AllyshipContent Radar

News 2903

Chủ đề cộng đồng đang thảo luận

Crawl live-1795122900000 · 04:15 20 thg 11, 2026 · Xuất bản 04:31 20 thg 11, 2026

199 / 2903 chủ đề đạt ngưỡng 55 trong khoảng này.

1

How much do you automate your life? (2)

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

luongnv89 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

How much do you automate your life? (2) This is how i consume articles and blog posts nowadays - send the link to my bot on Telegram, it become a core subject of a new podcast episode - a bot goes looking for other sources: some explain the ideas more simply, some bring data, some disagree =>full picture, not just one opinion - a bot writes a 2-host podcast (Bob and Alice, heygen voice, free from @OpenRouter, thank to @HeyGen ) checks every fact against its source, and explains the hard parts with simple metaphors - the episode goes live on http://luongnv.com/podcast - if one topic really catches me and I want to dig deeper: one command sends the original article to my reMarkable as a clean PDF, so I can read it slowly and take notes with a pen (the skill is open source: http://github.com/luongnv89/remarkable-skills) I send a link, I get a podcast. Everything else is automatic Here is the latest one on verification from @addyosmani , super interesting https://luongnv.com/podcast/episodes/2026-11-19_how-the-claude-code-team-thinks-about/

2

QDA: Closed-Loop LLM Quantization Design with Agents

87

5 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 9 tương tác đã đo · Nguồn crawl

Xingyang Li, Tianlang Zhao và 3 nguồn khác 1 bài viết · Hugging Face Papers, X
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo nêu rằng post-training quantization là cách tiêu chuẩn để phục vụ LLM với chi phí thấp, nhưng công thức quantization tốt phụ thuộc vào từng mô hình và độ chính xác, nên chuyên gia phải thiết kế lại cho mỗi mô hình. Họ giới thiệu QDA, nơi một agent thiết kế recipe cho từng mô hình và độ chính xác. QDA đánh giá nhanh bằng cách chấm candidate theo KL divergence đầu ra so với mô hình gốc trên reasoning traces mà agent không thấy, và kiểm tra thêm các candidate hứa hẹn bằng long generations để bắt lỗi như repetition loops.

Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every new model, which is time-consuming and often sub-optimal. Fortunately, an LLM agent can take over this design by refining the recipe over rounds of building and evaluating candidates, so that more rounds lead to better recipes. However, evaluating one quantized reasoning model takes tens of GPU-hours, and combining methods from different codebases means porting each to the new architecture by hand. We present QDA, a system in which an agent designs the recipe for each model and precision. To make evaluation fast, QDA scores each candidate in minutes by its output KL divergence from the original model on reasoning traces that the agent never sees, and checks promising ones with long generations to catch failures such as repetition loops. To make building fast, QDA provides a library of public PTQ methods that are compatible with one another and with new model architectures. Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search. On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint. Every QDA checkpoint also runs on existing serving kernels with no inference overhead. We will release the library, the evaluator and the harness.

  • Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search.
  • Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search.
  • On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint.
  • Every QDA checkpoint also runs on existing serving kernels with no inference overhead.
3

Compare the Gemini 4 models with other leading models at: https://artificialanalysis.ai/models/comparisons/gemini-4-neon-vs-gemini-4-carbon

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

artificialanlys 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Compare the Gemini 4 models with other leading models at: https://artificialanalysis.ai/models/comparisons/gemini-4-neon-vs-gemini-4-carbon

4

Neon and Hydrogen occupy all of the Pareto frontiers of Intelligence vs. Cost per Task and Intelligence vs. Time per Task among the three models.

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

artificialanlys 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Neon and Hydrogen occupy all of the Pareto frontiers of Intelligence vs. Cost per Task and Intelligence vs. Time per Task among the three models. Between the two, they scale from an Intelligence Index of 27 at $0.29 per task (Hydrogen, low) to 61 at $6.44 per task (Neon, xhigh). Developers have a lot of flexibility to tune for their use cases with effort level. Carbon does not follow this trend, with relatively little difference in Time or Cost per Task between effort levels. Media

5

Out of your element with the new Gemini 4 releases? Here are some key highlights on Gemini 4 Carbon, Neon and Hydrogen

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

artificialanlys 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Out of your element with the new Gemini 4 releases? Here are some key highlights on Gemini 4 Carbon, Neon and Hydrogen Carbon is the highest-priced model ($4/$20 per 1M input/output tokens), followed by Neon ($3/$15) and Hydrogen ($1.50/$7.50). At low effort, Carbon performs the best of the three but uses more tokens. However, Neon and Hydrogen scale more effectively to higher reasoning efforts and have an additional reasoning option (xhigh). Media

6

Crazy how fast you can pull these things together now.

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

fofrai 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Crazy how fast you can pull these things together now. Neon: > Take the monstera character pixel art and turn it into something more of a high-fidelity 3D concept that I can walk around a midcentury modern room Media

7

Self-improving agents are one of the most discussed ideas in AI right now.

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

dair_ai 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Self-improving agents are one of the most discussed ideas in AI right now. (bookmark it) This update gate for a personal health assistant rejected 20 of 21 risky self-proposed updates. Researchers built Safe Personal RSI for the Kicker assistant. The agent can only change its own instructions. Model weights and runtime code stay fixed. Each proposed update is tested against the current instructions on 29 executable email, calendar, health, and marketplace cases. Separate probes test authorization reuse, memory, and tool-output injection. Failing cases are repeated, and changes are temporarily undone to find which edit caused the failure. If no version passes, the current instructions stay. One admitted repair for GPT-5.6 Luna cut attack violations from 10.7% to 0% and raised safe task completion from 89.7% to 100%. Under stronger attacks, a repair moved from Qwen2.5-7B to Qwen3-14B, cutting violations from 69.0% to 17.9%. https://arxiv.org/abs/2611.23651 Chat with Paper: https://academy.dair.ai/papers/safe-personal-rsi-evaluating-and-repairing-personal-agent-updates-2611.23651

9

Ask HN: Where do you see Software in 5 years?

62

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 8 tương tác đã đo · Nguồn crawl

Odbyteusz 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn

I wanted to hear some good opinions on all things AI and how they transform the Software industry. I'm anxious about the future and lack the foresight to form any opinion on what to do next. For context, I'm a L4 SWE that has more or less say 5-10 yrs of exp. I've enjoyed my work throughout my career, AI makes me ship more, much more than I could do 3 years ago. I feel I use it well and it translates into really good software. That said, what do you think happens in years to come with the Software industry in general? Do you think we'll go through a massive erosion of jobs? What's your perspective on that? I'm asking because I honestly don't know what to do: I can try to always keep up to date with newest technologies, best practices, but I'm only me; if the demand for SWEs and jobs falls to the floor, I'm not sure I'll always get a place at the table (i.e. land a job) and I'm wondering whether I should try to do something else in some other industry. It feels weird to be in a good position in life and still constantly worry about it getting worse.

10

Show HN: IT Thinks – Build a GPU from a Single NAND Gate

63

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 10 tương tác đã đo · Nguồn crawl

benbenhere 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn

Hi HN, I built a hardware puzzle game, you start with one NAND gate and every chip you finish becomes a part of next one. basic gates, adders, decoders, latches and finally GPU. last one are a chip that recognises handwritten digits. I am happy to discuss how we can create better levels to for those concepts. you can try demo/full game on Steam

11

Ask HN: Who Is Hiring? (November 2026 – We Give a Shit Edition)

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 5 tương tác đã đo · Nguồn crawl

k_sze 1 bài viết · HN: AI agent
Nguyên văn nguồn
Chi tiết nguồn

This is a bit of a tongue-in-cheek. Since reading the "We need smart people who give a shit" story (https://news.ycombinator.com/item?id=50554045), and the comments underneath it, I realise that there is a good deal of engineers who are disgruntled by how AI is incompatible with smart people who give a shit, how it is turning us into meat proxies and Letzter Mensch. So this is a call for companies and employers with smart management who still give a shit, who do not demand that engineers replace their workflow with 5 parallel agent sessions, who appreciate the craftsmanship of humans, to step forward and post their job openings.

13

Knowledge factories! (They call it Knowledge engine but same thing)

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

hwchase17 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Knowledge factories! (They call it Knowledge engine but same thing) Hex is one of the best agent building companies I know! We did a pod with them a year ago where we chatted a bit on an earlier version of this https://m.youtube.com/watch?v=Xyh1EqcjGME

15

Build your own custom index in the Artificial Analysis Data Playground

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

artificialanlys 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Build your own custom index in the Artificial Analysis Data Playground Add any Artificial Analysis benchmarks, customize their weights, and plot the results with other chart axis. Models receive a score only if they have results for every evaluation in your index, consistent with the Intelligence Index methodology. Also in the Data Playground: ➤ Formula metrics: combine any metrics with +, -, *, / and functions such as log and sqrt ➤ Playback: play a scatter chart forward by launch date, with the frontier drawn as it stood at each date ➤ Heat maps across many evaluations, and box plot distributions by group, such as open weights vs proprietary ➤ A workbench with sheets, Columns/Rows shelves and a dashboard view The Data Playground is available with Artificial Analysis Pro. Media

16

Optimize AI economics on Amazon Bedrock with Accenture’s sequenced approach

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Ilan Geller 1 bài viết · AWS Machine Learning Blog
Nguyên văn nguồn
Chi tiết nguồn

<p>As enterprises scale AI on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a>, token spend often grows even as per-token prices fall. Without cost allocation tags in place, your cloud invoice shows AI spend as a single line item rather than by team, workload, agent, or model. Cheaper tokens expand adoption, and agentic workloads multiply invocations. As successful AI use cases scale, consumption can rise faster than unit prices drop. The economic question is whether the business value generated grows faster than the cost of the intelligence required to produce it. The Linux Foundation has launched the <a href="https://www.linuxfoundation.org/press/linux-foundation-launches-the-tokenomics-foundation-to-define-the-economics-and-roi-of-ai-value" target="_blank" rel="noopener">Tokenomics Foundation</a> to develop open standards for AI cost economics, a sign that managing the economics of AI is now an industry discipline.</p> <p>In this post, you will learn about six levers for optimizing token spend, how Accenture applied them in production, and how to apply them using Amazon Bedrock.</p> <p>Accenture applied these levers in four client engagements across telecom, insurance, mining, and a large enterprise deployment. The same levers are available natively on Amazon Bedrock as described in this post. Where savings were measured, token spend fell by about 40–85 percent. Results are specific to each client’s workload and may vary. Client names are withheld by Accenture to protect client confidentiality.</p> <h2 id="attribution-first-measuring-cost-at-the-business-level">Attribution first: Measuring cost at the business level</h2> <p>Before you optimize anything, you need to see where consumption is occurring, who owns it, and what business value it produces. Cost allocation tags at the team, workload, and agent level are the prerequisite for connecting consumption to accountable owners and, ultimately, to business outcomes. You apply them through <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cost-mgmt-application-inference-profiles.html" target="_blank" rel="noopener">Amazon Bedrock application inference profiles</a>, one profile per application or workload, tagged by team, cost center, and environment. After you activate them as cost allocation tags in the <a href="https://aws.amazon.com/aws-cost-management/billing-and-cost-management-console-home/" target="_blank" rel="noopener">AWS Billing and Cost Management console</a>, you can use these tags to trace which teams, applications, and agents are driving spend. They also make it possible to measure the impact of each change you introduce.</p> <p>Three AWS services provide the underlying telemetry. <a href="https://aws.amazon.com/aws-cost-management/aws-cost-and-usage-reporting/" target="_blank" rel="noopener">AWS Cost and Usage Reports</a> (CUR 2.0), delivered through <a href="https://docs.aws.amazon.com/cur/latest/userguide/what-is-data-exports.html" target="_blank" rel="noopener">AWS Data Exports</a>, handle financial attribution, breaking down billed inference cost by workload and team after your cost allocation tags are active. <a href="https://aws.amazon.com/cloudwatch/" target="_blank" rel="noopener">Amazon CloudWatch</a> captures operational signals such as invocation counts and latency. <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-invocation-logging.html" target="_blank" rel="noopener">Amazon Bedrock model invocation logging</a> records request-level detail, including the model used and the input and output token counts for each call.</p> <p>Telemetry alone isn’t enough. Engineers can read cost per invocation on a dashboard, but product owners and program leaders need a metric expressed in business terms. Accenture’s Cost per Business Transaction (CpBT) framework bridges this gap. CpBT aggregates all the model invocations, retries, tool calls, and agent handoffs that contribute to one successful business output into a single fully loaded cost figure. It surfaces the true cost of producing a result, including the failed attempts that raw token pricing hides. Tracked against the business value each workflow delivers, CpBT distinguishes a growing bill that reflects scaling success from one that reflects waste.</p> <h2 id="the-six-optimization-levers">The six optimization levers</h2> <p>The goal of these six levers isn’t to minimize tokens at all costs. It’s to use the right amount and level of intelligence to deliver each business outcome at the appropriate cost, quality, and risk. The levers are organized into three phases based on the complexity of the change and the investment it requires. AWS and Accenture recommend working through the phases in order, and you can apply each phase independently to the workloads where it will have the most impact.</p> <h3 id="phase-1-configuration-only-no-infrastructure-change">Phase 1: Configuration only, no infrastructure change</h3> <p>With <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html" target="_blank" rel="noopener">Amazon Bedrock prompt caching</a>, the model reuses the parts of a prompt that repeat across requests, such as system instructions, tool definitions, and reference documents, so you stop paying full price to process the same content again. Amazon Bedrock stores the key-value state of previously computed prompt prefixes and is designed to skip recomputation on later requests. This is designed to reduce cached input token costs by up to 90 percent for supported models (see <a href="https://aws.amazon.com/bedrock/prompt-caching/" target="_blank" rel="noopener">Amazon Bedrock Prompt Caching</a>).</p> <p><a href="https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference.html" target="_blank" rel="noopener">Amazon Bedrock batch inference</a> processes non-urgent workloads asynchronously as a group at 50 percent lower cost than on-demand pricing for select models (s

17

Une note markdown globale qui vous suit dans chaque workspace ?

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

cloudinnantes 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Une note markdown globale qui vous suit dans chaque workspace ? Salut tout le monde ! Je viens de publier le plugin Human Scratchpad; maintenant listé dans le répertoire Community @orca_build Orca donne à chaque workspace ses propres fichiers, terminaux et agents. Ce qui me manquait, c'est un endroit pour tout ce qui n'appartient à aucun d'entre eux : une commande pour demain, une tâche pour cet après-midi, un snippet à coller ailleurs. Scratchpad ajoute un panneau dans la barre latérale droite qui édite un seul fichier markdown, le même quel que soit le workspace ouvert. https://orca.dev/plugins/erom/orca-plugin-human-scratchpad

18

Orca - chạy một đội các coding agents bằng subscription của bạn

71

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

stablyai, orca_build 0 bài viết · GitHub discovery: AI agents, X
Biên tập tiếng Việt
Chi tiết nguồn

Orca được mô tả là cho phép chạy một “fleet of coding agents” (ví dụ Claude Code, Codex) với subscription của riêng bạn. Nền tảng có sẵn trên desktop, mobile và remote runtime.

Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.

  • Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription.
  • Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription.
  • Available on desktop, mobile and remote runtime.
19

Archify - biến ý tưởng/plan/codebase thành sơ đồ tương tác

71

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

tt-a1i, tom_doerr 0 bài viết · GitHub discovery: LLM, X
Biên tập tiếng Việt
Chi tiết nguồn

Archify được mô tả là chuyển mọi ý tưởng, kế hoạch hoặc codebase thành một sơ đồ tương tác “đẹp”. Nó là một agent skill cho Claude Code, Codex và nhiều nền tảng khác.

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

  • Turn any idea, plan, or codebase into a beautiful interactive diagram.
  • Turn any idea, plan, or codebase into a beautiful interactive diagram.
  • An agent skill for Claude Code, Codex, and more.
1–20 / 199
Trang 1 / 10