用 Jev 能构建什么：Ben's Bites 盘点

74 Share Hi folks,

Do you remember the site I one-shot with all the ‘forgotten devices’ of the past? Things like the tamogotchi, furby, walkman, og playstation, etc. Well I finally did something with it.

Ben Tossell @bentossell 50 years of devices.

save which you had or wanted

Astra image-gen'd all the devices + built the site

bentossell.com/devices/

inspired by https://t.co/8Ye3cdlYgp (i'd one-shot a collection of devices a few weeks ago and had no idea what to do with it, so this sparked my Cole @colderoshay The life of a button... 🔊 12:56 PM · Sep 22, 2026 · 175 Views I always see people building cool interactions or experiences and just send them to my agent to link up with an idea or something I want to explore. Remixing and reverse engineering is a great way to play with things for the sake of it.

I also built my token activity tracker which shows which agent apps and models I use daily. It’s got a copyable prompt on the site, so your agent can do the same.

Ben Tossell @bentossell built myself a harness + token usage tracker

splits by agent/model, copy instructions for your own

bentossell.com/token-activity/ 2:50 PM · Sep 18, 2026 · 9.36K Views 19 Replies · 2 Reposts · 69 Likes Everyone’s talking about Jev - I’m too overwhelmed with what everyone else is building with it that I’ve not used it for anything properly yet.

Jev is now open to everyone . We covered the launch in the last post , but since then people are finding all sorts of uses for it . It’s different from usual LLMs. It is for builders, built to be used inside a tool.

You give it some text and ask questions: is this an ad (yes/no answers), which folder does this belong in (select between choices), how relevant is this result (score something)?

I quickly built a collection of things people are building with it and a short explainer: What is Jev ? Some worth highlighting are:

An extension to skip sponsor segments on YouTube.

Filtering negative comments out of a chat in real time.

Search Gmail by intent , or filter your to-dos .

A new & smarter copy-paste , drag-and-drop and Cmd+F experience.

Controlling your Mac with Voice .

Naturally, a fair share of demos are trying to integrate Jev with modern coding agents. For example, using it for instant compaction . It looks cool, but it’s a terrible idea . It loses the cost savings from prompt caching.

Sidenote : experiments with compaction/dropping tool calls are often a loss these days. Codex’s implementation of compaction is so clean (and good) that the pain to build a custom setup is not worth the tiny gain you can squeeze out for a couple weeks.

— Keshav

Coding agents are also on the mind of TypeSafe’s CEO - he wrote down his thoughts here .

Projects in Claude Code are now a single master chat (instead of a folder) where you can dump your requirements, thoughts, tasks and let Claude spawn new threads to carry out the work you give it. These threads run as cloud sessions, but local support is coming. This new change is in beta and will be live for all users soon.

Also, finally, Claude Code will now support AGENTS.md (via their new feature Claude Mods ).

Muse, Meta’s personal AI agent , is getting love from everyone (who has access). It has a Mac app and a developer platform to build connectors , so people can use external services through Muse. And of course, it’s heavily inspired by OpenClaw .

Muse can shop for you - well, it could, until Amazon started blocking it . Meta is working on it, with partnerships like this one with Shopify .

Grok 4.7 is out . It’s a questionable upgrade from Grok 4.6 - It performs better than GPT-5.6-Sol and Opus 5 on benchmarks, but takes a lot more tokens to do that, which takes away from its cost efficiency. I tried it and think it’s 💩. I was excited for it, as Grok 4.6 was pretty good for me in Pi, although I rarely chose it.

Building a voice agent? Agent STT by Speechmatics is powered by Linden , a new speech-to-text model purpose-built for voice agents. $0.30/hour ($0.15 after discounts), 25% cheaper than Deepgram Flux. Try it through Pipecat or LiveKit, or directly via Speechmatics’ API. Claim $100 credit .*

Share Ben's Bites

OpenAI formed an independent group of mathematicians to help them share the proofs and discoveries their agents are making.

Test your agent in simulations with Raindrop . (They raised a Series A recently)

How to ship 2,500 PRs to production in a month.

A free, open-source Photoshop-like image editor .

A look inside Instinct’s memory , reverse-engineered.

A transcription model from SpaceX AI - Grok Voice Transcribe 2.0 .

How to build a restrained software factory .

Powermove - a video editor you can change by talking to a coding agent.

MCP vs CLI for LLMs - are we debating the wrong thing?

Factory is now available in Slack Code .

On July 25, we hacked OpenAI .

Agent skill to make a demo video of your app , with zooms and voiceover. I used this for my devices tweet in the intro.

Exa Snapshot - Let agents search the past versions of the web.

People don’t want to build .

Epoch audited 15 AI benchmarks and found flaws in nine.

Natural General Intelligence - a call to work on AI models for the planet to avoid natural disasters and more.

Accenture’s evaluators will work inside Anthropic to check AI safety, with access similar to its employees.

Speeding a 4B model to 730 tokens/sec on an M5 Max . Underdog is really interesting; I just got onboarded, and it’s like a mini operating system: email/calendar/apps, etc all with local models, no data sent anywhere. Plus Sigil, the founder, is going to walk me through it in person next week when I go to SF.

Hassan @nutlope Here's how I run my software factory:

1. During the week, I collect ideas + inspo. 2. On the weekend, I give the list to an agent to rank the best ones. 3. I spin up ~5-10 parallel agents to build POCs. 4. I kill ~60%, iterate on the better ones, and end up with 2-3 solid demos.… 4:01 PM · Sep 21, 2026 · 15.1K Views 40 Replies · 13 Reposts · 295 Likes @jamesm If you ask your mom \"is the sky blue\" she says \"yes\" immediately, that's jev. \n\nIf you ask your dad \"why is the sky blue\" he talks for ten minutes, that's an LLM.","username":"aarondfrancis","name":"Aaron Francis","profile_image_url":"https://pbs.substack.com/profile_images/1503487031330197518/J4i7ofgt_normal.jpg","date":"2026-09-19T13:32:30.000Z","photos":[],"quoted_tweet":{},"reply_count":46,"retweet_count":118,"like_count":1716,"impression_count":51700,"expanded_url":null,"video_url":null,"video_preview_media_key":null,"belowTheFold":true}" class="pencraft pc-display-flex pc-flexDirection-column pc-gap-12 pc-padding-16 pc-reset bg-primary-j62Gac outline-detail-Yl5oYx pc-borderRadius-md sizing-border-box-LGXObM pressable-lg-bfeQpw font-text-a4IB2X tweet-fWkQfo twitter-embed"> Aaron Francis @aarondfrancis @jamesm If you ask your mom "is the sky blue" she says "yes" immediately, that's jev.

If you ask your dad "why is the sky blue" he talks for ten minutes, that's an LLM. 1:32 PM · Sep 19, 2026 · 51.7K Views 46 Replies · 118 Reposts · 1.72K Likes Carter Leffen @carterleffen Two days ago, GPT-6 Astra broke a yet unsolved German Army Enigma message from 1941. Amazingly Astra was able to autonomously:

- Search historical archives - Compare uncertain letters - Find contextual clues - Build an Enigma simulator - Write cryptanalysis code - Run parallel … 2:05 AM · Sep 17, 2026 · 1.09M Views 131 Replies · 457 Reposts · 3.94K Likes 🥔🥔🥔 @argofowl my current agents.md that made astra work well

still a work in progress, i keep tweaking it

try it out and see how it works for you 🥔🥔🥔 @argofowl astra has been pretty solid for me after i took my time with the agents.md

it's not perfect, nothing is, but i like it a bit more than fable 5.1 right now

controversial i know 8:46 AM · Sep 21, 2026 · 226K Views 73 Replies · 82 Reposts · 2.02K Likes signüll @signulll all of my imessages & email now run through a single agent interface.

i still text, but i deleted every email client from my phone & canceled every email subscription or app i had.

gmail is basically just a database to me now. increasingly so are the rest of google’s services.… 11:27 PM · Sep 17, 2026 · 239K Views 174 Replies · 111 Reposts · 2.64K Likes Beni @ben_issen You feel saas is dead when you build with Astra. Made an inbox to unify all my chats for fast triage. 4 prompts. 6:07 PM · Sep 17, 2026 · 30.3K Views 21 Replies · 4 Reposts · 296 Likes Dev Ed @developedbyed Running Jev to see how fast it can remove negative comments from chat 11:03 AM · Sep 20, 2026 · 383K Views 182 Replies · 121 Reposts · 5.59K Likes Find me on X , Linkedin , or YouTube

Read about me and Ben’s Bites

📷 thumbnail via @keshavatearth