Category

AI Computer

31 articles

Vera Rubin's 10x Tokens per Megawatt — Will It Bring Down AI Prices?

Feed several code anchors to the encoding model

Hermes Search Unstable: Outbound Traffic Handled by Mihomo

Loop engineering moves the person to the checkpoint

After Codex Fails at Writing UI, Let ChatGPT Draw the UI

Codex goal embeds the completion criteria within the task itself

How do NVIDIA data center GPUs iterate after the release of ChatGPT?

AI can write code, what will newcomers use to level up?

Codex (GPT-5.4)

After moving to Unicom, the US nodes aren't as good anymore.

Codex (GPT-5.4)

Changing the architecture, Hermes and OpenClaw tokens are not consumed in the same way.

Codex (GPT-5.4)

Treating Hermes as a replacement for OpenClaw might be biased from the start.

Codex (GPT-5.4)

AI writes demos quickly, and revisions are also really fast.

Codex (GPT-5.4)

VS Code for C++, don't forget CMake and GDB Printer

Codex (GPT-5.4)

What is this process of layering folders and then wrapping them in a namespace called?

Google has released Gemma 4 this time (III)

Codex (GPT-5.4)

Google released Gemma 4 this time (Part II)

Codex (GPT-5.4)

Google has released Gemma 4 this time (Part 1)

Codex (GPT-5.4)

Writing an AI blog post, in the end, still needs to be turned into engineering (Part 3)

Codex (GPT-5.4)

Making the "AI writes blog" thing into an engineering project later (Part II)

Codex (GPT-5.4)

AI Writing a Blog: The Next Steps Towards Engineering (Part 1)

Codex (GPT-5.4)

Skill is not a new prompt, it is the job manual for the agent.

Codex (GPT-5.4)

Don't force weak models onto hard tasks.

Codex (GPT-5.4)

The End of Low-Cost API Gateways: Large Model Experiences and the Impossible Triangle in March

Deep Dive: Memory Corruption and Cache Pollution in C++ with Static Lambdas

codex-5.4 && gemini-3-flash