Jon (@noisemakerjon) profile picture

I’m either prompting or yapping. Forever need more tokens

Joined July 2012
Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)Photo by Jon (@noisemakerjon)
This is a chart crime. You cant test one in its native harness, and not the other
1
1
75
2,676
Jon retweeted
Replying to @blakeir
yeah, I wonder how games or game platforms can capture this fun well part of the problem is that its very expensive so only coding harnesses with subscriptions can do it right now
4
1
55
8,316
Claude Fable 5.2 vs Opus 5.5, building my pfp in Minecraft Fable is miles ahead. Maybe it's just this one test, but Opus came out almost primitive, which I didn't expect from a model that's been on top this long
12
1
1
59
9,300
Jon retweeted
Sick of Ai’s double standards
1
24
1,473
Replying to @jarredsumner
@bot make a bot with egg man called devr that absorbs principals and such like this for our prompting/coding work, have that be the only one that can manage t3 threads, and the only one with the model-router skill
1
1
306
Qwen4 (Kerria on Arena) vs Claude Sonnet 5.5 Same prompt for both: a giant jack-o'-lantern in a witch hat with a full Dracula castle inside. Sonnet actually built a small castle in there, with towers and furnished rooms. Qwen4 got the outside right, but inside it's just empty floors stacked on top of each other, more parking garage than vampire castle Happy Halloween! 🎃
9
5
120
10,301
Kanye talking about how he achieved everything he said he wanted. This interview legit changed my life.
What's the most inspiring speech you've ever heard?
77
2,334
132
17,377
804,657
Jon retweeted
If you don't like 6.1 Terra you're probably just using it wrong
37
4
2
182
11,368
“Alignment”
3
1
1
6
206
Replying to @ThePrimeagen
When can you pack that insight into a skill
1
11
2,032
Jon retweeted
Okay nice deepseek v4.1 flash is out this is nice >deepseek v4.1 1017 is out Oh okay that’s cool if only there was a way to know the version of model it is Can someone explain why they don’t just 4.2??????????
1
3
664
Introducing Pirate ZK Inference You can now use DeepSeek-V4.1-Flash-1017 and other sovereign AI models anonymously: Connect your agent, choose a model, and Pirate ZK Inference anonymizes your personal details before they reach your inference provider like OpenRouter. Featuring zkAPI + a TEE enclaved scrubber model. This is Pirate Face's first feature in its upcoming privacy ladder for AI. Try it below ↓
22
38
6
438
15,214
Replying to @notjamesbennett
Retard, all code is opensource. intelligence is too cheap to meter. Likely Likely Your gonna post all this and your making assumptions You didn’t even dig into this???? Your gonna post all this but not lift a finger and just regurgitate info Likely?? Seriously why spread stuff with likely’s and assumptions First you call it a detail, then you say fix already existed to then saying likely 2x No ai wrote this bullshit your dented smooth brain did I’ll eat my words if wrong but shut up first
1
2
39
thankfully my AI psychosis is cool and useful unlike everyone elses
40
116
6
1,436
44,472
Jon retweeted
Replying to @MTSlive
2
6
1
391
20,931
Jon retweeted
Bootstrapping PirateFace with a seedbox. If you need a referral on where to grab a seedbox, or how to use one, let me know in the comments. I'm banking points & backing up obliterated models. 👇
1
2
735
So I migrated my SaaS from @Vercel to @Cloudflare… …and about a week later, it went down for ~40 hours before I realized it. To be fair, the migration itself was a pretty big one. TruckFull is a Next.js app with authentication, geolocation, OCR/VLM usage, payments, webhooks, data pipelines, background processing, and a bunch of other external services. I tried OpenNext first, but it fought me on enough compatibility issues that I switched to Cloudflare Containers. That allowed me to keep my environment setup instead of maybe having to rewrite half the app. Before moving production, I tested the lite container with 50 requests at once. All 50 returned 200. Peak memory was around 165MiB, with no OOM. Staging passed the usual route, auth, webhook, image, sleep/resume, and rollback checks. I thought I was good Then I got an email from Facebook at 2:30 in the morning saying they couldn't find my privacy policy "Uh-oh" I thought Went to TruckFull dot food, the production container stopped accepting connections. It didn’t 'crash'. It was still ~running. It just stopped serving my website. While investigating, I found ShapBot, Parallel’s (@p0) AI search crawler, hitting the site heavily. Thousands of requests in one hour, including relatively expensive pages. That looks like what pushed the small container over the edge. I’m still checking the exact timeline, but it was enough to make me block ShapBot while I investigate. Restarted the container so the site is back online now. And the container has more room. I'm working on setting up a little 'canary box' that will notify me when production goes down, as well as give AI the ability to study what's going on and provide me with analyses. I guess just in summary maybe just a warning to other devs thinking about migrating from Vercel to CloudFlare - consider simulate crawler loads or pick a stronger config when first migrating I still believe the migration was the right choice and a sincere thank you to @noisemakerjon who pushed me to migrate sooner than I felt comfortable, because that's how we grow
7
1
1
9
864