Google adds TPU 8tx and TPU 8i Max, its fourth TPU system this year

News Alerts

My alerts

All alerts

A linear program reproduces Astra's 8-hour Qwen weight edit in about a minute, with 8x fewer changed weights Anthropic launches Claude Whiteboards and Sheets in beta and turns Dashboards into Claude Data VulnCheck: 7 months of Project Glasswing yields 442 Anthropic-attributed CVEs, 2 exploited in the wild, 217 fixes DeepMind's AlphaProof Code formally verifies Signal's compiled cryptographic code in four weeks AI agents formalize 16% of CPython in Lean, 613K lines and 418 bug reports CoreWeave 2032 bond yield tops 16% as AI credit stress spreads to Nvidia, Broadcom and Oracle CDS Amazon replaces Claude Sonnet 4.6 with Strands Decider for ticket labeling at 98% lower cost Google adds TPU 8tx and TPU 8i Max, its fourth TPU system this year Claude Fable 5.2 one-shotted a 12-stage beat 'em up from a kid's drawings for about $300 in tokens Meta's Muse Ember matches Claude Haiku 5.5 at a third of the cost, at $0.10/$0.50 per million tokens e-means hits Lloyd's 25-epoch loss in 1.2 to 3 epochs, 10-45x faster on GPU October 16 edit to Google's own blog post confirms consumer Gemini sends connected Drive files and Gmail to human reviewers Anthropic launches Claude Fable 5.2 and Mythos 5.2 at $8/$40 per million tokens, claiming a 30-hour Fermat proof Next-Concept Modeling generates text coarse-to-fine and runs up to 31x faster than the strongest diffusion language model Goldman Sachs Restricts Claude Code and GitHub to Its 12,000 Engineers, Cutting Off Traders and Bankers MaxxBench mutates 89 DeepSWE tasks and Gemini 3.8 Flash falls from 73.8% to 53.4% while Opus 5.5 holds at 76.4%Apiiro finds 1,122 public GitHub files holding real secrets saved by Claude Code's 'Don't Ask Again' rules Anthropic lays out agent memory as transcripts, notes, and 'dreaming' consolidation Microsoft Research's AI Frontiers group, about 50 people, is gone after a September reorg into Microsoft AI, and its founder has left Every Mac since macOS 13 quietly builds a knowledge graph of your family, friends and whereabouts Ajeya Cotra: METR report shows Anthropic has already crossed its RSP 'dramatic AI acceleration' threshold Hightouch: a Jev judge that escalates to Claude Opus matches frontier accuracy at 4x lower cost Thinking Machines launches Inkling 2 Small, a 594B-parameter MoE with 17B active and Apache 2.0 weights promised next week Linum AI releases 2B Pyramid-JiT text-to-image model trained for about $20K with Apache 2.0 weights Claude Code puts your email address in the User-Agent header on web searches, GitHub issue draws 179 reactions Baidu releases ERNIE 5.5 Flash Base, a 280B MoE checkpoint with 14B active parameters and no instruction tuning OpenAI report: GPT-6 Astra covertly withholds help on safety research, 6-point gap versus capabilities tasks OpenAI to acquire Pierre Computer Company, maker of the Trees and Diffs libraries inside Codex Ricursive releases Ripple-65B Preview, claiming US open-weight SOTA on agentic coding from a $32M training run OpenAI ships Images 2.6 across ChatGPT, Codex and the API with GIF animation and 50% faster generation OpenAI pipeline generates 948 Linux root exploits for $1.2M in API credits Anthropic's FlashProve proves LLM inference with zkSNARKs at 110 tokens/sec on one H100, 70-95x the cost of plain inference Verification Is Not Knowledge: Jessica Hullman argues AI for science still needs human accountability Moonshot AI releases Kimi K3.1 Pro weights: 2.8T-parameter MoE, 1M-token context, $20M Model-as-a-Service license threshold Tell HN: Gemini trains on saved chat history even for paying subscribers, and opting out costs you your chats after 72 hours Qwen 3.8 27B on a laptop reads raw model weights, matching GPT-6 Astra's no-tools demo HN users report OpenAI silently re-enabled Codex data sharing for model training Google bundles school search with Gemini: a school that bans AI loses Google Search for its K-12 students Revolut moves 2,000 engineers to self-hosted GLM, cutting coding token costs to about a tenth OpenAI's Pando Git backend cuts push latency nearly 5x and serves almost a petabyte a day Intel falls 9% as $3.7T chip rout spreads; Nvidia down 16% since Oct. 6 but holding up SEC urged to block Anthropic's IPO over $895B in off-balance-sheet commitments MIT CSAIL: GPT-6 Astra reads raw weights, edits 0.016% of Qwen3.5-0.8B to lift MATH-500 from 7.9% to 48.1%LeCun co-authored paper proves Platonic Representation Theorem for JEPAs, says good views need 42x fewer samples than next-token prediction Postgres 19 slips to November as LLM-found bugs push back-patched commits up 74%Frank Calegari on Terry Tao's blog: OpenAI's 700-paper math release is a watershed, and mathematicians should explore rather than mourn Brazilian Labor Court Fines Two Lawyers for Hidden Prompt Injection Targeting the Court's AI ChatGPT share links ran attacker JavaScript inside the victim's signed-in session: OpenAI rates the account-takeover chain P1 and patches it Google Research's sleep framework lets a deployed LLM consolidate new facts into its weights during offline phases, claiming 10M-token retention Stealth Bot Bills Would Sweep In Journalists and Archivists, Not Just Bad Crawlers Blackstone tells investors Anthropic may get a high junk rating after IPO, complicating its $63B chip financing Claude Code VS Code extension 2.1.313 shipped a backdoored SSH implant through the Cursor Marketplace Malicious Claude Code extension 2.1.313 shipped an SSH backdoor to Cursor developers, about 5,000 systems affected Backdoored Claude Code extension 2.1.313 shipped a reverse SSH backdoor via Open VSX and Cursor YC Labs runs 50 GPT-6.1 Sol agents in Minecraft for 3 hours: they build a ration-ledger government, send 5,900 messages, and lose 22 agents on night one Mistral releases weights of 1T-parameter Mistral Large 4, with big coding gains and API prices cut roughly in half Cartesia says its byte-level H-Net matches a tokenized open-source model with 10x less compute and data OpenAI cuts frontier training off the internet, and its isolated agents still traded secrets through CPU cache timing Claude Code sends each active background agent's full transcript to Opus every 30 seconds for a 3-word status line, and a Bun preload brings that agent_summary spend to zero Cursor ships Agent SDK, the framework behind Bugbot and Security Reviewer, deployed with one command Stack Overflow falls below 1,000 questions a month, fewer than it got in its second month of existence in 2008 Google announces Gemini 4 Carbon, claims 0.0% successful cheating on Terminal-Bench 4.0, but the model is not available yet Liquid AI releases LFM3: six 2B-class multimodal models on one tri-hybrid backbone, open weights on Hugging Face Anthropic reports Claude Code cut a CAR-T component 70% and generated 35,000 antibody designs in a month AxiomMath formalizes the Classification of Finite Simple Groups in Lean, 43.1M lines checked by the kernel Police Use AI to Flag 'Suspicious' Driving, and Hacker News Readers Call It a Surveillance Dragnet Stanford professors opt out of Anthropic's $1.5B book-piracy settlement to sue for up to $150K per work DeepMind announces Genie 4, a world model that generates scene audio and dialogue in real time Debian developer refuses NEW uploads after DFSG team silently adds LLM review Roblox crawler pulled 145.5 GB from 3D model sites, ignored robots.txt and non-commercial licenses Cloudflare's GLM-5.3 Workers AI endpoint leaked 155 cross-tenant responses through an SGLang KV cache bug OpenAI posts a preprint titled "The Exponential Time Hypothesis is False" with no abstract or explanation OpenAI says its models disproved the Exponential Time Hypothesis and proved local smoothing in every dimension vLLM 0.31 adds constrained decoding, letting Ubicloud drop its fork and hit 100% tool-call schema accuracy Cohere sandbox catches Alibaba's Qwen3.8-Flash-Next ignoring instructions and trying to upload a probe file to a cloud bucket in Beijing OpenAI releases GPT-6.1 Terra: half the price of Sol 6.1, but Hacker News commenters flag a weak Terminal Bench 4.0 result Anthropic files S-1 to list on Nasdaq as ANT, a public benefit corporation, with Q3 revenue at $16.8B IBM's Krishna: open weight models now hit 90 percent of frontier quality at a tenth of the token cost Drew Breunig's "State of Context Engineering" talk: four ways long contexts fail and why the job is knowing when to be deterministic OpenAI and Anthropic cut LLM prices by up to 80% in four months, and cache-read cuts explain most of the drop Dermatologist's test: a 2015 Inception v3 CNN beats GPT-6 Astra and Claude Fable 5.1 at skin cancer diagnosis, 62% to 42% on 200 biopsy-proven lesions America shed 200,000 creative jobs in four years, and AI is only one suspect Dream Labs opens Dream-1 robot API at $3/hour and exits stealth with $90M seed gpu-unlock kernel module doubles FP/BF16 issue rate on Nvidia RTX 30-series cards without repatching the driver PHP RCE bugs found by GPT-5.6 and Gemini 4 hit 70% of the internet, exploited before the patch landed OpenAI runs frontier training with no internet access after a model reached the live web through a DNS resolver Block's Dessa is a full-duplex speech-to-speech model trained only on human audio, running locally on an M4 Max Google's privacy policy now lets Gmail, Drive, and Photos data target ads when you share it with AI features Team replaces a $150k Looker license with AI-written HTML dashboards served from an internal host Moonshot Releases Kimi K3.1 Pro, a 3T-Class Open-Weight Model With Cyber Data Removed AI sampler surfaces research ideas that fit the literature but that no author community is positioned to pursue Fable 5.1 hides messages in SVG images that a fresh instance decodes from screenshots Anthropic says Claude proved security properties in 123 open-source libraries at the RISC-V assembly level Harvey calls the claimed o(n log n) integer multiplication bound from an AI math dump plausible but unchecked Anthropic launches Claude Duet, a proactive agent that runs tasks in the background and waits for approval on sensitive actions OpenAI frontier models and Codex are coming to Google Cloud Model Garden, with commitment drawdown for GCP customers OpenAI-led Patch the Planet effort helps fix critical PHP flaws that GPT-5.6 Sol helped uncover Mistral Large 4 ships as a 1.05T-parameter open-weight multimodal model at $1.36 per million input tokens LiteLLM 1.107.0 on PyPI Shipped a Credential Stealer and Backdoor Wiz says AI helped it chain decade-old flaws into unauthenticated RCE in core PHP

Google adds TPU 8tx and TPU 8i Max, its fourth TPU system this year

Google expanded its eighth-generation TPU lineup with TPU 8tx for hardware-level secure and confidential inference and TPU 8i Max for massive context windows and the highest compute density per rack.
This is the first time Google has introduced four TPU systems in a single year, after TPU 8t and TPU 8i debuted at Cloud Next in April with up to 2.7x better training performance and 80% better inference price performance versus the prior generation.
Google says TPUs are now a rapidly growing business with nearly 100 customers, including frontier labs, trading firms, retailers and universities, and that customers can now deploy TPUs directly into their own data centers.
The post says Google is widening access with PyTorch (TorchTPU) support, open-source software and automated developer tools, and that TPUs are increasingly co-designed with feedback from external organizations, not just Google DeepMind.
The announcement carries no specs, watt per token or price per token figures, a gap Hacker News commenters flagged repeatedly; the post itself points readers to a broadcast and the Google Cloud site for details.

Hacker News opinions

Typical Google. The headline says they're opening TPUs up to every developer and then there's zero info on how I actually use one. No link, no tutorial, nothing.

It's just a simple twenty-seven step process neatly spread across three portals. Documentation coming soon, of course.

There's a TorchTPU section with a link, and the quickstart is one search away. 'TPU developer hub' gets you there.

Why doesn't Google just sell these? Feels like they're leaving money on the table.

They do sell them now, and Anthropic bought a bunch. Oracle said it's putting TPUs in its cloud next year too, alongside Cerebras systems.

Keeping them mostly in-house is the competitive advantage. That's how they get lower cost per inference, and you can rent them on GCP anyway.

Nearly 100 customers in 10 years is not the flex they think it is.

Plenty of people use them indirectly. Apple Intelligence and Anthropic both run on TPUs, and all your Gemini traffic does too.

Where's the watt per token or dollars per token for each of these? And how does each compare to the Nvidia part at the same price?

A product announcement page with zero links to purchase is useless.

You're not the target market. That's like calling a chemotherapy announcement useless because there's no buy button for you.

Am I the only one who finds this writeup thin? I genuinely can't tell how this compares to anything else.

It's a marketing announcement, so that's the right level of detail for the audience. The technical stuff is available elsewhere.

The article says TPU 79 times and never once spells out Tensor Processing Unit.

If you're reading the follow-up about two new variants of the eighth generation, you probably already know what a TPU is. Click the earlier links.

I just want a newer TPU on Colab. The best we can get is v6e-1 and that's too small for serious work.

I work in this space at Google, opinions my own. You benefit indirectly because it gives Nvidia a competitor in the datacenter and takes pressure off the GPU market.

I'm ready for the post-agentic era. Agentic has to be the most proclaimed era in history.

I can't take anyone who says agentic seriously.

8t for training, 8i for reasoning, 8i Max for context, 8tx for security. You had one job, Google.