haha the benchmark screenshots never show the alt+tab to Claude Code right after.
LLMS
-
FireworksAI: inference faster than other providers
By
–
By the way, I use @FireworksAI_HQ for inference. Other providers may not be as fast.
-
An image-blind model could become the best with a fix
By
–
The major flaw is that it is blind – it cannot process images at all. If they fix that, then perhaps it could become the best model available in the world.
-
GLM 5.2: a performant and low-cost open weights model
By
–
Wow. @Zai_org GLM 5.2 is a marvel! It is *at least* as good as Opus 4.8 and GPT 5.5. It is super fast, inexpensive, and not too verbose. It responds with nuance and judgment, & handles long contexts very well. I have never known an open weights model like
-
Handlebars templating can’t do string manipulation for LLM index
By
–
"What kind of programmable automated system can't do string manipulation!?" Handlebars templating, apparently. (I'm building an LLM-available index into some of my sites to have various tools able to read status of pieces w/o needing direct DB access.)
-
Wait, Claude Code had no artifacts? They invented them?
By
–
wait what claude code didnt have artifacts??? they invented artifacts?!
-
Codex manages Google Cloud settings itself via its browser
By
–
Having Codex handle all the Google Cloud settings itself (using its in-app browser) is so awesome pic.twitter.com/goLAn1aIo2
— Lenny Rachitsky (@lennysan) 18 juin 2026Making Codex manage all Google Cloud settings itself using its built-in browser is so great.
-
AI models unaware of my current role, GPT 5.5 ignores me entirely
By
–
mildly interesting that the models don’t know about my current role and gpt 5.5 doesn’t even think about me, at all!
-
AI equivalent to Opus 4.8 locally for under €4000 soon
By
–
Read carefully. We are just a few months away from being able to run the AI equivalent of Opus 4.8 locally on hardware for under €4000. Yes, yes…
-
Ineffective a posteriori API guardrails for cutting-edge models
By
–
Let's face the truth: a posteriori API guardrails are not the appropriate safety tool for cutting-edge models. They do not eliminate dangerous capabilities. They simply hide them behind a fragile interface that can be easily