Lu Nelson

Member of Technical Staff at HASH GmbH, Berlin. 🇨🇦 🇫🇷 🇩🇪

[Lu Nelson @lunelson]

@en_JS We describe this as "epistemic" planning —evolving belief state, working against a horizon of uncertainty— instead of the "instrumental" A-Z straight-path planning mode which IMO is largely an extension of AI marketing stunts (one-shots, etc.)

[Lu Nelson @lunelson]

@nickbaumann_ @cline Got it. I guessed that it was a tool name 👍

[Lu Nelson @lunelson]

@mattshumer_ A bit more of a sledgehammer approach but these are some that I worked up today https://t.co/SNNoYDcrm3

[Lu Nelson @lunelson]

@catalinmpit @shaykharr I compiled some new core prompt patterns today with these concerns in mind: https://t.co/SNNoYDcrm3

[Lu Nelson @lunelson]

@mattpocockuk A lot of solutioneering here with " use @windsurf_ai " or " use @thankscline "; but you do gain a lot of insight about rules and prompts by comparing. — e.g. Cline IMO has a fundamentally better system prompt with its "Plan" vs "Act" modes, and you can port some of that back

[Lu Nelson @lunelson]

@mattpocockuk @outoilkka You can, and very powerful is also to use it to force certain behaviour patterns. The @thankscline community has innovated a lot on this (they also have .clinerules) — e.g. for forcing the LLM to maintain a "memory bank"

[Lu Nelson @lunelson]

@jahabeebs @mattpocockuk @outoilkka Is it really deprecated? They serve different use-cases: .cursorrules is appended to every query; whereas .cursor/rules/*.mdc files are chosen by the agent based on glob and description. So the former remains good for any absolute patterns or rules you want the LLM to follow

[Lu Nelson @lunelson]

@mattpocockuk @mayowaoshin Otherwise you can do some context documentation about what files are relevant to which concerns, e.g. as a tree diagram with comments, or you can try writing glob-based rules for this in .cursor/rules/* with specific @-mentions

[Lu Nelson @lunelson]

@mattpocockuk @mayowaoshin In chats, there's the "codebase" option (cmd-enter) when starting (it will search to discover what's relevant); agent sessions are supposed to figure it out on their own apparently

[Lu Nelson @lunelson]

The @cursor_ai blog details a new autocomplete model in the 0.45.0 update... anyone got this yet?

https://t.co/Dg9fvrNmPp

[Santiago @svpino]

AI coding replacing programmers is the modern version of calculators replacing mathematicians.

[Lu Nelson @lunelson]

🦋

[Lu Nelson @lunelson]

@uixmat Telephone numbers!

[Lu Nelson @lunelson]

Someone please drop a really big cardboard box in to the Serengeti National Park, so I can see if lions will climb in to it

[Nature is Amazing ☘️ @AMAZlNGNATURE]

Whether wild or domesticated, a cat’s gonna cat.

[Seth Abramson @SethAbramson]

This video is incredible.

Everyone should RETWEET it so the whole *world* sees it.

[God @TheTweetOfGod]

I’m done blessing America. I’m moving on to Canada. It’s less needy and has better poutine.

[Alex Proyas @alex_proyas]

Hey Elon, Can I have my designs back please? #ElonMusk #Elon_Musk

[Lu Nelson @lunelson]

I wonder whether @datocms had these issues getting started? Or did you get profitable fast enough to avoid it?

[Alessandro Riolo @aledeniz]

When I tell this story, all Americans 🇺🇸 and most British 🇬🇧 don’t believe me.
Italy 🇮🇹 cannot have startups by design. This is due many items, starting with the untranslable “studio di settore”.
The 🇮🇹 tax authorities assume that given x company assets you MUST make a profit 1/5

[Lu Nelson @lunelson]

@stolinski Fastmail