Ai enthusiast, vibecoder, gamer, traveller (đ45 countries) Building autonomous AI systems with Codex
Joined February 2017
- Tweets438
- Following268
- Followers96
- Likes778
Pinned Tweet
I got @DOOM running right inside a @ChatGPT chat. Even thatâs possible with the new Intelligent UI mode! Fully playable. Try it yourself.
chatgpt.com/share/6aca8f7e-8âŚ
Chat Pro one-shotted it in 18 minutes. Absolutely insane. No MCP. No separate plugin. Just a regular chat and a prompt barely more complicated than âBuild DOOM, make no mistakes.â
Weâre living in the future.
ChatGPT limits are broken. I ran Astra medium long task and it ate 73% of my usage in 2.5 hours. That's not ok. $100 plan.
Iâve switched to @claudeai and Iâm leaving @ChatGPT.
đ Exclusive reveal for ChatGPT users at the end.
I just signed up for the $100 plan. First impressions are fantastic. Responsive, proactive, very smart. Astra is good too, but there are three reasons itâs impossible to work with it properly and let it run autonomously:
1. Connection interrupted. Waiting for the complete answer
2. 429 error
3. Could not load this ChatGPT conversation
Iâd also been using my dot to get truly unlimited access to Astra. In case you didnât know, your dot has seven subagents, and you can explicitly tell them which model and reasoning effort to use.
Yep, exactly what youâre thinking. "Hey Dot, run this prompt on Astra Ultra, do not add anything here."
Try it. It works. It can work at your server with root access. But thanks to the idiotic harness, the main dot constantly forgets the context and the tasks you give it, and keeps fencing its agents in instead of giving them freedom. I tried fixing this with skills. Didnât help.
Another incredibly stupid thing is auto-review, which brings all work to a halt. Thereâs literally no âallow everythingâ setting. I ended up building an autoclicker that sends âI approveâ into the chat with my dot whenever it asks me, yet again, whether itâs allowed to merge a PR.
Still, the dot did get a huge amount of work done. You can see my usage in the screenshot. Looks like its agents burned through the equivalent of two and a half $500 subscriptions over that time.
Anyway, Iâm tired of bugs, lag, and workarounds. I just want to get work done without all this hassle. Hopefully Claude can give me that. As for ChatGPT, I wish it good health. Unfortunately, itâs not doing too well in that department.
đşđ¸ Looks like Claude Duet will be US-only, just like OpenAIâs dots. Well, âUS-onlyâ as in youâll need a VPN set to the US to use it.
You can join the waitlist here if you want to be among the first to try it:
claude.com/product/claude-duâŚ
Alex Nesterov retweeted
Railway is compromised, rotate all API keys as soon as possible
Deployments are down so donât wait to redeploy
Attackers are draining keys in real time, we didnât lose much but can confirm this is still an active attack
Stay safe friends
Guys, am I the only one who thinks all these SVG pelicans and Ana de Armas renders look equally cringe, no matter the model? Are you seriously judging AI models by the SVGs they generate? Is there some deeper meaning Iâm missing?
OpenAI found the usage issue and gave a compensation of 12500 API credits to affected users, including me. Here is the official letter from them.
Token Gremlin harvest stripe donations via fake 6.5 Astra announcement? That's how you can lose reputation on X. Super odd move here.
WE MIGHT HAVE JUST GOTTEN THE FIRST SIGN OF GPT-6.5!
The domain opensi.lol has a hidden "6.5" in its source code and a countdown to November 1, 10AM SF time. That's exactly Day 28 of Tibo's 28 days.
Either this is the biggest troll of the week, or someone knows something we don't.
Fable 5.5 (or the new Opus), Gemini 4 Carbon and (wtf) new OpenAI model Terra -- upcoming releases for the early november, according to insider journalist from @theinformation
What's wrong with OpenAI, where is cost-efficient Astra 6.1??
đĽFirst review of Fable 5.5. Can't wait
official now: anthropic is preparing the release of their new model(s). Via The Information
Anthropic is reportedly preparing a model that, when asked to fix one bug, can identify the broader class of problems behind it and ask whether it should address those too. That account comes from one anonymous tester; the model family and release date remain unclear.
But looks like it will be a significant jump compared to their released models.
Smart words. If AI writes for you, that's AI's thinking, not yours. Even if it say what you want to say.
i love writing. i never let agents write for me. whether it's docs, or tweets, or shitposts, or even prompts (okay maybe that one's harder as agents manage other agents)
there's a simple reason for that: i still strongly believe that writing is thinking. it's a skill i hope to never give up. it's also important to me that whatever i say is always authentic, mistakes and all. my favorite posts are the ones that i just full send without any editing
i suspect it also helps with prompting. being able to clearly express what i want, and knowing the vocabulary i need to be able to direct my agents does seem to make for more effective usage of agents. in the same way that engineers have an advantage when we prompt agents to write code, because we are intimately familiar with the words that make up the discipline
knowing the right word incantations to get an agent to produce a desired goal almost feels like spellcasting. as models get more capable, and that input box looks more and more like a magic box that can output anything, words become the interface between you and the genie
there may come a time when we give up the keyboard in exchange for brain-computer interfaces. but until then, i'm writing every word.
One of the thing I love in OpenAI the most is that they hear us. Iâm still in the âteamâ ChatGPT and wanna stay there. I donât want to switch and I hope nobody will force me to do this. Gogogo @OpenAi!
I've been banned for Wanting the bug fixed.
I'm sorry, Claude. #ImSorryClaude imsorryclaude.com/AlexNesterâŚ
