K95

[K95 @dev_K95]

Hello everyone!

Do you have tasks you keep forgetting because they only happen once in a while?
That’s what Kiseki is for. It helps you track recurring tasks like habits, maintenance, renewals, bills, routines, work follow-ups, and other things you do not want to forget.

App Store link: https://t.co/e16XS3FY9M

Key features:

Workspaces & Sections
Organize trackers by areas like Work, Life, Health, Family, or anything that fits your routine.

Today View
See what needs your attention today, grouped clearly so you can act fast.

Complete, Skip, or Snooze
Handle each tracker based on real life: finish it, skip it, or snooze it for later.

Local Reminders
Get notified before or at the due time through iPhone notifications. No account needed.

List & Calendar Views
Browse your trackers in a simple list or calendar view.

Global Search
Search across trackers, workspaces, and sections so you can quickly find what you need.

Filters & Priorities
Filter by status, priority, workspace, or section so you can focus on what matters.

Custom Priority Statuses
Customize priority labels and colors to match how you personally organize tasks.

Templates
Create reusable tracker templates so repeated setups are faster next time.

Markdown-Ready Notes
Add notes with headings, bold, italic, strikethrough, code, links, lists, quotes, and checkboxes. You can also attach images from your iPhone Photos, Files, clipboard, or by taking a photo directly from the Kiseki app. Notes also have write/preview modes and can be expanded for easier editing.

Simple Insights
See your completion rate, overdue items, upcoming tasks, and best-performing section.

Offline First
Your data stays locally on your device.

Kiseki is currently available only on iOS for ₱199.

There may still be bugs, but I’m actively working on fixing them. If you notice anything, please let me know so I can take note and improve it. Feature ideas and suggestions are also very welcome.

[Daniel San @dani_avila7]

Introducing Jev Model Router for Claude Code

This Claude Code Mod lets you use Jev through its direct @typesafeai API or @vercel AI Gateway

With every request you send to Claude Code, Jev classifies the subagent model, main model (only at session start to avoid breaking the cache), and effort level

Install it with one command:
npx claude-code-templates@latest --mod productivity/jev-model-router

Full Mod details:
https://t.co/JWOXL9Nk88

[tamara @tamarajtran]

you can also use Jev to cut costs and token usage!

make your agents more efficient by compacting shell and large file output before it reaches the LLM

passing only necessary tokens to the model and carrying fewer tokens through the rest of the conversation

[Alex Volkov @altryne]

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run!

Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮

Ask your claude to install it and be amazed

Use this prompt

```
Install, and configure :
https://t.co/yD6PncSCtH

```

[Zachi @iam_zachi]

I think I just cooked something 🔥

jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function.

WHERE jev(people, 'could work from home')
or
WHERE jev(people, 'name sounds european')

129 rows judged in ~1s for $0.0009. Second run: 6ms from cache.

[Diogo Almeida @CompleteSkeptic]

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution

[Joe Devon @joedevon]

Codex users: a retired feature was silently burning my usage limit, even after I turned it off. It's probably a bug.

Here's how I found it, and how to check if it's burning yours.

FYI @thsottiaux @pvncher https://t.co/PKRp5UYOXt

[ChatGPT @ChatGPT]

Procrastination has met its match. ChatGPT is now in Word.

You can add ChatGPT to Microsoft Word to turn rough notes into first drafts, untangle tricky paragraphs, proofread, and get suggested edits—all without leaving your document.

It can even spot formatting issues. Which means a few less things to fix later 🔍

[K95 @dev_K95]

@jayden_reuben @Jaytel What effort do you usually set for luna?

[thijs @cdngdev]

you can use codex voice from your phone now, connecting to your computer from anywhere!!

@axbehr and i got to star in this new codex ad, showing how much you can get done while working out.

btw, this is powered by the new gpt-live-1

[Brent Traut @btraut]

Codex pro tip: You can reference one thread from another just by @-mentioning or drag/dropping! You can also ask it to message or monitor others. Combine this with schedules and you can manage whole fleets of threads working together.

[K95 @dev_K95]

🤣🤣🤣

[Eniola @Enywealthh_1]

This driver is definitely from Lagos 😂😂

[Tesla @Tesla]

What 0-60 in the new Roadster sounds like

[Digital Daisy🌸 @DigitalDaisyX]

Tesla just announced the new Tesla Roadster is coming in October…

Elon Musk talking about it:

“Most memorable product unveil ever.”

Then he hits us with:

“It’s crazier than anything James Bond. If you took all the James Bond cars and combined them, it’s crazier than that.”

And now we’re wondering… is this the Tesla that can FLY? 🔥🔥 ✨

[Lydia Hallie ✨ @lydiahallie]

Setting my subagent model to Opus has helped me save so much usage on Fable 5.1. It really likes to spawn subagents but mine rarely need Fable-level reasoning

`CLAUDE_CODE_SUBAGENT_MODEL=opus`

[K95 @dev_K95]

@weswinder Same thing I noticed. It doesn’t matter if your subagents are in low effort. They still consume so much

[K95 @dev_K95]

@Mr_Salio Nahhh! Medium still drains too fast

[OpenAI Developers @OpenAIDevs]

Get more out of GPT-6 Astra by revisiting your skills, AGENTS.md, and task prompts.

Make skill triggers specific, load guidance when it's relevant, and define what done looks like.

https://t.co/UGF0AC8Z5Y

[Zentrix⌚️ @ZentrixHQ]

GPT-6 Astra MAX just solved a real engineering problem on this rover build

It already handled the knuckle CAD design cleanly, so this time it was handed something harder, the upper mounts for the steering actuators, the Damiao 4340P. That's a part where the geometry has to line up perfectly or the whole steering assembly binds.

This clip shows the detail up close, every surface, every mounting point, worked out without a single manual tweak.

What's wild isn't just the output. Astra MAX ran for a full 2 hours straight on this design and only burned 7% of its weekly usage. A task that would eat a CAD engineer's entire afternoon barely touched its budget.

[Maciek Pekala @penzington]

Today I learned that a border-radius can cost you 45 MB of GPU memory and a blank frame per keystroke.
Left: rounded bottom corners. Right: rounded all four corners. That's it, that's the fix.

[ChatGPT @ChatGPT]

GPT-VI ASTRA