Hacker News: pdantix

New comment by pdantix in "GPT-5.6"

pdantix — Thu, 09 Jul 2026 20:15:49 +0000

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.

New comment by pdantix in "GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday"

pdantix — Wed, 08 Jul 2026 07:56:24 +0000

i already found his clear shilling of nextjs a bit distasteful, but his whole gpt-5 thing really just made it clear he's just not worth listening to.

New comment by pdantix in "Claude Code is steganographically marking requests"

pdantix — Wed, 01 Jul 2026 06:00:49 +0000

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

New comment by pdantix in "Codex logging bug may write TBs to local SSDs"

pdantix — Mon, 22 Jun 2026 21:50:18 +0000

> Nor is there a setting to disable/change it.

https://code.claude.com/docs/en/settings#available-settings

`cleanupPeriodDays` has always existed.

New comment by pdantix in "SpaceX to buy Cursor for $60B"

pdantix — Wed, 17 Jun 2026 10:15:34 +0000

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

New comment by pdantix in "Don't trust large context windows"

pdantix — Sun, 14 Jun 2026 15:14:27 +0000

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.

New comment by pdantix in "There is a shadow hanging over this Fable thing"

pdantix — Sat, 13 Jun 2026 06:39:25 +0000

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

New comment by pdantix in "WSL 2 is getting faster Windows file system access"

pdantix — Fri, 05 Jun 2026 09:48:23 +0000

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.

New comment by pdantix in "Why Ctrl+V won't paste images in Claude Code on WSL, with a fix"

pdantix — Thu, 28 May 2026 07:20:05 +0000

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.

New comment by pdantix in "Anthropic acquires Stainless"

pdantix — Mon, 18 May 2026 22:40:13 +0000

if this is petty, then i'd love to know where openai employees having claude derangement syndrome sits on the petty scale

New comment by pdantix in "From Supabase to Clerk to Better Auth"

pdantix — Wed, 06 May 2026 22:31:39 +0000

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

New comment by pdantix in "An AI agent deleted our production database. The agent's confession is below"

pdantix — Sun, 26 Apr 2026 23:59:22 +0000

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..

absolutely would not recommend

New comment by pdantix in "SpaceX says it has agreement to acquire Cursor for $60B"

pdantix — Wed, 22 Apr 2026 11:25:13 +0000

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

New comment by pdantix in "Anatomy of the .claude/ folder"

pdantix — Sat, 28 Mar 2026 02:30:50 +0000

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.