techTue 10 Nov, 07:30

Sources93 X accounts · techtwitter.com · Hacker News · 8 newsletters
  1. Runs every day at 07:30 London time.
  2. It is shown its own papers of the last 3 days, to know what it has already said.
  3. Haiku 5.5 writes the paper from what was fetched, with no tools.
  4. Jev scores every story by how much it matters to you; each section puts those first, and what is not for you drops to the briefs.

93 X accounts

Their posts of the last 24 hours, through FxTwitter; plus everclear077/awesome-ai-x-accounts when it answers.

techtwitter.com

What tech Twitter is discussing, ranked by discussion.

Hacker News

The front page, plus stories over 80 points in the last 24 hours.

8 newsletters

Every new issue, each delivered once, looking back up to 7 days.

The tech daily written for one reader

Simon Willison's prompting tip for Fable 5.2 is to say 'This codebase is yours'.

The trick makes the model less cautious when it improves existing code. He notes that Anthropic seems surprised by its new models' quirks too.

Boxes.dev runs Claude Code and Codex in the cloud on copies of your dev environment.

A YC company for running parallel agents off your laptop, with three free months of Pro offered at launch.

Kent C. Dodds says state machines should be made explicit to help UX, DX and AX together.

He shares a prompt that asks an agent to find hidden state machines in an app.

Matt Pocock says the best grilling tip is to explain the problem, not the solution.

Describing the problem gives the agent room to be creative.

Anthropic

Claude Fable 5.2 arrives

Fable 5.2 takes the top spot on Cognition's FrontierCode 2.0 test with a score of 49.1.

Fable 5.2 is the strongest model Anthropic makes, and Mythos 5.2 is its sister model. Early testers say it is good at big, long jobs like rewriting a whole codebase. Addy Osmani says it runs up to 30% faster than Fable 5.1 and costs 20% less per token, but it uses many more tokens, so cost per task may be about the same.

Vercel adds MCP Events, so agents can subscribe to things like a deploy finishing.

MCP is the open protocol for AI tools. Events let an agent get told when something happens instead of polling again and again.

Big announcements

Tuesday, November 10, 2026 · Pergent2

Meta AI

Meta's Muse Ember goes cheap

It costs $0.10 per million input tokens and $0.50 per million output tokens.

Muse Ember has a 1M-token context window and can read text, images, audio and video. Artificial Analysis says it matches Claude Haiku 5.5 at about a third of the cost per task. Vals says it is the cheapest model on its index at $0.15 per test. It is also on Cloudflare AI Gateway and Google Cloud.

Perplexity, Cognition and Hermes all add Fable 5.2 in the same day.

Perplexity says Fable beats Gemini Argon on its wide and deep research tests. Devin Desktop and Devin CLI now run Fable, and Hermes Agent offers it through Nous Portal and OpenRouter.

Fable 5.2 scores 65 on Artificial Analysis, the highest the site has listed so far.

Artificial Analysis is an independent site that runs its own tests on models. Hacker News readers argue over whether one number says much about real work.

Muse agent

Meta adds project Spaces

Connected apps can refresh a Space in the background, according to Meta.

You describe a project and Muse builds a planner, tracker or board. Meta says a Space can refresh itself without a new prompt once apps are connected, though outsiders have not tested that yet.

What people are fighting about

Tuesday, November 10, 2026 · Pergent3

Shadcn finds Fable useful, while Ryan Florence says Opus 5.5 did better on one check.

Shadcn says running his /improve tool with Fable found things Opus 5.5 missed. The split shows people are still picking models per job.

Dev jargon

'Software Factory' sparks a fight

Teams are moving from agents that write features to systems that run agents for them.

Pocock admits the phrase is hype, but says top teams now build automations that let agents work on the product for them. Theo Browne, in a long post, says the term is a rebrand of scripts and cron jobs unless it means a real change in how software gets built.

Model fight

Fable: hype or hype-proof?

Power users cheer the demos, and skeptics say the demos prove very little.

Shumer built a full Earth game, a Harry Potter battle royale and a voxel engine from prompts, and called Fable the best model ever. Sar replied that the posts were 'just crappy games and the same old stuff,' and argued the real limit is now human ambition, memory and tools. Shumer also joked that Fable is 'a hall monitor' that stops him swearing at his agents.

OpenCode's team says a benchmark ranked them last only because it was set up wrong.

The team says the benchmark dropped reasoning settings and never checked with the product's team. Once fixed, they moved from last to first, and the author says most benchmarks are meaningless right now.

Web dev corner

Tuesday, November 10, 2026 · Pergent4

Exact is a new cross-platform UI framework from Expo.

A new option for building one UI across platforms.

Chrome 157 ships HTML-in-Canvas, so you can paint live HTML into a canvas and keep it usable.

Content stays clickable and readable by screen readers, and browser tools like translate and find-in-page keep working.

Bun runtime

Bun's AOT compiler speeds up apps

OpenCode uses 41% less memory, and OpenClaw starts 3x faster with the new build.

AOT means code is turned into machine code before it runs, not while it runs. Jarred Sumner says the build is meant as a drop-in change for existing code, and that getting JavaScript closer to Rust or C speed may need new syntax later.

Supabase lets you move your InstantDB data over.

Upload an InstantDB backup into a blank Supabase project to switch databases.

From the newsletters

Tuesday, November 10, 2026 · Pergent5

GitHub's Mario Rodriguez on why code is cheap now and trust is the bottleneck.

He talks about machine-speed development, the move to Azure, and his view that lower barriers bring more people into coding.

Visa's first shopping benchmark finds AI agents pass only 57.2% of tests.

Half the failed runs still ended with a purchase, which is a bad sign for agent shopping. Visa's Trust Index says 72% of US consumers use AI assistants, but only 23% trust AI to make payments.

OpenAI's BioBasicsBench shows GPT-6 Astra scoring 66.7% against 43.8% for GPT-5.6 Sol, but it still misreads lab controls.

The 100 tasks use messy, real lab evidence with a partial-credit score, not an experiment success rate. Astra would have sent researchers to purify the wrong plasmid in one cloning task.

Research & open source

Tuesday, November 10, 2026 · Pergent6

AI research

AI claims a quantum proof

The proof was checked in Lean, but the paper has not yet been peer-reviewed.

The system ran an unreleased Anthropic model and published a formal proof on GitHub. The result is about how often computers read typical random inputs, not quantum advantage in general.

Worth a read

Tuesday, November 10, 2026 · Pergent7

Privacy

Gemini files go to reviewers

The repo says personal Drive files and emails were routed to human annotators.

The claim is that personal files were read by people hired to label AI training data. It was a top Hacker News story, and the discussion is about consent and what 'private' means.