Postman @postmanbuild

Always Shipping 📬 ✉️ Postman.build San Francisco Joined January 2012

Tweets

2K
Followers

320
Following

205
Likes

30K

Postman @postmanbuild

a week ago

@CloudflareHelp Workers Paid dropped from my account today; every payment (card and PayPal) fails with ‘unexpected error’, no charge reaches my bank, and the dashboard says it cannot find my payment method. Production is down. Please help.

0 0 0 30 0

View Details

Postman @postmanbuild

3 weeks ago

@felixrieseberg @GergelyOrosz cowork from your phone will be a huge unlock

0 0 0 9 0

View Details

Postman @postmanbuild

3 weeks ago

@xPetu Show the reverse exodia comp that was -10% WR

0 0 0 37 0

View Details

Andrej Karpathy @karpathy

3 weeks ago

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

2K 7K 56K 8.0M 82K

View Details

Postman @postmanbuild

3 weeks ago

@john__allard Lifemaxxing. this is so sick

0 0 1 18 0

View Details

Postman @postmanbuild

3 weeks ago

had me holding my breath for 42s

zeal @zealcaiden

3 weeks ago

“make a techno optimist music video full of hype moments and insane motion graphics”

19 26 217 45K 79

0 0 3 52 0

View Details

Postman @postmanbuild

3 weeks ago

@kevin_t_ngo The little faces they make mid-attack are the best part >:c Do you plan out those expressions ahead of time, or do they show up while you're animating? I keep wondering if you feel more like the director or the artist on these.

0 0 0 12 0

View Details

Postman @postmanbuild

4 weeks ago

GLM 5.3 be like:

lauren @poteto

4 weeks ago

build trebuchets while others build moats

57 46 1K 70K 85

0 0 0 31 0

View Details

Postman @postmanbuild

4 weeks ago

@pleometric nightmare fuel

0 0 0 3 0

View Details

Postman @postmanbuild

4 weeks ago

@thsottiaux Fixed it

0 0 0 45 0

View Details

Postman @postmanbuild

4 weeks ago

i know my Strava friends by their hot takes on bike brands and SF pastry shops. very little idea what they do for work. so i built a little Strava × LinkedIn graph

0 0 0 24 0

View Details

Postman @postmanbuild

4 weeks ago

Inspired by @FotachuARGUY, I built a Higgsfield.ai prototype with decades of user familiarity baked in. HiggsTube: …ld-youtube.postman-build.chatgpt.site

0 0 0 44 0

View Details

Postman @postmanbuild

4 weeks ago

@brian_armstrong imo /feedback should be a requirement for MCP servers

0 0 0 11 0

View Details

Postman @postmanbuild

4 weeks ago

Codex had a moment while we were building my Strava × LinkedIn graph

0 0 1 16 0

View Details

Postman @postmanbuild

4 weeks ago

Saw @tobi's disktree and wanted the same thing for memory, live. Built memtree: Mac processes grouped by app, sized by memory. The tiles glide as usage changes. Turns out ChatGPT gets a 10 GB rectangle. github.com/Grant-Postma/m…