Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe.
GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale.
We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.
I tested @typesafeai as a lightweight gate for assistant memory. The biggest lesson: decision quality matters more than model size. I reduced 24 noisy memory entries to 9 useful facts.
Models advise. Humans approve irreversible actions.
here @hackmdiohackmd.io/@Ali-G/Sk2_tZgcMg
Really cool concept, I was giving it some time until I tried it
I saw the possibility that we can do with HTML in canvas, and there are a lot of them
This is a small example I was testing the api
🚨 Solid 2.0 has reached Release Candidate! 🎉🥳
Async is first-class — computations return promises, the graph suspends and resumes itself. Plus optimistic mutations and a reactive core rebuilt from scratch.
The Big <Reveal> 👇 solidjs.com/blog/solid-2-0-r…
1/3
It was awesome walking the floor at CareerQuest 2026 and seeing so many bright minds turning ideas into real products. Huge respect to everyone who shipped, demoed, and kept pushing
Also, Awsome experience for me to talk about how we can bring AI closer to Angular using the new
one agent → a loop → a graph → a system that throttles itself
Google just put the whole ladder in one free course. most people never leave the first rung.
2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall.
17:55 - build your first agent
39:55 - loop engineering: iterate, check, break
1:13:25 - graph engineering
1:35:27 - agents that throttle themselves
1:56:19 - the full graph for multi-agent systems
the fourth one is the step nobody talks about.
an agent that cannot throttle itself is not autonomous, it is just unattended.
everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate.
and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself.
bookmark and watch it today, then read the eval setup below
Been deep diving Angular’s v 22 stable resource() API and wrote up the patterns I wish I’d had when the RFC first dropped
From reactive params to AbortSignal.any() and streaming with async generators + SSE, all with plain fetch() and signals,no HttpClient
medium.com/@hictors/angular-…
Number 7 in Angular v22
linkedSignal gains a custom set callback in v22.1
Intercept writes to a linked signal and syncs them back to the source, enabling true two-way binding patterns with proper state isolation. No more manual sync code between related signals.
Sixth hint in the Angular V22 :
Debounced(signal ,time ,{injector:injector ,equal:(a,b)=>...})
Angular just shipped a new primitive that quietly solves a problem every one of us has hand-rolled with RxJS at some point: debounced().
It's marked #Experimental (targeting Angular 22), so the #API can still shift, but it's a good sign of where signals are heading: less #RxJS glue code for the common cases, more built-in primitives that do one thing well.