Viewing profile — AmazingTurtle

how did this make it to the front page

[flagged]

coughs in agressive nord vpn ads

75% quality... it gets worse the longer the context.

Really just a (not so) fancy CLI wrapper about a prompt and a skill: https://github.com/openai/codex-security/blob/f22d4a36f26d16...

I have a suspicion that they are just trained on puzzles by now

Funny timing. I've been building something similar in my spare time called Daydream. There’s a lot of overlap: local screen/audio capture, OCR and transcription, window and activit…

codex CLI is already leveraging this internally. instead of performing raw MCP calls its internally using a js REPL to do that. elicitation is then propagated for approvals indepen…

This happened to me one time. On windows though, deleting C:/ lmao. The direction I'm heading now is a better harness, i.e. isolating codex at a container level with dedicated work…

Lmao this goes for literally any model. Deepseek etc is Chinese models and OpenAI/Anthropic/xAI are very western.

I learned that running goal for hours produces exponentially more slop than running targeted prompts over and over again manually. Personally, I use gpt 5.5 high with planning ever…

It's funny, they sell you a subscription for frontier models, then over time begin to nerf them rapidly and no one talks about it. Should give me a discount when they reduce reason…

how can one be sure you don't do rugpull in the future?

I founded a UG with 2 friends. 7.500 capital, 2.500 each. From that money, we paid the notary. We drafted with chatgpt on our own and presented it to an attorney for review, ~300€.…

> AI users were actually 19% slower, but they thought they were 20% faster. I don't know who made those numbers up, but for me... I can almost certainly guarantuee, I have never be…

I am now moving my stuff to cloudflare. Worker, Pages, R2, D1, heck even Hyperdrive with Neon or Supabase.

I was wondering "use" means here, as-in.. does it not recirculate? And apparently the answer seems to be: it's circulated/vaporized into the air. It may fall down as rain somewhere…

while unified memory may offer better performance than unsoldered DDR system memory, it still won't be as great as 1.8TB/s bandwidth on high end consumer GPUs right now. nvidias ma…

So my finding is: planning is worth it. For a little complex changes, I always run codex (5.5-high) in planning mode first. I have linked various docs/{ARCHITECTURE,BACKEND-GUIDELI…

6 months ago I already posted about this https://news.ycombinator.com/item?id=45349476

Bet their internal "tips team" used an LLM to generate "useful tips" for their coding agent system ;)

> like using PHP lmao, chuckled

> prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex. which is basically maxxed out quickly. So there is 2x (…

I just tried that in Codex CLI. With /fast mode enabled. Observations: 1. Fast mode ain't that fast 2. Large context * Fast * Higher Model Base Price = 8x increase over gpt-5.3-cod…