Silicon Feeds
Today's sponsor is https://www.amtechmicro.com Richard Ho leads hardware at OpenAI. He joined Google's TPU program as one of its first engineers, built Anton supercomputers at D. E. Shaw before that, and now runs the team behind Jalapeño. He tells me how close he came to a blank cheque, why the team bet on wiring HBM…
VP Hardware for Jalapeño
Financial markets have always relied on timely information, and the drive for timeliness has always adapted to the latest technology. From clipper ships transiting the oceans to telegraph wires connecting cities to fiber-optic cables conducting trades in microseconds, traders have embraced any advantage to get the…
Cadence, Synopsys, and Siemens all offer agentic AI for chip design, largely built on Nvidia's stack, with varying claims of autonomy.
NuvaCore says it is developing its new WarpCore CPU IP without first choosing the ISA it will implement. This unusual development strategy is meant to offer the company maximum technology and business flexibility.
In a personal blog, former EVGA product manager Brendon Ray Hedrick shared how the first Nvidia Founders Edition GPUs alarmed the company and how pricing pressure and risky forward-looking tech ultimately led to the end of the two companies' storied partnership.
Laptop chips have gotten very powerful in recent years, with increasing CPU core counts, more powerful iGPUs, and higher DRAM bandwidth to feed that compute.
Sponsor: ID-Cooling Frozn A620 SLK on Amazon https://geni.us/Vc8Zi NVIDIA keeps talking about GPU rentability, GPUs equaling GDP, how fantastic scarcity is for its business, and how it definitely, absolutely isn't engaging in circular financing. No, NVIDIA says it is not a circle. It's a cycle. A "virtuous cycle" --…
The owner of a Zotac RTX 3060 in India was denied warranty coverage just one year after buying the card in 2025, despite Zotac's offer of a three-year standard warranty in the country. The company claims that the warranty begins from the date of import, not the date of sale, and that the card was imported in 2023.
I walk the show floor at TSMC's Open Innovation Platform (OIP) event in the Bay Area. It's a one-day conference where TSMC puts its partners front and centre. We stop by Cadence, Samsung, SK hynix, Synopsys and GUC to see what's next for HBM thermals, co-packaged optics, UCIe 2.0 and AI-assisted chip design. If you've…
How close is AI to designing the very same chips it runs on? We explore how artificial intelligence is being used in modern chip design today.
Intel is prepping Core Ultra 400-series 'Nova Lake' platform launches as CPUs and chipsets pass interoperability and compliance tests with PCI-SIG and USB-IF.
AMD has shared the full SKU list for its 6th Generation EPYC 9006 (codenamed Venice) series, with 1Ku pricing.
A recently published Intel patent reveals a system for embedding MicroLEDs directly into a CPU for diagnostic or aesthetic purposes.
Learn how engineers can shift from manually managing tools and handoffs to defining objectives and supervising AI-driven execution across the silicon development lifecycle. Key Takeaways Explore four critical technologies enabling silicon design autonomy Understand how autonomous AI accelerates complex engineering…
Samsung Electronics, Samsung C&T, Samsung SDS, Samsung SDI, Samsung Life Insurance and Samsung Fire & Marine Insurance today announced they are investing a combined USD 1 billion in Helix Digital Infrastructure, an AI infrastructure company established by global investment firm KKR. Launched in June 2026, Helix is an…
GLM-5.3, KV Cache Offloading, HiSparse, DeepSeek Sparse Attention, IndexShare, Single-rollout Asynchronous Optimization, Cybersecurity
Check it out here: https://newegg.io/nc24068d37 You can find us... Twitter - https://twitter.com/level1techs Twitch - https://twitch.tv/teampgp Patreon - https://www.patreon.com/level1 For all our social links, websites, and more, check out our link tree! https://linktr.ee/level1techs Thank you for watching!…
Synopsys unveiled seven AgentEngineer agents on its new Autopilot platform, with general availability planned for the end of 2026.
The Noctua Edition replaces the original WireView Pro II cooling solution with a semi-passive design that can handle up to 300W without active cooling and runs below 2,000 RPM when the fan is needed.
An unofficial project is bringing Nvidia’s DLSS 5 to AMD Radeon GPUs, with early testing showing performance climbing from around 30 FPS to 50 FPS in Cyberpunk 2077 after rapid optimization.
Forget the data center - the real AI action might be happening in microwatts. Sally Ward-Foxton and Ian Cutress dig into the tiniest AI chips on the market, from analog compute upstarts to ARM's revived Ethos NPU line, and debate why an "AI ASIC" isn't really an ASIC at all. Plus: a mysterious defense-linked startup…
Links: - Patreon (Support the channel directly!): https://www.patreon.com/Asianometry - X: https://twitter.com/asianometry - Newsletter & Podcast (available through Stratechery Plus): https://asianometry.passport.online/ - LinkedIn (feel free to connect): www.linkedin.com/in/jon-y-asianometry
The two PlusAI trailers with Nvidia-partner markings were apparently left outside the startup's warehouse, making it a juicy target for criminals looking to make easy money on AI GPUs. However, they were deliberately left outside as the trailers only contained sand for simulating real-world truck loads.
My job is to translate dry and unrelenting code into a user interface of surpassing beauty. With my mouse, I roll one pixel after another up the vast anthill of the internet. My dream is to translate the visions of the holy ones into a communication protocol of universal wonderment. I want to launch shreds of light…
A deep-dive into the 2nm Apple A20 Pro SoC, based on die shots from @SemiAnalysis STEEL. How does the first TSMC N2 chip work? Check out the open positions at STEEL: https://semianalysis.com/semianalysis-careers/ Support me on Patreon: https://www.patreon.com/user?u=46978634 Follow me on X: https://x.com/highyieldYT…
Looking inside Intel 18A and Intel’s Panther Lake. A free SemiAnalysis STEEL teardown.
The Sandisk Optimus GX Pro 850P is a WD Black SN850P by another name. It’s a great PS5 SSD with good performance in a mature package, but with a stiff premium.
Nvidia’s RTX Mega Geometry 2.0 SDK arrives alongside RTX Kit 2026.3 with on-demand ray-tracing geometry streaming.
A user's GeForce RTX 5090 died when his 12V-2x6 connector melted, and then PNY denied his warranty claim based on technicalities that aren't even present in the warranty policy.
Part 1 of an extended discussion, covering the Softbank takeover of Arm in 2016
1,000+ facilities across 60+ operators mapped, built retail-first and flipped by AI, largest hyperscaler leases 1/5 national capacity, 100MW in 12 months, Eastern Data Western Compute
Meta's new Muse AI agent is powered by AMD EPYC Turin hosts, with each user getting a private sandbox with two vCPUs and 8GB of memory.
Forget the data center - the real AI action might be happening in a coin-cell battery near you. Ian Cutress and Sally Ward-Foxton dig into six ultra-low-power chip architectures built to run always-on AI for years on almost nothing, from analog processors that skip the ADC entirely to sparse compute engines that only…
Intel's Naga Chandrasekaran now claims that Intel 14A node will deliver performance 'within 5%' of TSMC's A14 technology, a claim that requires a closer examination.
QuasarZone tests show the 16-pin power connector on a GeForce RTX 5090 reaches temperatures above 90 degrees Celsius at peak power consumption near 650W.
Links: - Patreon (Support the channel directly!): https://www.patreon.com/Asianometry - X: https://twitter.com/asianometry - Newsletter & Podcast (available through Stratechery Plus): https://asianometry.passport.online/ - LinkedIn (feel free to connect): www.linkedin.com/in/jon-y-asianometry
It's not all hardware nowadays! Software is just as important! You can find us... Twitter - https://twitter.com/level1techs Twitch - https://twitch.tv/teampgp Patreon - https://www.patreon.com/level1 For all our social links, websites, and more, check out our link tree! https://linktr.ee/level1techs Thank you for…
ASML calls EU authorities to help create demand for European chips as Europe's share in its revenue drops to 0% in 2026.
A 3D artist looking to build a new workstation bought this RTX 5090 off of a used marketplace expecting a unit autographed by an Asus executive. But when they opened the box of the GPU, they were surprised to find that it was actually autographed by Jensen Huang himself.
WiCi wireless external GPU with onboard storage puts AI workloads reach of local machines via WiFi 7.
The latest review of the Lisuan Tech LX 7G100 shows performance comparable to AMD's Radeon RX 580 but trails the GeForce RTX 2060.
CyberPowerPC is offering five different pre-built gaming PCs with either an RTX 5070, 5080, or 5090 Founders Edition GPUs paired with either an Intel or AMD X3D CPU. They also come with 32GB of DDR5 RAM and 1TB of NVMe SSD, all for reasonable prices.
SUPPORT OUR WORK https://store.gamersnexus.net/data-dragnet Microsoft has filed for a new patent that describes a credit system to "rent" software and games, including rate-limited rentals based on the type of use. In their examples, singleplayer costs more than training mode, but multiplayer costs more credits than…
In gory detail: reliability, performance, support, pricing—and, of course, security—in our most thorough analysis of GPU cloud providers globally.