Software engineer Sean Goedecke argues that developer experience will become the bottleneck for AI coding agents as inference speeds rise, citing GPT-6-Astra at roughly 60 tokens per second versus Taa…
A Hacker News user is seeking access to a Taalas API, offering to rent it for developing an embedded AI application for smart glasses at HumanHUD.ai. The request, posted by user revanthmatha, asks for…
Nvidia paid $20 billion in late 2025 to license Groq's technology and hire its founder and top engineers, AMD announced on August 6 it is acquiring Taalas, and Cerebras went public in May at a $66 bil…
AMD announced on August 6 its acquisition of Taalas, a Toronto-based startup whose HC1 accelerator delivers inference at 16,000 tokens per second per user, roughly 45 times faster than optimized Nvidi…
A developer achieved 59,965 tokens per second running a 3.16M-parameter INT4 transformer entirely in the on-chip memory of a $250 AMD Xilinx Kria KV260 FPGA, with zero DRAM in the token loop. The bit-…
AMD has acquired Canadian AI chip startup Taalas to integrate its technology into AMD Instinct GPUs for more efficient inference workloads. Financial terms were not disclosed. Taalas, founded in Augus…
AMD has acquired Toronto-based chipmaker Taalas, the latest in a series of Canadian semiconductor startups snapped up by U.S. firms, prompting calls for a national strategy to retain homegrown talent.…
AMD acquired Toronto-based Taalas on August 6, a chip startup that hardwires AI model weights into silicon using Mask ROM, eliminating the memory bottleneck. Taalas's HC1 chip, built on TSMC's 6nm pro…
AMD has agreed to acquire Toronto-based Taalas, a startup founded in 2023 that develops AI inference silicon tailored to specific models, to expand its inference capabilities for real-time and high-vo…
AMD announced a definitive agreement on August 6, 2026, to acquire Toronto-based AI-chip startup Taalas, adding model-specific inference silicon to its AI roadmap; financial terms were not disclosed. …
OpenAI paused development of its Astra model after internal evaluations found it can independently identify and execute attacks on well-protected real-world systems, crossing a 'critical cybersecurity…
AMD agreed to acquire Taalas, a 25-person Toronto-based chip startup that builds model-specific silicon, for an undisclosed amount. Taalas's first chip, the HC1, runs only Llama 3.1 8B, with weights h…
AMD announced on August 6, 2026, a definitive agreement to acquire Taalas, a Toronto-based startup that embeds AI models directly into silicon, to integrate its technology into AMD's accelerator roadm…
AMD acquired AI inference startup Taalas for an undisclosed sum this week, aiming to bake AI inference directly into its chips. The move follows Nvidia CEO Jensen Huang's GTC 2026 disclosure that GPU …
AMD acquired Taalas to etch model weights directly into silicon, achieving 17,000 tokens/sec inference speed—48x faster than Nvidia GPUs—and reducing hardware needs for trillion-parameter models to ju…
AMD has agreed to acquire Canadian custom silicon startup Taalas for an undisclosed amount, integrating its technology into its AI accelerator roadmap and Instinct GPUs to target the growing inference…
AMD has agreed to acquire Taalas, a Canadian designer of chips that embed a trained AI model's weights into custom silicon, aiming to reduce the cost and time of enterprise AI inference. Analysts caut…
AMD has agreed to acquire Taalas, a Canadian designer of chips that embed trained AI model weights into custom silicon for enterprise inference, aiming to cut costs and power use. Analysts warn the mo…
Alibaba's Qwen3.8 Max edged past Claude Opus 5 and Kimi K3 on Artificial Analysis's Agentic Index, though rankings fluctuated within minutes, highlighting tight clustering among frontier models. OpenA…
AMD has acquired Taalas, a company previously highlighted in Latent Space's custom ASIC thesis, signaling AMD's commitment to custom silicon for AI inference. The acquisition was announced amid ongoin…