Tommy Pang

read; else chill;

[lauren @poteto]

codebases have always contained slop. we have always been okay with this because code rarely needs to be perfect, outside of mission critical "hard" (eg embedded) software.

swe is a unique form of engineering because you're often building something that constantly evolves and is almost organic - user tastes change, your mental models evolve, and features come and go.

admittedly, i and many others who've been coding for a long time were initially (like back in 2024) skeptical that agents would write production code. "but what about all the slop that would enter our beautiful codebase?".

well, even before, we had human slop, and there was a lot of it! if we're being truthful, most people call "code i didn't write" slop. the reality is that 99% of people (i include myself in that number) don't even know what Good Code looks like, let alone be capable of writing it. i would propose that Good Code is:

• correct
• bug free
• fast and cost efficient to run

it has always been exceedingly difficult and expensive to write truly Good Code, because for the longest time (maybe @bendlang will change that), code was not something you could cheaply and formally guarantee to have all 3 of these properties. this is why writing hard software is much more difficult and expensive, because depending on the use case, you may only get one chance and so you have to be right from the start.

but the vast majority of software we use does not need to be Good Code to provide value to users. in fact, it is very likely that most software we use is not formally verifiable! we accepted some bugs in exchange for velocity and progress, so we rely on tests and o11y instead and have adopted a more incremental approach. this is a good thing!

agents help us move faster, and if you're open to the idea, are capable of helping us write better code. it won't be Good Code (that is still expensive), but it is likely to be much better on average at scale.

the new craft of swe is to figure out how to do this. it's your job now! if your productivity with and without agents is not significantly different, you're doing something wrong. but it's not too late to embrace it and use it as an opportunity to learn a whole new skill tree

[Tommy Pang @tommypang248]

@lydiahallie Can we pin or set the reasoning effort for the agent too? I tried to find the docs but I couldn’t find it on how to pin the reasoning effort for subagent’s model. E.g: I just want to set the effort as Opus medium instead of inheriting from the main agent effort selection.

[Tommy Pang @tommypang248]

@theo Does it starting to have a good taste like Fable?

[Kun Chen @kunchenguid]

i still don’t understand the “local AI is free” point of view

it literally costs thousands of dollars to get started on anything useful, a small data center worth of cost and complexity to do something near frontier

if you sum up all the money spent buying hardware and paying power bill and your time spent fiddling with it, it’s almost decades worth of consumer subscription from frontier labs which give much better intelligence at much larger concurrent throughput

the only reasonable explanation for doing full-on local AI seems:

1. it’s fun
2. it’s cool
3. you really hate the labs

i do think we can look at it in another way - for those who already bought a capable computer, use the idle gpu capacity to do some secondary tasks that don’t require frontier intelligence while you continue to rely on cloud models for primary usage

did i miss anything? genuinely curious if there’s a sound argument

[Guillermo Rauch @rauchg]

Your software factory should be a monorepo. All your company context (design, marketing, sales, engineering, support…) in one place for agents to build upon

[Tommy Pang @tommypang248]

@thsottiaux @AbdoKerdawy Sadly Sol 1m context window only opened at API base pricing instead of at subs level.

[Tommy Pang @tommypang248]

@saylordocs @grok is this interview real?

[Tommy Pang @tommypang248]

@jarredsumner Ohh wow!

[Tommy Pang @tommypang248]

@WhaleInsider @grok explain this and what will be the impact to upcoming crypto market?

[Tommy Pang @tommypang248]

@hanouticelina @code Ohh wow.

[Tommy Pang @tommypang248]

👌🏻

[typecraft @typecraft_dev]

Terminal tier list. This is the hill I will die on

[Tommy Pang @tommypang248]

@AndrewBolis Guides

[Tommy Pang @tommypang248]

I registered for Google I/O 2024 and earned a badge! Join me! #DevBadges #GoogleIO https://t.co/CU8OsrhrWj

[Tommy Pang @tommypang248]

@codedailyML SQL

[Tommy Pang @tommypang248]

Going to be building my own GPT using @typedreamHQ's new GPT Builder. Curious? Get early access https://t.co/hXnoSkdavD

[Tommy Pang @tommypang248]

@eyishazyer 😮

[Tommy Pang @tommypang248]

Thanks @justinbieber for spending 243 minutes with me in 2022. I couldn’t stop listening to Hold On. #SpotifyWrapped https://t.co/pWwHTKAmFa

[Marques Brownlee @MKBHD]

@oneplus OnePlus 5 tea. OnePlus 5T. You tease.

[dbrand @dbrand]

5 new winners have been published. Still 75 more phones to go... https://t.co/v7EqoG3fd4

[dbrand @dbrand]

Don't build walls. Build hype.