Joe Pindar

Asking ‘Why?’ and listening intently. Avid @swardley mapper. #nohype

[Joe Pindar @joepindar]

The hardest part of strategy is #execution. Without it your #strategy is simply a good idea.
What are you doing to execute? #MondayMotivation

[Joe Pindar @joepindar]

This is in reference to Claude Code… using Opus 4.5.
But I’m seeing the same with all of @AnthropicAI’s 4.5 models with @cursor_ai.
Monitoring the thinking output I see a breakdown when the context window is almost full; preferring to save tokens at the expense of doing the task

[Marc @MarcJSchmidt]

It started lying constantly "Has been implemented!" / "FOUND THE BUG!", but it
- Implemented workarounds
- Simplified tests
- REMOVED TESTS
- Refused to write tests
- Ran only a subset of tests
- Removed features to make others work
- Regressions framed as "preexisting"

[Joe Pindar @joepindar]

@ZackKorman @fabsx00 It’s all the tech we had back in 2014… especially at conferences put on by drunk German geeks over the Christmas holidays… 🎄🤣

[Joe Pindar @joepindar]

The most overpowered prompt in AI...
At the end of a conversation, ask:
Based on what we have just done, how could we have worked better together? What information should I have shared earlier? What critical details were unclear to you for too long?
#alwaysImproving

[Joe Pindar @joepindar]

@ZackKorman Yes. I see it.

I seem to spend most of my time constraining AI brain-farts… because the agent suddenly has a “great idea” (or fractionally different context).

[Joe Pindar @joepindar]

Sounds to me like a need for:
1) More orchestration…
2) Less AI…
I always start as small as possible, then expand the scope of an AI micro-agent until the eval %s start to drop off.

Start too big and the uncertainties cannot be tamed in retrospect.

[Zack Korman @ZackKorman]

Yesterday I wrote a thread about AI threat detection, and today I woke up to ten different alerts where Gemini said “I’ve decided this isn’t a threat, so I’ll return false” and then returned true anyway. So maybe y’all are right AI sucks

[Joe Pindar @joepindar]

I’ve been through 2 deep optimization cycles.
And reduced my token usage by ~40%.
Currently, I only with @cursor_ai 8-10 days per month…
because the ultra package doesn’t include enough tokens.
Agentic coding is not constrained by the models…
It’s constrained by energy.
#jevons

[Joe Pindar @joepindar]

I am not a competent coder.
I am a product guy…
But @cursor_ai + @claudeai make my ideas real.
I have standards - code quality & test coverage.
The cost?
50-125 million tokens per day.
Roughly 1-2 billion per month.

[Joe Pindar @joepindar]

Currently building AI like soil builds fertility…
But that’s a story for another day.

[Joe Pindar @joepindar]

@ericzakariasson @cursor_ai A prompt improvement optimizer…
Plugin: “you’re doing X a lot… do you want me to create a new rule so I will do it automatically in future?”
Plugin: “I can save 30% token used if i use JIT context priming. It will slow the completion time by 7s. Do you want me to do that?”
etc

[Joe Pindar @joepindar]

Hmm… @cursor_ai’s planning mode is not good enough… yet.
I still need to use my own planning SOP…
But the past 2 releases have increased agentic dev’s self-control so much that I barely need to tend a 40 minute dev task. 🔥

[Joe Pindar @joepindar]

In the last month, 10 days of dev used 396M tokens…
And that was after 2 rounds of token use optimisation.

[Joe Pindar @joepindar]

What is a normal token usage on @cursor_ai?
Over 40 days of dev, I’ve used 1.75B tokens as a solo developer… (88% cache reads).

[Joe Pindar @joepindar]

@swardley @GBNEWS @DailyMail @TheSun Trusted and biased are not the same thing @swardley…
Accuracy vs precision…
Systemic error vs random error…
It’s all the same thing.

[Joe Pindar @joepindar]

@benln @benln Do any of the devs at the London Cursor cafe work on the agentic code generator size of the product? Would love to speak to someone about the changes you’ve made over the last few weeks and where you’re heading.

[Joe Pindar @joepindar]

Algorithms WORK in complicated domains.
Agents LIVE in complex domains.
Use the right tool for the job.
#ai #hybrid

[Joe Pindar @joepindar]

@ctrl_alt_focus @obsdmd All good. I suspected it may be a life happening situation. Let me look at some alternatives - and loop back with a contribution if it is still the best way forward. 😀👍

[Joe Pindar @joepindar]

@swardley @elonmusk 🤔
If NASA hadn’t signed a contract with SpaceX… it would have gone bust.
That could be viewed as a bailout.

Equally NASA needed a service and tendered a contract.
That could be viewed as a vendor supplying what the customer needed.

1 event, 2 interpretations - neither untrue

[Joe Pindar @joepindar]

@swardley Does it make them American Oligarchs?