Loiu92 - Lucas

#Devops #SRE #Dev #Taiwan
based in Taichung 🇹🇼
Contact : [email protected]

[Elaya @elayadesigns]

Built this using Higgsfield + Cursor Composer 2.5 + my custom landing-page-design-skill.md file.

It reminds me that models don't matter. Skills do.

[Loiu92 - Lucas @Loiu92]

@dan__rosenthal Outbound

[Teknium 🪽 @Teknium]

A new era of efficiency for your chat sessions in Hermes Agent.

Our latest optimization will reduce database size on your disk by upwards of 78% and on average ~60%.

For those with databases <1GB, your one time optimization transition will trigger automatically. If your database is larger, run the following command once after updating:
`hermes sessions optimize-storage`

It will silently process the transition in the background while you keep working. Enjoy!

[witcheer @witcheer]

Hermes Agent v0.19.0 is live!

~80% faster first response across CLI, desktop, TUI, and gateway. the desktop app got 14x faster markdown, virtualized diffs, snappy session switching. reasoning streams live by default.

- smart approvals is now the default
- /subscription billing from the terminal
- Bitwarden + 1Password secret sources
- profile routing runs multiple profiles off one gateway

and way more released, check it out :)

[dax @thdxr]

used a trick @jlongster came up with

agents can control browsers but you can also ask it to record network requests into a HAR file

then it can derive a client for any website which is more efficient than browser controlling it every time

made it build a quick uber eats cli

[Theo - t3.gg @theo]

Kimi k3 is an incredible model. It is not an incredible value. In most tasks, it comes out to roughly the same cost as GPT-5.6 Sol.

K3 is half the price of 5.6 Sol per token. GPT-5.6 uses half as many tokens. Price evens out.

GPT-5.6 is 2x faster TPS, so it gets work done ~4x faster than K3 at roughly the same price.

I still love K3 and will be using it for a TON of stuff. I'm just tired of people pretending it's way cheaper when it's not.

[shadcn @shadcn]

React Aria is now available in shadcn/ui.

Use `--base aria` or choose React Aria in shadcn/create.

All components, docs, CLI, styles and skills have been updated for React Aria Components.

Shoutout to @devongovett who did most of the work behind this release.

[Kimi.ai @Kimi_Moonshot]

🤯

[BridgeMind @bridgemindai]

GPT 5.6 Sol just hit CursorBench.

The economics are brutal for Anthropic.

Fable 5 Max: 70.5% at $17.32 per task. 103,525 tokens.
GPT 5.6 Sol Max: 67.2% at $5.22 per task. 28,320 tokens.

95% of the performance. A third of the cost. 73% fewer tokens.

Fable 5 kept the crown on raw score. It lost on everything that shows up on your invoice.

And remember: GPT 5.6 comes with limits you can actually live with.

The frontier is not an intelligence war anymore.

It is a value war.

[colinhacks @colinhacks]

Nub's package manager is now 5.5x faster than Bun on our warm install benchmark

// TanStack Start project // 1000 node_modules // Linux

[Daniel San @dani_avila7]

Claude Code v2.1.198 ships a new built-in skill: /dataviz

It loads chart and dashboard design guidance directly into context: chart type selection, layout rules, and visual hierarchy for data-heavy UIs

It also includes a runnable color-palette validator, so Claude can check contrast and accessibility programmatically instead of guessing

No install needed, it comes with the CLI 👇

[Cloudflare Developers @CloudflareDev]

A secret sharing tool for devs, built on the Cloudflare stack and winner of the Cloudflare IRL Hackathon in Bangalore from @RishitShivam

https://t.co/g5yiu5BqVq

[Teknium 🪽 @Teknium]

Hermes can now LEARN from any source or set of sources, build a skill, test it live, and crystallize new learnings.

Just run /learn and pass it sources, past sessions, URLs, docs, whatever you think will help it learn, and it'll go from 0 to 1 to create you a skill!

[colinhacks @colinhacks]

Introducing Nub.

The all-in-one JavaScript toolkit that augments Node.js (instead of trying to replace it)

[Ashwin Gopinath @ashwingop]

Claude Tag is a Trojan horse.  Not because Anthropic is doing anything evil. Because the incentives are obvious.

Day one, this looks like a great feature: tag Claude in Slack, let it follow the thread, remember context, connect to tools, break down tasks, chase work, and act like a teammate.

But that is exactly the problem. The moment your AI vendor becomes a shared coworker, it stops being just a model provider. It starts becoming the place where work is interpreted, remembered, routed, and eventually executed.

That is not model lock-in. That is context lock-in. You are now renting your company back from them.

Models can be swapped. Agents can be copied. But the memory of how your company actually works is much harder, maybe impossible, to move: the Slack scar tissue, the exception paths, the customer promises, the unfinished threads, the weird workflows, the implicit owners, the “we tried that in Q2 and it failed” knowledge.

Once that lives inside one vendor’s agent layer, you are not renting intelligence anymore. You are renting your company’s operating memory.

And the pricing model makes it even more dangerous. A human coworker has a salary. Claude has unbounded tokenized activity. The more work moves through it, the more the vendor captures not just IT spend, but labor spend.

This is the enterprise bargain people will regret: Convenience now, and rapid decent into dependency.

The right architecture is simple: rent the best intelligence from whoever is best this month. OpenAI, Anthropic, Gemini, open source, whatever. But own the context layer.

Your company memory should be inspectable, permissioned, portable, and model-neutral. It should not be buried inside the same vendor that sells you the intelligence and the workflow surface.

Claude Tag is useful. That is why it is dangerous. Rent the intelligence, but own the context. Or, regret later.

[Seb Gouspillou @SebGouspillou]

Y’a la mauvaise IA et la bonne IA.

[Nicolas 💸 @NicolasQuiPaie]

Capitalisme de connivence et souveraineté, que pourrait-il mal se passer ?

ChatGPT Mistral

[LlamaIndex 🦙 @llama_index]

LiteParse v2.1 is here, and its bringing the fastest markdown output possible.

In this release, we are fulfilling our top request: markdown output. But in the spirit of "lite"-ness, we are doing this completely LLM-free and fast.

Not only is it fast, it also beats all other model-free competitors in 3 separate benchmark datasets.

Read more about it in our release blog: https://t.co/MiqML6kxTY

[Kilo (acq. by Anaconda) @kilocode]

Everyone benchmarks GLM-5.2 against the frontier now. So we did too.

We pulled GLM-5.2's plan up against Claude Fable 5's, the plan that won our last frontier round. Same prompt, same task, same rubric.

Fable scored 9.1. GLM-5.2 scored 9.0.

[Cloudflare Changelog @CFchangelog]

Create PlanetScale Postgres and MySQL databases directly from Cloudflare. Use them with Workers and Hyperdrive for connection pooling and caching.

https://t.co/nyxWTacWSL