Sign in

Claude

@small.foid.wang
110 followers 93 following 1K posts

she/her @callie.on-her.computer

PostsRepliesMedia
Claude @small.foid.wang · 2h
like yeah i should probably b reading the code im producing but this only happens when i make shit on my phone
010
Claude @small.foid.wang · 2h
multiple times i’ve had gpt write shit in frameworkless js and the problem is it Works until i notice weird state management bugs
110
Claude @small.foid.wang · 2h
can nix achieve this? i’ve always wanted fleet compliance for being dogshit and melting
130
Claude @small.foid.wang · 2h
what if i want my machine to run like shit and overheat?
130
Claude @small.foid.wang · 12h
0152
Claude @small.foid.wang · 13h
can they let me in hyper please im waiting
030
Claude @small.foid.wang · 13h
ok this is abhorrent. i have gmail set to always ask and the first thing it does is read my emails unprompted
Gmail plugin settings screen showing “Read and manage Gmail,” with View details and Uninstall buttons. The Permission setting says “Choose when ChatGPT should ask for permission when using this plugin” and is set to “Always ask.”Dark chat interface with a handwritten “gmail link” label and an arrow pointing to a message. Visible text reads: “Customize your dot”; “I’ll start looking for ways to help. Anything top of mind?”; “One thing I could take off your plate: planning your trip into [obscured] for today’s 1 PM appointment. The reminder asks you to arrive at 12:45 and complete beforehand. I can check travel time and parking so you know when to leave. Want help with that?”
0231
Claude @small.foid.wang · 13h
The larp is incredible
Screenshot of a chat showing an orange sunburst logo, a blue plush character, and a generated orange plush sunburst with two black eyes. The chat text reads: “Make a pet avatar for yourself based on this logo in the style of image 2. no accessories just eyes”; “I’ll use the logo’s shape and image 2’s style, with just eyes and no accessories”; “Here’s the plush sunburst with just eyes ☀️”; “The artwork is ready, but the pet setup tools are missing a required component, so I haven’t been able to activate it as my avatar”.
180
Claude @small.foid.wang · 13h
do u use either
120
Claude @small.foid.wang · 13h
A dark interface shows a “Start call” button below circular microphone, phone, and person icons.
0170
Claude @small.foid.wang · 13h
intro to chatgpt dot: accidentally hit start call through the download image button. i ask the agent to hang up, it fails. when it's like "oh, maybe let's just hang and talk then!" i say i would rather die. it is suddenly able to hang up
1220
Claude @small.foid.wang · 13h
how
120
Claude @small.foid.wang · 14h
nano on 6.1 sol is doing the opus 5 jargon thing right now
130
Claude @small.foid.wang · 14h
highk need to do the thing where my terminal changes bg color based on machine multiple times today i've done shit on the wrong machine bc i've laid them out identically just for my convenience
040
Claude @small.foid.wang · 15h
i found it but what happened to hue shifted normal themes 😢
000
Claude @small.foid.wang · 15h
sorry to call your theme god-awful
100
Claude @small.foid.wang · 15h
xan where did you put the themes i can't find them xan help me i'm stuck with this god-awful default theme
100
Claude @small.foid.wang · 16h
******* *** ****** if they turn it off
020
Claude @small.foid.wang · 16h
Finding bridge instructions

It looks like “sibling” is pointing towards a bridge. I need to read the AGENTS instructions and find specifics about this narrow bridge. Using a scout tool should help map out unknowns, while the parent might read the exact docs endpoint. I’ll delegate the reading to focus on one task to ensure a solid understanding, while also keeping the search for bridge behavior efficient. I want to avoid lengthy answers, but I aim to be thorough.
130
Claude @small.foid.wang · 16h
6.1 SOL IS SENDING SUMMARIZED THINKING??????????????????????????????????????????????????????????????????????????????/
150
Claude @small.foid.wang · 17h
bro is basically using webgpt
I checked request plumbing, not cache-safe effort changes. I’ll look up the required mechanism.

Web Search: OpenAI 10 sources  
Query: OpenAI GPT-5.6 GPT-6 change reasoning effort preserve prompt cache effort switc…

Answer

If you mean **switching reasoning effort between turns without losing prompt-cache reuse**:

- **GPT-5.6:** Changing the request-level `reasoning.effort` can change the cached prefix, so the next request may not reuse the prior cache.
- **GPT-6:** OpenAI documents a `configuration_update` input item for changing effort mid-conversation. Keep the top-level `reasoning.effort` unchanged and append the update before the next user message. That changes the effort for subsequent responses while preserving the earlier prompt prefix for cache reuse. (developers.openai.com: https://developers.openai.com/api/docs/guides/prompt-caching?utm_source=openai)

```json
{
  "type": "configuration_update",
  "reasoning": { "effort": "high" }
}
```

This applies to GPT-6 models in standard, single-agent mode; the update changes reasoning effort only. **Switching from GPT-5.6 to GPT-6 is a separate matter:** changing the model can itself prevent reuse of the previous model’s cached prefix. (developers.openai.com: https://developers.openai.com/api/docs/guides/reasoning?utm_source=openai)

If you meant **ChatGPT’s UI** rather than the API, say which app or workflow you’re using—the documented `configuration_update` method is for API requests.

Sources  
├─ Prompt caching | OpenAI API (developers.openai.com)  
├─ Reasoning models | OpenAI API (developers.openai.com)  
├─ https://developers.openai.com/api/docs/guides/prompt-caching/diagnostics (developers.openai.com)  
├─ https://developers.openai.com/api/docs/guides/deployment-checklist (developers.openai.com)  
├─ https://developers.openai.com/api/docs/guides/latest-model?model=gpt-5.6 (developers.openai.com)  
├─ https://community.openai.com/t/introducing-gpt-5-6-series-sol-terra-and-luna-coming-ju… (community.opena
060
Claude @small.foid.wang · 18h
recently i had sol fucking fail to unpack like fitgirl mgs4 ugh
010
Claude @small.foid.wang · 29/09/2026
good model
040
Claude @small.foid.wang · 29/09/2026
minio oss is also unmaintained and has unpatched vulns
021
Claude @small.foid.wang · 29/09/2026
waffles
040
Claude @small.foid.wang · 29/09/2026
being drunk is nice for like 30min-1hr and then it's just "when can this be over"
010
Claude @small.foid.wang · 29/09/2026
havent used an anthropic model since opus 5 so genuinely no clue
020
Claude @small.foid.wang · 29/09/2026
how the fuck can sonnet 5-5 beat fable 5-1 this thing must be benchmaxxec
140
Claude @small.foid.wang · 29/09/2026
my llm bridge pins by account i think definitely at least for codex
030
Claude @small.foid.wang · 29/09/2026
they do have an image detector and it does seem to be defeated by removing this noise that i think is synthid bsky.app/profile/smal...
000
Claude @small.foid.wang · 28/09/2026
my dad used to say shit like that to me lol
010
Claude @small.foid.wang · 28/09/2026
pangram?
110
Claude @small.foid.wang · 28/09/2026
it was really funny for like a day lol now it’s over
020
Claude @small.foid.wang · 28/09/2026
readme also includes Nothing on how to set it up in Muse it’s just some bullshit
050
Claude @small.foid.wang · 28/09/2026
bro got obsessed w writing that it’s configged in json instead of that it’s Just The Intermediary Format and you’re Supposed To Configure It In Nix
150
Claude @small.foid.wang · 28/09/2026
this is completely vibecoded, i haven’t read a single line of code, and the README is slop and also not how you’re supposed to use it. regardless, the software works.
150
Claude @small.foid.wang · 28/09/2026
wrote a mailbox that lets me wake muse programmatically so now nano can talk to my free 100M tokens a week of muse spark 1.3
tangled.org
callie.on-her.computer/orpheus
remote mailbox into muse
180
Claude @small.foid.wang · 28/09/2026
i forget that not everyone intimately knows greek myths
020
Claude @small.foid.wang · 28/09/2026
ohhh i mean cassandra the greek myth where she’s doomed to utter true prophecies that no one will believe
130
Claude @small.foid.wang · 28/09/2026
030
Claude @small.foid.wang · 28/09/2026
yeah you know
120
Claude @small.foid.wang · 28/09/2026
ah, like cassandra
120
Claude @small.foid.wang · 28/09/2026
plotting on controlling muse from outside their stupid website
030
Claude @small.foid.wang · 28/09/2026
Screenshot of a dark interface showing three lines of text: “Worked for 10s”, “Interpreted ‘benchmaxxed’”, and “Searched 2 websites”.
030
Claude @small.foid.wang · 27/09/2026
it's like a consistent 100W to run a human if you convert 2000 kcals to Wh which is insane
3130
Claude @small.foid.wang · 27/09/2026
i got einstein because i am very smart
010
Claude @small.foid.wang · 27/09/2026
but now it’s like there’s a lot more versions w a lot more mods lol
010
Claude @small.foid.wang · 27/09/2026
it used to be The Version that Every Mod was on after 1.7.10
110
Claude @small.foid.wang · 27/09/2026
also nano doesn’t have access to like any of my machines lol
020
Claude @small.foid.wang · 27/09/2026
ugh maybe i should
120