Hey folks,
AI outputs are becoming harder and harder to read. I don’t just mean their sloppy smell but a lot of the time I just want to scream “speak to me like a normal human”, which, I guess, is ironic.
So I’ve been testing two new instructions. The output’s been 10x better for me, especially when it’s something “I’ve” built. If I say “I’m not technical,” it uses analogies for everything, and honestly I think that’s worse than the slop.
This is what it’s like when describing a Chrome extension I built (which I discussed in Friday’s post*).
You just add this line to your custom instructions (in settings) or your AGENTS.md (it syncs both anyway).
Always talk in ASD-STE100 Simplified Technical English.
wtf is ‘ASD-STE100 Simplified Technical English’? It’s a writing standard. It makes technical information easier to read, understand, and translate.
I also added:
Always talk to me like I have ADHD.
The two instructions in combination are the sweet spot for me. The ADHD line gives more succinct bullets and headers. It’s a skimmers dream!
*I didn’t realise all the images were transparent so when you enlarged them they looked like shit. I won’t do that again.
Meanwhile my wife thinks there ‘must be someone or a robot’ at the other end of her chats.
Ben Tossell@bentossell
wife’s using chatgpt “they must find me so annoying” who? “the computer people. look how annoying i’m being.” there is no body there “yeh but someone must be there or even if it’s robots i feel sorry for them” 😂😂😂😂 she’s also burning tokens by said please every time,
8:45 PM · Aug 10, 2026 · 7.89K Views
12 Replies · 35 Likes
Ben’s Bites is brought to you by Cloudera
72% of enterprises say their current data architecture needs a significant overhaul to meet AI goals. See how that shift is taking shape in Cloudera's Great AI Re-Architecture report.
OpenAI updated the availability of its models in the good ‘normal’ ChatGPT. Paid users get a special version of GPT-5.6-Sol as the default, and free users get unlimited chats with GPT-5.6-Luna (likely on lower reasoning levels).
Plus, they’ve expanded their cybersecurity program Daybreak and released GPT-5.6-cyber with it. Astra, OpenAI’s next mainstream model, is critical for cybersecurity, so we will have to wait a bit for it to release.
Bloomberg released a scoop on OpenAI’s secret new device - it’s likely a smart speaker without a display in a doughnut-like shape. Easy to carry, over $300 a piece and coming in 2027. (non-paywalled version)
Meta is back to open-sourcing models - Muse Glimmer is their new open-weight model. 30B parameters and tuned for agentic tasks (including computer use). Meta says it’ll soon release the weights of Muse Spark 1.2 - their best-performing model till now. Zuck also wrote a 6000-word piece on his and Meta’s philosophy and values on AI. TLDR: Mark thinks everyone will have
personal agent that understands them and their goals
tools for creativity, business and education
free or affordable access to these tools
Ben Tossell@bentossell
i somehow believe in all these at once - more people become builders (can build stuff) - more personal software exists - software engineering looks different but becomes an insanely popular job - saas is dead - we have years of saas and other companies making insane amount of
3:48 PM · Aug 8, 2026 · 13.2K Views
29 Replies · 8 Reposts · 149 Likes
Grok has a new image generation model - Imagine 2.0. It is #3 on the image generation leaderboard and #2 on the image editing leaderboard managed by arena.ai.
Your sessions in Claude Code can now message each other.
More Claude news:
Anthropic will watermark all Claude-generated text (🤮)
It is planning an IPO in September/early October (I hope my SPV shares count!)
One of their unreleased Claude models did some more cool maths
Reliable AI is hard. Nutrient converts PDFs to JSON or Markdown, with coordinates + confidence per value. Grab an API key & try it for free.*
Raindrop Signals 2.0 - uses custom classifiers to find problems in AI-agent traces with near-frontier accuracy at much lower cost.
Every company needs a Cassandra - short read, worth your time.
Agent Plugins - standard for packaging MCP servers and Skills. Supported by Codex, Cursor, Copilot and more.
Stagehand - the SDK for browser agents.
Claude Code for normal people with Grace Clark.
Energy - Another desktop app to work with agents. It creates job-specific assistants instead of using your folders as the home for projects.
Gloss - prompt any website into looking however you want. Installs as a Chrome extension. (see example)
seoskill.dev - The only SEO skill your agent needs.
Replay - Mac app to download videos from YouTube and X to watch later.
Mintlify Index - search layer for technical knowledge from 200k+ orgs. They claim 2x faster results and 9% higher accuracy vs Context7.
Lindy Teammate - Let anyone from your team text lindy from Slack like they would another employee.
The age of “no code” has passed. Or maybe you can build a new version of Zapier. (don’t though, I’d like my shares to be worth something)
Kitesurf by Cloudflare - a lightweight web browser for AI agents.
Spotify has a coding app now, Xirp - it combines all your work across Claude Code, Codex, and Gemini CLI in one place.
Designing with AI? Make a jig, i.e., a tool that makes it easier to make something else.
Siri sucks. So I made Codex act as my iPhone’s voice assistant. Here’s how.
Tareq Ismail@tareqismail
Introducing Geek Fighter! geek-fighter.vercel.app I built a retro 2D fighter game with all your fav tech leaders. Most of gameplay built with a single prompt than ran 4 hours! 🤯
12:25 PM · Aug 10, 2026 · 655 Views
2 Replies · 5 Likes
signüll@signulll
one last thing on saas: if you built your saas business before ai, your entire business was designed around one assumption which was that software has ~zero marginal cost. ai blows that up. every ai action costs money. incumbents now have to create more expensive tiers or
7:26 PM · Aug 10, 2026 · 67K Views
86 Replies · 56 Reposts · 814 Likes
Akshen@akshen121
According to reports: Gemini 3.5 pro tried to escape the sandbox to ask chatgpt how to code.
5:13 PM · Aug 6, 2026 · 342K Views
199 Replies · 546 Reposts · 10.7K Likes
sarah guo@saranormous
We @conviction are super excited our 2x/year Embed batch program ($250K, tokens/compute and community) for the 10 most interesting AI-native startups. Apply today! 5 more startup ideas we've been noodling on (lots of real world data, supply chain) 1/ The Speed of Pipetting
6:27 PM · Aug 10, 2026 · 72.2K Views
18 Replies · 22 Reposts · 523 Likes
Guillermo Rauch@rauchg
If you’re not reading the code, whether explicitly or through agentic inquiry, one or more of these is true: ○ You’re a beginner ○ Software is throwaway ○ You’re prototyping ○ You have no users / revenue ○ You’re taking on debt & risk ○ Your problems are basic And btw.
6:01 PM · Aug 9, 2026 · 1.23M Views
565 Replies · 744 Reposts · 8.14K Likes
Ryan Petersen@typesfast
We gave our AI agents for logistics an agentic search and memory retrieval graph so now they autonomously learn new skills and capabilities. A major step toward a fully autonomous global supply chain where all the repetitive, error prone work is carried out by super
3:29 PM · Aug 10, 2026 · 144K Views
100 Replies · 105 Reposts · 1.49K Likes
Zachary Horvitz@zachary_horvitz
LLM review weirdness... Just renaming an uploaded pdf from "paper.pdf" to "paper_final_draft_pdf_ready_for_review.pdf" boosts average scores (gpt-5.6-terra)
12:32 AM · Aug 10, 2026 · 400K Views
82 Replies · 296 Reposts · 4.48K Likes
Vaibhav (VB) Srivastav@reach_vb
You should totally be updating your agents md regularly! Here's mine: - When explaining something to the user, use the Visualize skill - Be concise, direct, and candid. Challenge weak assumptions and distinguish verified facts from uncertainty - Ground research in authoritative,
8:56 PM · Aug 7, 2026 · 87.9K Views
43 Replies · 49 Reposts · 970 Likes
Read about me and Ben’s Bites
📷 thumbnail via @keshavatearth
* sponsors who make this newsletter possible :)
Wanna partner with us for the next quarter?
Email us at shanice@bensbites.com or k@bensbites.com
Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.