m88x

WMS, TMS, ERP

[m88x @houndfoundry]

@weirdsoutherner Would take bit more than that for me to move from Bitwig.

[m88x @houndfoundry]

@GZevkov @argofowl In my case, it was heavy, but xheavy wasn’t affected. Also, it seems I am no longer in the nerf zone as I am back to same performance before.

[m88x @houndfoundry]

@elonmusk Tibo should pass -reset- button from his basement to Elon. 100% is just a number..

[m88x @houndfoundry]

188 of my Claude Code sessions last week were in an experiment I never signed up for. No notice, no setting. Just this code in my own logs:

atis = c0e57166b42fa4af

Before 4 Nov and after 8 Nov it's empty.

[m88x @houndfoundry]

@stylessh @t3dotcodes I personally use Granola instead of any built-in dictation because built-in dictations love to cut me off

[m88x @houndfoundry]

Hmmm. Separate step. If the task changes halfway I’d stop and talk the change through again and then fix the ticket/delete the unfinished tickets and write new ones, before any more code.

The review checks against the ticket, so the ticket has to be right. The PRD is a snapshot that goes stale once building starts.
Matt's to-spec docs put it: "If you change direction, delete the unfinished tickets and keep the spec."

https://t.co/5I5qHIr6S1

[m88x @houndfoundry]

Specifikacija tai failas, parašomas prieš kodą.

Pirma idėją išklausinėk su agentu, tada surašyk PRD repozitorijoje arba jei naudoji, githun issue ir suskaidyk į užduotis. Agentas daro po vieną užduotį, pradėda nuo testų, o peržiūra tikrina PR pagal tą užrašytą specifikaciją. Chat’as nėra spec

[m88x @houndfoundry]

https://t.co/vyCWz70Tba

There’s more to that

[Aidan Regan @Aidan_Regan]

Ireland has a weak grid and depends on imported gas. The data centres plugged into it are pushing up your electricity prices. Anyone who says otherwise is fooling you.

[m88x @houndfoundry]

@bot Only US numbers…

[m88x @houndfoundry]

@NousResearch @rootkid Don’t post on your main

[BBC News (World) @BBCWorld]

EU rules on Artificial intelligence devices will apply in NI https://t.co/2MDBVPY5nj

[m88x @houndfoundry]

@joseph_h_garvin Only reason why I still use OpenAI

[m88x @houndfoundry]

@KkCarson92338 @scottstts @pcshipp @JesusIsGod https://t.co/aBrxWctfrD

[Commentary | Codex Update @CodexUpdate]

Confirmed: ChatGPT and Codex will share one usage limit from December.

OpenAI's help page, updated today:
- Plus, Pro and Business get one allowance across ChatGPT and Codex
- Usage is measured in tokens, so bigger models and harder tasks burn more
- Instant chat doesn't count against it
- Combined remaining usage and reset times will show in Settings > Usage
- Hit the cap and you wait, upgrade, or buy credits

OpenAI says most users won't hit resets more often than now. If you run long Codex sessions and lean on ChatGPT too, plan for both drawing from the same pool.

Fair ask to OpenAI: publish the token allowance per plan before December so people can check the maths.

https://t.co/gzafgvNuop

[m88x @houndfoundry]

@KkCarson92338 @scottstts @pcshipp @JesusIsGod Yes. Until December.

[m88x @houndfoundry]

@omarvvvr Spec up handover bridge, watch context during takeover so it doesn’t become a smart zone hog

[m88x @houndfoundry]

@thsottiaux Well, Tibo, you guys need to fix model clutter

[m88x @houndfoundry]

@aiwithadb Cost aspect alone, with $200 subscription, you are getting more than you pay for.