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.
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
@bentossell352
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.
built myself a harness + token usage tracker splits by agent/model, copy instructions for your own bentossell.com/token-activity/
@bentossell204
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 everyone430. We covered the launch in the last post111, 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 it457 and a short explainer: What is Jev537? Some worth highlighting are:
An extension to skip sponsor segments206 on YouTube.
Filtering negative comments83 out of a chat in real time.
Search Gmail by intent128, or filter your to-dos64.
A new & smarter copy-paste134, drag-and-drop146 and Cmd+F71 experience.
Controlling your Mac with Voice161.
Naturally, a fair share of demos are trying to integrate Jev with modern coding agents. For example, using it for instant compaction41. It looks cool, but it’s a terrible idea31. 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.
— Keshav18
Coding agents are also on the mind of TypeSafe’s CEO - he wrote down his thoughts here113.
Projects in Claude Code119 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.md107 (via their new feature Claude Mods111).
Muse, Meta’s personal AI agent, is getting love from everyone (who has access). It has a Mac app75 and a developer platform to build connectors31, so people can use external services through Muse. And of course, it’s heavily inspired by OpenClaw33.
Muse can shop for you - well, it could, until Amazon started blocking it30. Meta is working on it, with partnerships like this one with Shopify28.
Grok 4.7 is out30. 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 Linden44, 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 credit44.*
OpenAI formed an independent group of mathematicians44 to help them share the proofs and discoveries their agents are making.
Test your agent in simulations with Raindrop147. (They raised a Series A recently)
Turning your best X posts into an automated blog and newsletter88.
How to ship 2,500 PRs to production153 in a month.
A free, open-source Photoshop-like image editor282.
A look inside Instinct’s memory160, reverse-engineered.
A transcription model from SpaceX AI - Grok Voice Transcribe 2.047.
How to build a restrained software factory159.
Powermove97 - a video editor you can change by talking to a coding agent.
MCP vs CLI for LLMs137 - are we debating the wrong thing?
Factory is now available in Slack Code43.
On July 25, we hacked OpenAI79.
Agent skill to make a demo video of your app167, with zooms and voiceover. I used this for my devices tweet in the intro.
Exa Snapshot57 - Let agents search the past versions of the web.
Epoch audited 15 AI benchmarks32 and found flaws in nine.
Natural General Intelligence45 - a call to work on AI models for the planet to avoid natural disasters and more.
Accenture’s evaluators will work inside Anthropic32 to check AI safety, with access similar to its employees.
Speeding a 4B model to 730 tokens/sec on an M5 Max132. 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.
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.…
@nutlope99
@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.
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 …
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
@argofowl133
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.…
You feel saas is dead when you build with Astra. Made an inbox to unify all my chats for fast triage. 4 prompts.
Running Jev to see how fast it can remove negative comments from chat
Read about me8 and Ben’s Bites
📷 thumbnail via @keshavatearth18
* sponsors who make this newsletter possible :)
Wanna partner with us for the next quarter?
Email us at shanice@bensbites.com9 or k@bensbites.com8
What can you build with Jev
Muse is off to a good start
2,482 readers clicked at least once. 60 links, 60 with clicks. Heat is relative to the most clicked link in this issue.
Substack · essay