Back Home   RSS

Haiku 5.5 vs GPT-6 Luna

2026-10-08

Below 100,000 input tokens, Claude Haiku 5.5 and GPT-6 Luna have the same listed API rates: $0.10 per million input tokens and $0.50 per mil...

AI Game Mods Are Getting Easier

2026-10-07

People are using coding agents to make game mods and crossovers. In this video, Chaz shows examples and describes three approaches: Pass-thr...

Spring Physics for UI Motion

2026-10-05

CSS easing is great for ordinary transitions, but sometimes I want motion that responds like a spring: it can overshoot, settle, and feel co...

Batching LLM Calls

2026-10-05

If several small questions can be answered independently, sending each one as its own request adds overhead. This little Python experiment p...

What People Are Doing with OpenAI Dots

2026-10-01

OpenAI dropped "Dots" at DevDay alongside GPT-6.1 Sol. Instead of a chat box where you type a prompt and wait, a Dot is an always-on agent....

Gemini 4 Argon

2026-10-01

Anthropic dropped Sonnet 5.5 on Sunday. OpenAI dropped GPT-6.1 Sol and Dots on Tuesday. Now Google dropped Gemini 4 Argon. Four frontier dro...

GPT-6.1 Sol

2026-09-30

Anthropic dropped Sonnet 5.5 on Sunday. Exactly 24 hours later, OpenAI dropped GPT-6.1 Sol. Model shelf life is down to 24 hours now, lol. O...

Is the Dunning-Kruger Effect Real?

2026-09-29

Partly right. The critique you read is real and pretty strong, but "Dunning-Kruger isn't real" overstates it a bit. The famous 1999 study so...

Claude Sonnet 5.5

2026-09-28

Anthropic dropped Claude Sonnet 5.5 six days after Opus 5.5. Anthropic Claude Sonnet 5.5 (Sept 28) List price stays at $2/M in and $10/M out...

Claude Opus 5.5 and GPT-6 Sol

2026-09-23

Three weeks after the Astra and Fable drops, Anthropic, OpenAI, and Xiaomi dumped new models on the exact same Tuesday. Anthropic dropped Cl...

Building a Harness with Jev

2026-09-18

Building a Harness with Jev Jev is a model released by TypeSafe AI. The company reports up to 200x faster inference and 400x lower cost than...

What is GPT-6 Provider Adapter

2026-09-05

In my last post I wrote Astra hit 99.9% on ARC-AGI-3 and called the benchmark dead. But the leaderboard shows two numbers: 62.7% and 99.9%....

Claude Fable 5.1

2026-09-02

The latest OpenAI model GPT-5.6 went public on July 9, 2026. Meanwhile, Anthropic has dropped two frontier models: Opus 5 and now Fable 5.1....

How to Make Real Money with GTA 6

2026-08-30

GTA 6 is an economy. Players spend real cash on in-game progress, millions watch streams, and attention scales to billions of eyeballs. Buil...

Million Product Companies

2026-03-28

It has never been easier to build a product. Coding is no longer the bottleneck. The bottleneck is figuring out what people actually want (w...

how to fix ai slop

2026-03-10

Code used to be the hard part of software (was it?). Now it isn't. The hard part is building systems that don't break (or rather break grace...

which language takes least ai tokens ?

2026-02-15

When prompting AI models, token count directly affects both cost and latency. This benchmark compares how efficiently different languages ex...

Journey

2026-01-22

Started coding around 2014–15; I don't remember exactly. Why? Games! My first language was MSW Logo, then QBASIC also VBA. Then C++; here’s...

Visitors: -