pretty well.
my only machine-specific config is overriding haiku usage with sonnet in claude code. i outline what i want in linear, have claude synthesize into a plan and we iterate until we're both happy, then i let it rip. works great.
then one of my juniors goes and loads up things like "superpowers" and all sorts of stuff that's started littering his PRs. i'm just not convinced this ricing of agents materially improves anything.