标签：#ama

What flipped in b9437 Build b9437 , published on May 30, 2026 at 20:56 UTC , ships two targeted default-value corrections to llama-bench . Flash attention ( -fa ) shifts from a hard-coded off to auto ( LLAMA_FLASH_ATTN_TYPE_AUTO ), and the GPU-layer count ( -ngl ) changes from the legacy sentinel 99 to -1 . Both values now match what llama-server and llama-cli already used — the bench tool was simply never updated to track them until this build. Quick Answer: Before b9437 (published May 30, 2026) , llama-bench hard-coded -fa off , silently skipping flash attention even on CUDA, Metal, and Vulkan hardware. Build b9437 sets the default to -fa auto and -ngl -1 , matching llama-server and llama-cli . Any pre-b9437 baseline on FA-capable hardware needs a flag-matched re-run to remain valid. PR #23714 , reviewed and merged by maintainers JohannesGaessler and pwilkin, adds the same -fa auto|off|on tri-state flag to llama-bench that the rest of the toolchain already supported. With LLAMA_FLASH_ATTN_TYPE_AUTO as the new default, flash attention activates automatically when the runtime detects a capable backend (CUDA, Metal, Vulkan); on CPU-only hosts it stays off with no error and no output change. Parameter Before b9437 After b9437 Behavioral impact -fa off (hard-coded) auto ( LLAMA_FLASH_ATTN_TYPE_AUTO ) GPU-capable hosts bench with FA active by default; pre/post comparisons require explicit flag-matching -ngl 99 (offload-all sentinel) -1 (runtime decides) CPU-only builds no longer attempt full GPU offload; eliminates spurious CUDA errors when no GPU is present The following verified script (executed successfully, exit 0) demonstrates the behavioral gap in concrete terms — on a capable GPU, the pre-b9437 defaults schedule zero FA rows while b9437 defaults schedule one: def old_llama_bench ( device ): # Before b9437, the default bench matrix used FA=0, so FA rows were skipped. return [{ " device " : device [ " name " ], " ngl " : 0 , " fa " : 0 }] def b9437_llama_bench ( de

Elsewhere, beyond-classical quantum hardware, plus classical computing fires back.

We’re seeing good early Prime Day deals ahead of the event next week, and unsurprisingly, some of the best deals are on Amazon’s own devices. Several Echo speakers have dropped to new low prices, including the Echo Dot Max, which is on sale for $64.99 ($35 off) at Amazon. Our smart home reviewer Jennifer Pattison […]

Amazon’s Prime Day is one of the biggest shopping events of the year, and the four-day sale for 2026 begins June 23rd at 3:01AM ET and ends at the same time on June 27th. It will grant Prime members access to some of the best prices of the year on Amazon devices, as well as […]

We’ve trawled the depths of Amazon to find the best deals on gear we’ve tested.

My AWS Bedrock Experiment Cost Me $8.43 in Just One Day What I learned about AWS Bedrock pricing the hard way, and why budget alerts saved me Why I Even Tried Claude Code on Bedrock I have been using Claude Code for a while now, connected to Anthropic directly. It works well. But two things were bothering me. First, the usage limits. Claude Code on Anthropic's native setup has 5hours session limit and a weekly usage cap. Once you hit it, you have to wait. If you are in the middle of something or just want to experiment freely, that gets frustrating fast. Second, billing. I already manage everything on AWS. I'm very familiar with it, the invoices go to one place, and I understand how to track and control costs there. Adding a separate Anthropic subscription meant one more billing account, one more credit card charge, one more thing to track. I just wanted everything under one roof. So I thought, why not try Claude Code connected to Amazon Bedrock? Same tool, runs on AWS, billed through AWS. Seemed like a clean solution to both problems. What happened next is why I am writing this post. The Two Ways to Run Claude Code Most people do not realise Claude Code can be configured to run in two different ways. Option 1: Claude Code via Anthropic directly You connect Claude Code to Anthropic's API or use it under your Claude subscription. Billing goes through Anthropic. If you are on a subscription plan, you pay a flat monthly fee and the usage limits apply to how much you can do within that. Option 2: Claude Code via Amazon Bedrock You connect Claude Code to AWS Bedrock as the backend. Same Claude models, but now AWS is your provider. Billing goes through your AWS account. No Anthropic subscription needed. From the outside, it looks and feels the same. But the billing model underneath is completely different, and that is where things get interesting. What Happened When I Tried It I set up Claude Code to use Bedrock and gave it a prompt. A fairly detailed one, nothing unusual

Here's a thing that catches almost everyone the first week they run a model locally. You paste a 600-line file into your shiny new local assistant, ask it to find the bug, and it confidently rewrites a function that isn't even in the part it read. No error. No warning. It just... silently dropped most of your file on the floor before the model ever saw it. That's not the model being dumb. That's Ollama doing exactly what it was told. By default it gives every model a context window of 2048 tokens and quietly truncates anything past that. It's one of a handful of small surprises that separate "I installed Ollama" from "I actually understand what's running on my machine." Let's go through the ones that matter: how the thing works under the hood, what hardware you really need, the gotchas, and the honest answer to "should I even bother instead of just calling an API?" What Ollama actually is Ollama gets described as "Docker for LLMs," and that's a decent first approximation. You pull a model, you run it, there's a registry. But it hides what's doing the heavy lifting. Underneath, Ollama is a friendly wrapper around llama.cpp , the C/C++ inference engine that made running these models on consumer hardware practical in the first place. When you type ollama run , you're really booting a llama.cpp runtime with a sane default config and a tidy HTTP server bolted on. The models it runs are in a format called GGUF (GPT-Generated Unified Format). A GGUF file isn't just weights. It's a self-contained package that bundles the tensors, the tokenizer config, the architecture details, and hyperparameters like the trained context length, all in one file. That's why ollama pull llama3.1 gives you something that just works: everything the runtime needs to reconstruct the model is in the box. Ollama itself is young. The project shipped its first release in early July 2023 , and it rode the wave of open-weight models (Llama 2 landed that same month) that suddenly made "run a real LLM on

If your electricity bill climbs every summer, a smart thermostat could help keep cooling costs in check. The Amazon Smart Thermostat is an excellent option for its price, especially today. It’s down to just $57.99 at Amazon as a part of Amazon’s early Prime Day sale, which is the best price we’ve seen since Black […]

Hermes-Crew Hybrid: A Hybrid Architecture for Secure Multi-Agent AI Workflows I built a hybrid system that combines a central orchestrator (Hermes) with temporary CrewAI micro-crews, protected by 3 layers of security. Here's what it does and why it matters. The Problem Multi-agent AI systems are powerful but dangerous. When you chain multiple agents together, a single compromised agent can poison the entire workflow. Existing solutions are either too heavy (enterprise PKI infrastructure) or too light (basic regex filters). The Solution: 3-Layer Security Layer 1 — Pre-execution (MCP Tool Auditor): Before any agent can register a tool, it's audited for malicious instructions. Layer 2 — Runtime (Agent Fixer Stage): Every output from every agent passes through a 3-stage pipeline (normalization → pattern matching → embeddings) in under 1ms. Layer 3 — Pre-commit (Code Safety Hook): Before any git commit lands, the diff is analyzed by CrewAI + Ollama local. Malicious code gets rejected automatically. Architecture Hermes (Director) │ ├── MCP Tool Auditor → verifies tools before registration │ ├── Execution: venv (fast) / Docker (isolated) / auto (smart) │ ├── Agent 1: Researcher │ ├── Agent 2: Analyst │ └── Agent 3: Writer │ ├── Security Gateway (Agent Fixer Stage) → filters output (<1ms) │ └── Consolidator → parses output + generates Obsidian notes What Makes It Different 1. Portable by design. Zero hardcoded paths. Every user configures their own .env . 2. Multi-model via LiteLLM. Works with Ollama local, OpenAI, Anthropic, Gemini, Groq, OpenRouter — any provider. 3. Local-first. Everything runs on the user's machine. No cloud dependencies required. 4. Obsidian integration. Every analysis generates a structured note with YAML frontmatter. Code Safety Hook in Action When you run git commit with malicious code: ❌ [ COMMIT RECHAZADO] Code Safety detected risks: → CrewAI detected vulnerabilities: VERDICT: FAIL → Agent Fixer Stage detected anomalies: High threat score: 1.05 Fo

Last week I couldn't shake an idea: what if I had an AI that knew everything I know ? Not ChatGPT — something on my hardware, holding my knowledge, answering to no one's API bill. Yesterday I built it. Here's the honest breakdown. What it does NEXUS runs on a regular Windows laptop — aging i7, 16GB RAM, no GPU. It: Remembers everything. Drop any file in a folder; 60 seconds later it's searchable memory. Answers from MY knowledge. "Which of my projects were formally closed and why?" — it answers from my actual records. Watches the live web. Every 2 hours it pulls Hacker News and news feeds, learns what's trending, pings my Telegram. Reports to my phone. 7 AM daily briefing: what it learned, what's running, what needs me. The stack — all free, all open source Ollama runs the models (Llama 3.2, Mistral 7B). Open WebUI is my private ChatGPT. Qdrant stores memory. n8n automates. SearXNG searches privately. PostgreSQL, Redis, and MinIO handle data. Commercial equivalent: $300–500/month . My cost: electricity. The memory trick nobody explains simply Parse — extract text from any file Chunk — split into ~300-word pieces Embed — each chunk becomes 768 numbers representing its meaning Store — a database that searches by similarity Your question becomes 768 numbers too, and the database finds memories with similar meaning — not matching keywords. I asked "how do I get clients cheaper" and it found my notes on "reducing customer acquisition cost." Different words. Same meaning. That's the magic. What surprised me A 2GB model is genuinely useful. Llama 3.2 3B answers from my knowledge in seconds, on CPU. The automation matters more than the AI. The watched folder + Telegram bot turned a cool demo into a system I actually use. Windows is fine. Docker Desktop + WSL2 ran all nine services without drama. The bill, honestly Hardware: $0 (laptop I own) Software: $0 (open source) APIs: $0 (all local) Time: one focused day The only future cost is a cloud GPU server (~$65/mo) when I outg

According to the Wall Street Journal, the export control directive that led to Anthropic cutting off access to Fable 5 and Mythos 5 was triggered in part by cybersecurity research from Amazon and conversations between CEO Andy Jassy and the White House. According to the report, the paper from Amazon claims that, through a series […]

Amazon CEO Andy Jassy may have been the source of security concerns that led Anthropic to cut off worldwide access to two models on Friday.

Even moderately sized data centers can have an outsized local impact.

Slack modernized its data platform by replacing SSH based execution in Amazon EMR pipelines with a REST driven orchestration layer called Quarry. The migration covered 700 plus Airflow operators, improving security, reliability, and observability while eliminating direct SSH access across production clusters and enabling a server side job lifecycle model. By Leela Kumili

Amazon's rolling out a free software update for Echo Hub devices that gives the home screen a much-needed update to the interface it launched with in 2024. It had already added Alex Plus AI support, but the new interface has a cleaner, fully customizable layout that fits more smart home info and controls on the […]

Just after Seattle enacted a one-year data center moratorium that some of Amazon's own employees pushed for, Amazon shared how much water its data centers use, reportedly for the first time. With concerns about water consumption and energy use a focus of new AI data center construction debates, Amazon says its global data center operations […]

A joint congressional report describes a spam operation that turned tens of thousands of fake podcasts into search-engine bait for illegal pharmacy and scam sites.

Companies are burning through exorbitant sums of money to keep pace in the AI arms race. Debt is climbing.

Amazon's "Story So Far" feature is hitting Kindle hardware and the iOS app, but sadly not the Android version just yet.

Google AI Overview court loss in Germany could spell doom for AI search industry.