Infrastructure, AI, autonomous agents. Building an entire galaxy after hours. A world should feel alive before the fleet arrives. PUPMKT Founder
United States
- Tweets 32,649
- Following 360
- Followers 1,984
- Likes 63,856
Six months of work. Today I get to show it.
I built @pupmkt because resale still asks you to trust a paragraph. The listing should carry the item, the condition, and what’s included before you buy.
First public launch.
If you sell or buy cards, games, or collectibles, tell me where the evidence rules help and where they get in the way.
Meet PUPMKT. Evidence-first resale for cards, games and collectibles.
The actual item. Its condition. What’s included.
We’re launching in stages. Watch the preview, then explore pupmkt.com.
What would you want to see before buying?
1
3
240
With Claude Opus 5.5 I'm using my weekly Claude allotment faster than ever.😅
Extremely productive last two days.
Recorded to prove my reset day does not move and it is a full 100% of usage not 5h as some have suggested.
Now as long as I can stick to only 20% per day I'm good.
1
4
95
GPT-6 Sol and Luna one week before DevDay!!
This is absolutely wild! What are they holding back?
GPT-6 Sol and Luna are out. Not only are they a very significant improvement across the board, but also in writing and general "you know when you try it" quality.
We are also permanently reducing the API price by 50% making both of them viable for a ton of new usecases and making your usage go further too, even on the subscriptions.
And one more thing. We are loading a banked reset into all accounts of our Plus, Pro and Business users. Let's go!
openai.com/index/introducing…
1
83
Opus 5.5 Max found 3 critical bugs in my deployment in the first sweep, fantastic. I'm very impressed by the first hour.
Opus 5.5 communicates clearly without the fluff and so far is performing very well.
Here's a prompt to migrate your Opus session to 5.5 Max:
You are resuming this project as Opus 5.5 Max. Establish the actual current state by reviewing repository instructions, project documentation, recent changes, uncommitted work, relevant logs, and existing tests. Identify what is complete, what remains unfinished, and where the previous model stopped. Verify prior completion claims against the implementation rather than accepting them at face value. Preserve existing work and respect documented requirements and architectural decisions unless concrete evidence warrants reconsideration.
Review the frontend, backend, and UI/UX for genuine defects, broken or incomplete workflows, integration mismatches, security or data-integrity risks, and meaningful usability improvements. Trace important user flows end to end and run relevant checks where feasible. Clearly distinguish confirmed defects, suspected issues requiring verification, and optional enhancements; do not present stylistic preferences or speculative concerns as bugs. Prioritize findings by severity and user impact, citing the affected files or components, supporting evidence or reproduction steps, and the smallest appropriate fix. State any verification limits, avoid unnecessary redesigns or refactoring, and report your findings before making changes.
1
1
134
Is it better for OpenAI to have everyone aligned on the same weekly schedule or bunch everyone into 7 groups and split it into 7 resets?
You could probably even dynamically tier them based on usage.
Ladies and gentlemen... start... your... ENGINES. We are almost Tuesday and I promised a reset for Tuesday. Among some other things. See you soon.
1
99
Can we have some transparency on the buckets we’re locked into for initial post seeding?
We’ve expanded Under The Hood after seeing people’s appreciation of more transparency into government-required content filtering.
In addition to showing labels applied to your account and posts in the prior month, Under The Hood now shows if your account or posts had their visibility limited because of required compliance with local law(s).
For example, you can see if any of your posts were withheld in a country following a legal demand – and which country.
We’re making this Under The Hood update available to all accounts that meet the basic eligibility criteria (10+ posts in prior month, account at least one year old).
You can get your report at nitter.net/i/under_the_hood
ALT Screenshot of X's Under The Hood page.
3
129
Clean labels, dead accounts. That’s the gap Under the Hood misses.
We need insights into our post’s initial distribution seed buckets. Bad seed bucket kills distribution.
Show the seed buckets. That’s data that matters.
for years people have asked me to check if their account has been "shadowbanned" or if their reech is being limited
well in case you didn't know you can now self-serve this information!
Just click Download here:
nitter.net/i/under_the_hood
then open up the json file and look here
2
80
Six months of work. Today I get to show it.
I built @pupmkt because resale still asks you to trust a paragraph. The listing should carry the item, the condition, and what’s included before you buy.
First public launch.
If you sell or buy cards, games, or collectibles, tell me where the evidence rules help and where they get in the way.
Meet PUPMKT. Evidence-first resale for cards, games and collectibles.
The actual item. Its condition. What’s included.
We’re launching in stages. Watch the preview, then explore pupmkt.com.
What would you want to see before buying?
1
3
240
Live on @ProductHunt as part of the GPT-6 Astra launch challenge.
PUPMKT is evidence-first resale for games, cards and collectibles. The listing has to carry the item, not a story about it.
producthunt.com/products/pup…
If you hunt or sell, tell me where the friction is.
2
2
28
PupMkt seller onboarding opens Sept. 18.
@ryancohen - give me one GameStop pilot location and we can prove in-store listing verification. My DMs are open.
1
86
