Blog

AI news, software analysis and practical guides from the Telli.sh team.

93 articles

Four frontier models in three days, and nobody will tell you which one you needed
ai industry

Four frontier models in three days, and nobody will tell you which one you needed

Between September 1 and 3, 2026, Anthropic, Meta, Google and OpenAI all shipped frontier models, and CNBC gave the resulting exhaustion a name: model fatigue. The number of releases is the boring part. The interesting part is that every release creates an evaluation somebody downstream has to run, and the companies shipping them have no reason to help you skip it. A look at what a model swap actually costs, why cheaper per token is not cheaper per task, and why fully-managed software built for one narrow job is the only arrangement where somebody else can make the decision for you.

Ken Jo16 min read·Read more
NVIDIA agreed to buy a model hub for $12.93 billion. The bigger prize is the default
ai industry

NVIDIA agreed to buy a model hub for $12.93 billion. The bigger prize is the default

On September 3, 2026, NVIDIA agreed to acquire Hugging Face for $12,930,300,000 — its second-biggest deal ever, after $20 billion for Groq's assets. Hugging Face began in 2016 as a chatbot app for teenagers and ended up hosting 3 million models for 18 million developers. A close read of how it got there, why NVIDIA's two previous platform bets ended in opposite ways, and where the neutrality promise will actually be decided: not in a blog post, but in kernels, quantization formats and default deploy targets.

Ken Jo13 min read·Read more
Clip files a web page in your notes with the summary already written. Today it opens to every Telli.sh account.
product update

Clip files a web page in your notes with the summary already written. Today it opens to every Telli.sh account.

Clip turns a web page into a Telli.sh note with an AI-written title and a one-line summary, not just a saved link. It shipped behind an admin flag, so two analytics counters never fired once. That gate is gone: free accounts get 30 saves and 10 AI summaries a day, and version 1.18 of the browser extension adds a right-click Save to Telli.sh that authenticates with a token which can do nothing but save clips.

Ken Jo14 min read·Read more
40 minutes instead of 75: what GPT-6 Astra is genuinely good at
ai models

40 minutes instead of 75: what GPT-6 Astra is genuinely good at

OpenAI shipped GPT-6 Astra on September 3, 2026 and called it the world's most intelligent model. Its own announcement tables tell a sharper story: enormous jumps on narrow tasks — Terminal-Bench Science 22.4% to 64.6%, SRE-Bench 55.9% to 88.0%, OSWorld at 47% less time per task — sitting on top of a neutral aggregate that moved three tenths of a point. Where the gains are real, where the asterisks are, and what a 1M-token text model still cannot do.

Ken Jo15 min read·Read more
Google's UCP puts four headers on every checkout. Three exist for the argument afterwards
ai agents

Google's UCP puts four headers on every checkout. Three exist for the argument afterwards

The Universal Commerce Protocol shipped on January 11, 2026 with Google, Shopify, Etsy, Wayfair, Target, Walmart and 20+ endorsing partners. Read the spec and the shopping is the boring part: /.well-known/ucp discovery, RFC 9421 message signatures, mandatory webhook signing, and an AP2 mandates extension whose entire job is making an agent's purchase non-repudiable. A close read of what UCP actually standardises — and the one thing it standardises that has nothing to do with buying.

Ken Jo14 min read·Read more
The extension popup was answering the wrong question. In 1.16 it draws the page you are on instead.
product update

The extension popup was answering the wrong question. In 1.16 it draws the page you are on instead.

Telli.sh: Every Translator 1.16 rebuilds the toolbar popup as a status view: a miniature of the page you are on, five labelled chips, and dots that go green only when the extension can confirm it is running. Every setting moved to a dedicated settings page with live skeleton previews, instant translation gained its own tab with a self-pruning 30-day history, and a notification bell now carries the Telli.sh blog in your browser's language across 15 locales.

Ken Jo13 min read·Read more
One install command and a bot token: setting up OpenClaw 2.0 when you have never run an agent before
guide

One install command and a bot token: setting up OpenClaw 2.0 when you have never run an agent before

A verified, step-by-step OpenClaw 2.0 setup guide for beginners: the Node version you need, the three ways to give the agent a model and what each costs, the exact six-step guided onboarding introduced in v2026.8.1, the four-step Telegram pairing flow, three first tasks worth running, the day-one permission settings that keep the blast radius small, and the five failures new installs actually hit.

Ken Jo18 min read·Read more
OpenClaw 2.0 shipped half of everything the project has ever merged — after seven weeks of not shipping at all
ai agents

OpenClaw 2.0 shipped half of everything the project has ever merged — after seven weeks of not shipping at all

On August 31, 2026 an open-source AI agent released v2026.8.1: 16,000+ pull requests from 933 contributors, roughly half of every PR the project has ever merged, after 49 days of deliberate silence following 106 releases in 230 days. The setup wizard now imports the ChatGPT or Claude subscription you already pay for, or finds your local Ollama models. Sessions moved to SQLite and downgrades are no longer free. A close read of what 'AI you own' actually looks like — including the breaking changes and the defaults that are still off.

Ken Jo23 min read·Read more
A consecutive interpreter doubles your meeting. A live translator forgets it. What Thai teams are actually choosing between in 2026.
ai translation

A consecutive interpreter doubles your meeting. A live translator forgets it. What Thai teams are actually choosing between in 2026.

Bangkok agencies publish consecutive interpreting from 3,000 THB an hour and simultaneous from 5,000, and consecutive roughly doubles how long the meeting runs. Google Translate's Live translate covers 74 languages including Thai, Google Meet's translated captions cover 69 including Thai — and Meet's Transcripts and Gemini note-taker cover 8 each, neither of which is Thai. Deepgram's Nova-3 transcribes Thai as th and th-TH but excludes it from the 10-language code-switching mode, which is exactly the Thai–English sentence your meeting is made of. A full accounting of meeting translation options for Thai teams.

Ken Jo22 min read·Read more
Same 10.0% error rate, opposite decision: how to measure meeting transcription accuracy
guide

Same 10.0% error rate, opposite decision: how to measure meeting transcription accuracy

Word error rate scores the word 'not' and the word 'the' identically, which is why two transcripts can both land on 10.0% and only one of them be usable. Here is the full measurement procedure: a 12-minute test clip built to meeting specs, a reference transcript with frozen normalisation rules, the exact cpWER and DER commands, and a five-dimension scorecard that gives raw WER 10 points out of 100.

Ken Jo15 min read·Read more
40+ languages translated live, then deleted at hang-up: multilingual transcription is the layer that keeps the meeting
ai translation

40+ languages translated live, then deleted at hang-up: multilingual transcription is the layer that keeps the meeting

DeepL launched Voice-to-Voice on April 16, 2026 across 40+ languages, and the same product's FAQ says meeting data is 'processed temporarily in memory and deleted once the call ends.' On August 28 the Open ASR Leaderboard added its first Global South language and showed two models tied at 4.9 WER differing almost fourfold in how much their accuracy depends on where the speaker is from. Real-time meeting translation is becoming a commodity. The record is not.

Ken Jo13 min read·Read more
An anonymous model burned 26 trillion tokens in four days. Its price list arrived later: 24 cents.
ai models

An anonymous model burned 26 trillion tokens in four days. Its price list arrived later: 24 cents.

On August 20, 2026 a model with no lab, no card and no price appeared on OpenRouter as stealth/ox-alpha. Four days later OpenCode users had pushed 26 trillion tokens through it. Six days later Z.AI put its name on it: GLM-5.3-Flash, 320B total parameters, MIT weights, $0.15 per million in. Why labs now ship models without their own name attached, what the traffic numbers really measure, and what a 24-cent blended price does to the economics of speech pipelines.

Ken Jo16 min read·Read more
Nova-3 added its 58th language this month. Only 10 of them work in the same sentence.
speech recognition

Nova-3 added its 58th language this month. Only 10 of them work in the same sentence.

On August 4, 2026 Deepgram added Punjabi and Nepali to Nova-3; on August 7 it added Armenian and improved Tamil, Indonesian, and Belarusian. Nine months ago the model covered 31 languages — today the docs list 58. But code-switching still works in exactly 10, and August's own changelog shows Indonesian improving in batch while Belarusian improved only in streaming. A look at the pace of speech-recognition language coverage, and at what the word 'supported' is actually hiding.

Ken Jo13 min read·Read more
Google will translate your Vietnamese meeting in real time. It will not write a word of it down.
ai translation

Google will translate your Vietnamese meeting in real time. It will not write a word of it down.

Google Meet's translated captions cover 69 languages including Vietnamese, and Google Translate's Live translate covers 74. Meet's Transcripts feature and its Gemini note-taker each support exactly 8 languages, and Vietnamese is in neither. DeepL Voice can only transcribe spoken Vietnamese through a third-party provider that has to be enabled by an admin and cannot use auto-detect. A look at what live voice translation actually gives Vietnamese teams in 2026 — and what it never gives them.

Ken Jo15 min read·Read more
Nobody said September: the nine-minute review every AI meeting summary needs
meeting operations

Nobody said September: the nine-minute review every AI meeting summary needs

Research on meeting-transcript summarization found that 30.4% of generated summaries of city-council meetings carried at least one factual error, and seven distinct error types behind them. A practical guide to reviewing an AI meeting note against its own transcript: what to check, in what order, and what to say in the room so the review takes nine minutes instead of thirty.

Ken Jo17 min read·Read more
The re-meeting: how to stop your team deciding the same thing twice
guide

The re-meeting: how to stop your team deciding the same thing twice

OpenAI's July 2026 research found that 43.5% of occupation-specific ChatGPT messages are about work outside the user's own job. That kind of work runs on context — and most of an organization's context evaporates in meetings. A practical guide to turning meetings into searchable work knowledge: what to capture, how to name it, which meetings deserve a durable record, and what search changes for onboarding and handovers.

Ken Jo12 min read·Read more