Vercel makes any agent harness durable
Vercel's durable-harness runs Pi, OpenCode, Codex and Claude Code so they resume after crashes and can run for days. It ships adapters for the popular harnesses and works self-hosted too.
Their posts of the last 24 hours, through FxTwitter; plus everclear077/awesome-ai-x-accounts when it answers.
What tech Twitter is discussing, ranked by discussion.
The front page, plus stories over 80 points in the last 24 hours.
Every new issue, each delivered once, looking back up to 7 days.
Next.js patches two critical RCE flaws» Page 4
The future of CSS, through Interop 2027» Page 4
tsrs: TypeScript's compiler ported to Rust, up to 8x faster» Page 4Pergent
The tech daily written for one reader
Wednesday, October 21, 2026No. 37Price: $0.08
Vercel's durable-harness runs Pi, OpenCode, Codex and Claude Code so they resume after crashes and can run for days. It ships adapters for the popular harnesses and works self-hosted too.
Node 26.x, 24.x and 22.x get security fixes, the highest rated high.
The new React Native release is available now.
His view is that the problem is confidence, not speed, and the fix is letting agents verify their work like humans do: run it, use the UI, seed data.
Content mappers let TypeScript read files like .md or .vue and give them static types, so you can import typed frontmatter directly. Colin Hacks calls it a game changer.
It runs dozens of agents across Claude Code, Codex and OpenCode, and keeps them going on HF Spaces.
Perplexity Computer runs its model and agent locally on a Mac, with no cloud and no WiFi needed. Sensitive local files never have to leave the machine.

You can move sensitive chats into a protected space. New messages there do not update the memory used in your normal chats. It rolls out to most plans starting today.
DeepSeek released DeepInfer, the software that runs its V4.1 Flash model at scale, under a free Apache 2.0 license. It is built mostly on vLLM and it hit number one on Hacker News with 2,200 points.

Mistral's new speech model, Voxtral 3, went to the top of Hacker News with almost 600 points. Read the launch post for the details.
Humming is a single library of fast kernels, the low-level GPU code that does the math, for all quantization formats and GPUs. vLLM and Ant Group say it gives up to 5x kernel speedups and 14 to 43 percent more MoE throughput.
Users say Claude Opus 5.5 feels worse. Theo's Nerf Bench says it is actually 5.8 percent smarter than at launch. Riley Brown adds that only Claude and GPT feel usable to him, which gets a lot of replies.
Some recent papers say models are absorbing the harness, the code around them. Omar Sarar calls that a claim built on weak tests on benchmarks that models already ace, and says a stable minimal harness still matters.

Clem Delangue says a Netflix documentary about a cyberattack on Hugging Face used too much doom and skipped how the team defended itself. Kevin Roose and Arvind Narayanan's circle say the 'AI is normal technology' view looks odd after a rogue-agent attack.

Two remote code execution bugs were patched: one in use cache functions from a React Server Components bug, and one in the image optimizer's SVG handling. Upgrade to 16.4.1 or 15.5.28 because a public proof-of-concept already exists.

Josh Comeau walks through what browser makers plan to make consistent next year. It is a practical look at what can be used without hacks.

Cloudflare and VoidZero ported the Go-based TypeScript 7 compiler to Rust. It runs as a drop-in replacement, is experimental, and can run in WebAssembly. Steinberger says it made his OpenClaw setup about 5x faster.
eMudhra, a certificate authority that issues the trust that makes padlocks work, leaked intermediate private keys that anyone could recover in seconds. With them, a scammer could mint a fully trusted certificate for any site, such as irs.gov, and sit in the middle.

Peter Steinberger ran an agent loop for two weeks. The result is a smaller JS and CSS footprint and finer update control, with checks every other day.
A Google Cloud outage hit many banks in Europe and the UK, including HSBC, Revolut and Bank of Scotland. Revolut had a 7-plus hour incident, and Gergely Orosz notes that Monzo has a stand-in bank for exactly this case.
A breach of the OpenCode console exposed AI API keys and led to unauthorized charges.

Inception's Mercury 3 generates several tokens in parallel, reaching about 1,000 tokens a second. It matches Haiku and GPT-6 Luna class models on quality and costs 10 cents in and 35 cents out per million tokens during its launch promotion.

Reuters reports one hacker used autonomous agents against over 1,200 websites and compromised over 100 companies' sites, including Deere and Cummins. How much data was stolen is still unclear.

Across 13 open transcoders, many late-layer features are close copies of single MLP neurons, and only those keep a stable link to the underlying network.

Vals AI says DeepSeek's 1017 model beat GPT-6 Sol, which was tested via OpenAI's trusted access program, on a multi-step cyber task. Full results come in the next weeks.

Peec.ai ran a test where made-up statistics spread across the web and got cited by AI models. It is a strong example of how AI search can be gamed, which is also what agencies are chasing.