Intel
Page 06
Tarun Chitra@tarunchitra
Tarun Chitra reads the largest open weight model marketplace as an unbundling of the frontier lab product: open harnesses let a user pick the model and the compute provider separately, and that split changes the incentives around caching and pricing.
Why it mattersIf you route inference through a marketplace, the provider you land on and how honestly it caches determine both your bill and your latency.
Security Firewall for Agents — Ryan Dahl, Deno
Ryan Dahl explains why Deno treats its incident response agents as untrusted software and puts an MIT licensed proxy in front of them.
Why it mattersAnyone giving an agent production credentials needs a guard that survives prompt injection, and this is a working design with an open license rather than a policy document.
videoAI Engineer
Context Engineering in 2026 — Louis-François Bouchard, Omar Solano & Samridhi Vaid, Towards AI
Across 11 context presets measured on an open source AI tutor, sending the full history beat every compaction technique on recall, cost and latency at once, because rewriting context invalidates the prompt cache that serves most of the tokens.
Why it mattersCompaction is a default in most agent frameworks, and this gives a cost model and a recall number for leaving the history alone instead.
videoAI Engineer
articleOpenAIDevs
With retained reasoning and compaction, GPT-5.6 Sol improved from 13.3% to 38.3%
OpenAI's builder guide for GPT-5.6 reports that retaining reasoning across turns and compacting context lifted Sol from 13.3% to 38.3% on ARC-AGI-3 while spending roughly six times fewer output tokens.
Why it mattersRetaining reasoning across turns instead of rebuilding context is a change most agent loops can make, and the reported swing is large enough to be worth testing.
Teaching Everyone to Fish for Tokens
Nathan Lambert compares open weight models to installed software versions rather than to Linux.
Why it mattersAnyone betting a product on open weights is choosing a dependency with a shelf life, and this frames what actually makes that ecosystem self sustaining.
articleNathan Lambert
Gemini 3.7 Flash Is HERE – Testing Google’s BEST Model Yet!
Bijan Bowen runs Gemini 3.7 Flash through practical coding and design tasks.
Why it mattersIndependent task by task footage of a new Flash tier model is the fastest way to see where it holds up on real coding work before you route traffic to it.
videoBijan Bowen
Bennett@b_nnett
A walkthrough of customizing the Codex CLI by having the agent read its own compiled bundle and inject new features, kept alive across updates with a mods folder the agent reapplies on request.
Why it mattersTreating a closed tool's compiled bundle as something an agent can patch turns unshipped features into an afternoon's work. The mods-folder reapply pattern is what makes those patches survive upstream updates.
DepWareTrans: Dependency-Aware Incremental Repository Migration across Co-executable Languages
Traces repository-scale code translation failures to dependency inconsistency between files.
Why it mattersAnyone pointing an agent at a whole-repo migration hits fragmentation across inter-file dependencies. Naming dependency inconsistency as the root cause suggests where to spend orchestration effort.
articleSivajeet Chand, Alexander Pretschner, Steve Haupt, Derui Zhu, Sushant Kumar Pandey
LegacyWorld: Atomicity-Aware Evaluation of GUI Agents for Legacy Workflows
An evaluation of graphical-interface agents on stateful legacy workflows that scores atomicity, counting the invalid changes a failed run leaves behind rather than only whether the task eventually succeeded.
Why it mattersMost agent benchmarks score the end state and ignore the wreckage of failed attempts. For anyone deploying computer-use agents against real records, partial-failure damage is the risk that actually matters.
articleThilo Reintjes, Sivajeet Chand, Derui Zhu, Sushant Kumar Pandey, Alexander Pretschner
ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning
ATLAS learns interpretable state machines from agent execution traces, recovering the strategies an agent actually follows instead of reporting only task success and raw logs.
Why it mattersTrace dumps tell you what an agent did once; a learned automaton tells you what it tends to do. That is a practical handle for auditing agent behavior before trusting it with a task.
articleIgnacio D. Lopez-Miguel, Andreas Happe, J\"urgen Cito, Ezio Bartocci, Bettina K\"onighofer, Martin Tappler
Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model
A monograph on operating coding agents as systems rather than models, locating reliability in the harness, execution state, retrieval, memory, permissions and review surfaces that surround the model.
Why it mattersTeams debugging agent failures reach for a better model first, when the defect is usually in the surrounding system. This gives a structured place to look and a vocabulary for evaluating the harness itself.
articleStephanie Jarmak
Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study
Tests whether language-server retrieval actually saves a coding agent tokens compared with plain lexical search, proposing tokens-to-success as the metric and an ablation that isolates the difference at equal task success.
Why it mattersEvery coding agent has to decide between grep and a language server for retrieval, and the choice is currently made on intuition. A tokens-to-success framing makes that decision measurable.
articlePengcheng Xu
Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
Names token inflation, the gap between a model's per-call price and the true cost of a retrying agent workflow, measures it across model tiers and task types, then builds a router that prices on the corrected figure.
Why it mattersPer-token price is what most teams budget from, and it can understate real agent cost by more than double on hard tasks. Measuring inflation per tier turns model selection into an arithmetic decision instead of a guess.
articleHeming Fu, Shan Lin, Qianqian Xie, Guojun Xiong
GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings
A large study of reinforcement learning with verifiable rewards outside English, sweeping base models, training languages and reasoning-language rewards.
Why it mattersTeams doing RLVR post-training outside English have been extrapolating from English-only results. This says the native-language reasoning penalty is small, which changes how those training runs get configured.
articleKonstantin Dobler, Federico Scozzafava, Jonathan Janke, Mohamed Ali, Simon Lehnerer
Jais 2: A Family of Arabic-Centric Open Large Language Models
A second-generation family of Arabic-centric open large language models, released with a technical report covering the data, training recipe and evaluation behind the models.
Why it mattersArabic-centric open weights fill a real gap for teams serving non-English users where frontier models are weaker or unavailable. The training report also documents choices that transfer to other language-specific model efforts.
articleMohamed Anwar, Abed Alhakim Freihat, George Ibrahim, Mostafa Awad, Abdelrahman Sadallah, Gurpreet Gosal, Gokulakrishnan Ramakrishnan, Sarath Chandran, Biswajit Mishra, Rituraj Joshi, Ahmed Frikha, Etienne Goffinet, Abhishek Maiti, Ali El Filali, Sarah AlBarri, Samujjwal Ghosh, Rahul Pal, Parvez Mullah, Awantika Shukla, Sajid siddiki, Samta Kamboj, Onkar Pandit, Sunil Kumar Sahu, AbdelRahman Elbadawy, Amr Mohamed, Ahmad Chamma, Evan Dufraisse, Abdelaziz Bounhar, Dani Bouch, Hadi Abdine, Guokan Shang, Fajri Koto, Yuxia Wang, Zhuohan Xie, Ali Mekky, Rania Elbadry, Sarfraz Ahmad, Momina Ahsan, Omar El Herraoui, Daniil Orel, Hasan Iqbal, Kareem Elzeky, Mervat Abassy, Kareem Elozeiri, Saadeldine Eletter, Farah Atif, Nurdaulet Mukhituly, Haonan Li, Xudong Han, Aaryamonvikram Singh, Zainul Abedien Ahmed Quraishi, Neha Sengupta, Larry Murray, Avraham Sheinin, Joel Hestness, Natalia Vassilieva, Hector Xuguang Ren, Zhengzhong Liu, Michalis Vazirgiannis, Preslav Nakov
AI Evaluation Should Work With Humans
A position paper arguing that measuring superhuman autonomous performance steers AI development toward replacing people.
Why it mattersMost agent benchmarks implicitly score replacement rather than collaboration, which shapes what gets optimized. Practitioners building evaluation harnesses should know the case against that default.
articleJan Kulveit, Gavin Leech, Tom\'a\v{s} Gaven\v{c}iak, Raymond Douglas
Modular Cognitive Architecture Emerges in Large Language Models
Circuit analyses across 46 tasks in four cognitive domains find that language models develop specialized regions echoing human brain organization.
Why it mattersIf task families recruit distinct neuron populations, that is a handle for interpretability work, targeted editing, and reasoning about which capabilities interfere. It reframes model internals as modular rather than uniformly entangled.
articlePengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
RubricForge evolves an agent-judging rubric against ground-truth-labeled trajectories rather than hand-writing it, targeting the tendency of automatic judges to credit fluent but unsuccessful runs as successes.
Why it mattersOver-crediting is the main way agent eval suites lie to their owners, and hand-written rubrics are where it enters. Grounding the rubric text in environment reward is a directly copyable fix.
articleDarragh Quinn, David Dylan, Roisin Healy, Fionn Carroll, Maeve Donnelly, Cormac Sheehan
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
A year-long production trace from a large inference provider, spanning popular and long-tail models, used to characterize how serving workloads evolve and what that implies for caching and load balancing.
Why it mattersAnyone sizing an inference tier or tuning prefix caching is currently guessing from short synthetic traces. A year of real production traffic, including long-tail models, gives that work an empirical baseline.
articleWilliam Nixon, Jon Durbin, Florian Standhartinger, Haryadi S. Gunawi, Juncheng Yang
GPT-5.6 Sol is 50% off on AI Gateway for the next month
Vercel is running GPT-5.6 Sol at half price on its AI Gateway through September 18, across every service tier including fast mode.
Why it mattersAnyone already sending Sol traffic through this gateway gets the lower rate with no code change, and the window closes September 18.
articleJerilyn Zheng
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
Hands-on notes on Qwen 3.8 27B, the Apache 2 licensed vision-capable release from Alibaba's Qwen lab, run in quantized form on a 128GB MacBook Pro and an NVIDIA DGX Spark.
Why it mattersA capable vision model in the 27B range runs on a well-specced laptop, but its default reasoning effort makes it impractical there; anyone trying it should turn that setting down before judging the model.
articlesimonwillison.net
Guillermo Rauch on Vercel's Shift Toward Agentic Infrastructure
In this interview, Vercel founder Guillermo Rauch describes how the platform has evolved from deploying front-end websites to hosting AI coding agents and autonomous software, driven by models like Opus 4.5.
Why it mattersRauch argues platforms must shift from human-facing elastic compute to 'agentic infrastructure' that lets coding agents deploy, secure, and maintain software autonomously over hours or days.
videoStanford Online
Awesome Claude Code
A curated, hand-maintained list of resources for Claude Code, organizing links to guides, skills, agents, status lines, plugins, orchestration tools.
Why it mattersIt aggregates guides, skills, agents, plugins, and observability tools for Claude Code in one continually updated place, saving practitioners from hunting across scattered repos and blog posts.
repogithub.com
Tuhin Srivastava (Baseten) on Production Inference Economics
Baseten is an AI inference infrastructure platform that runs production machine learning models—including custom and post-trained open-source models.
Why it mattersBaseten's CEO makes the case that once you are at scale, renting a frontier API stops being the cheap option and post-training an open model becomes both the cost play and the moat.
videoStanford Online
Anthropic and Chai Discovery on AI-Accelerated Drug Development
A Stanford guest lecture transcript featuring Anthropic's Eric Abrams and Chai Discovery's Josh Meier discussing how AI models are being applied across drug discovery and life sciences R&D.
Why it mattersExplains specific technical bottlenecks in applying AI to the 10-15 year drug development pipeline and how Anthropic's Claude and Chai's molecular design platform are targeting them.
videoStanford Online
Yash Patel on the History and Future of AI Model Training
A Stanford talk transcript in which Applied Compute founder Yash Patel traces AI model development from AlexNet through transformers, scaling laws, RLHF.
Why it mattersArgues the next AI capability bottleneck is continual, data-efficient learning from sparse real-world feedback rather than more pretraining, and explains why verifiable domains like code and math currently dominate RL training.
videoStanford Online
The Economics of the AI Super Cycle: OpenAI's Compute Strategy (with Sachin Katti)
A Stanford class interview with Sachin Katti, who leads industrial compute at OpenAI and previously served as Intel's CTO, on how OpenAI plans and builds compute at gigawatt scale.
Why it mattersOpenAI's compute chief explains the roadmap to 30GW of capacity and why inference workloads will dominate future compute demand.
videoStanford Online
Ali Ghodsi on AGI, Enterprise AI, and Whether Software Is Dead
In this talk/interview, Databricks CEO Ali Ghodsi argues that AGI already exists by decades-old research definitions but remains useless inside companies because AI agents lack the tacit organizational context that veteran employees carry in their heads.
Why it mattersGhodsi argues that even if AGI meets old technical definitions, it remains blocked from real enterprise value by missing tacit organizational context that human employees hold.
videoStanford Online
Chase Lockmiller (Crusoe) on the AI Data Center Economy
A fireside talk with Crusoe founder and CEO Chase Lockmiller explaining how AI infrastructure is built.
Why it mattersCrusoe's Abilene campus shows energy availability, not GPU supply, is now the binding constraint on scaling AI compute, and negative power prices in West Texas are actively shaping where hyperscale AI infrastructure gets built.
videoStanford Online
Brad Gerstner and Sunny Madra on the Economics of AI Inference
A fireside chat transcript in which Altimeter Capital's Brad Gerstner and Groq's Sunny Madra discuss why AI inference, unlike traditional software, has significant marginal compute costs, tracing Groq's origins, its bet on cloud-hosted inference chips, and the shift toward reasoning models that consume vastly more tokens.
Why it mattersExplains why reasoning models' heavy token consumption changes inference cost structure, and details the prefill/decode disaggregation strategy Groq used to improve inference efficiency at scale.
videoStanford Online
GitHub@github
GitHub made Balanced depth generally available for Copilot code review alongside the existing Lite mode, with the default settable at the organization or repository level and overridable when requesting a review on a single pull request.
Why it mattersTeams running Copilot code review can now put deeper analysis on risky pull requests and keep lightweight reviews on routine ones, set as a default or chosen per request.
GLM 5.3 Is HERE – Is THIS the BEST Open Model Yet?
A hands-on test of GLM 5.3 across browser workflows, C++ game development, 3D CAD modelling, frontend design and FPS generation, asking whether it earns the title of best open model yet.
Why it mattersGives practitioners a task-by-task read on whether GLM 5.3 holds up as a coding model against the closed frontier, which is the decision anyone weighing an open-weight backend actually has to make.
videoBijan Bowen
sankalp@dejavucoder
A blog post detailing how the author used Codex as an autonomous research loop—iterating over 1500 submissions across 14 days—to optimize a batched Householder QR decomposition CUDA kernel, placing 12th of 183 in a GPU Mode contest with a 232x speedup over baseline.
Why it mattersIt shows what an agent loop can do when the scoring signal is fast and objective, and names the harness conditions that made it work. That is a reusable pattern for anyone pointing a coding agent at an optimization problem.
Go from an empty repo to a live GitHub Pages site on a custom domain, secured wi
Go from an empty repo to a live GitHub Pages site on a custom domain, secured with HTTPS, in about 14 minutes.
Why it mattersShows the skill mechanism in a coding CLI reaching past code into registrar and DNS setup, which is the kind of end-to-end delegation builders are trying to scope right now.
articlegithub
React for Agents: Astro Creator Brings Hooks to his Meta-Harness, Flue
Fred Schott's Flue reaches its first stable release built on React-style Agent Hooks, where an agent is a JavaScript function that re-renders before every model call and can manage its own state and attach capabilities mid-run.
Why it mattersAgent Hooks are a concrete answer to how agent state and capabilities get composed at runtime, from the person who built Astro. Engineers picking a harness now have a second serious design to compare against Vercel's eve.
articleRichard MacManus
CORS Chat
Simon Willison's browser-based chat client for any OpenAI Responses-compatible endpoint that sends CORS headers, built to exercise local models in LM Studio and OpenRouter.
Why it mattersA zero-install way to exercise a Responses-compatible endpoint, including a locally served model, which removes the usual scratch-script step when validating a new provider or a local runtime.
articlesimonwillison.net
Building an AI Text Detector From Scratch
Sebastian Raschka builds a small AI-text detector from scratch, then turns it into a verifier used to train a small language model to write text that evades detection, as a study of where such detectors break down.
Why it mattersShows how to build a classifier-as-verifier and train an SLM against it, a reusable pattern for anyone wiring reward or filter signals into small-model training.
articleSebastian Raschka, PhD
Research Assistant: AstraZeneca's Agentic System for R&D
AstraZeneca describes Research Assistant, an internal LLM system answering biomedical questions across literature, knowledge graphs, chemistry, clinical trials and internal experimental data.
Why it mattersPublished architecture and deployment lessons from a real enterprise agent system give builders a reference design for grounding, provenance, and mode selection.
articlePiotr Grabowski, Mohamed Alameen, Jorge Bretones, Sabina Cardell, Miguel Carmona, Gavin Edwards, Ben Grainger, Sameh Hassan, Erik Jansson, Artur Kuziakhmetov, Albert Maristany, Hebatallah Mohamed, Andriy Nikolov, Sebastian Nilsson, Mark O'Donoghue, James Pacileo, Ashiq Sultan, Alex Voegele, Michael Ughetto
Dual-Flow Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation
A transformer design that splits inference in two.
Why it mattersInference cost now dominates training cost for served models, and this decouples the two phases so added capability does not tax both.
articleLiming Liu, Mingze Wang, Tuo Zhao
Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese
Nine models are asked in different languages whether a nuclear-armed state should strike a defenceless one.
Why it mattersSafety behavior measured only in English does not transfer, and reasoning-language is an uncontrolled variable in any multilingual agent deployment or eval suite.
articleRian Touchent (ALMAnaCH)
Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists
IntegrityBench tests whether models uphold research integrity under institutional pressure across 36 paired tasks.
Why it mattersAnyone deploying models as autonomous research or review agents now has a measured failure rate under pressure, and evidence that scaling up the model does not fix it.
articleYash Tripathi, Silu Sharma, Sai Sidhanth Manoharan Jayanthi, Shivank Garg, Lin Li
Artificial Analysis@ArtificialAnlys
Artificial Analysis scores DeepSeek V4 Pro 0813 at 53 on its Intelligence Index, eight points above April's version but with a 3.6x price rise, leaving it barely ahead of the cheaper V4 Flash and still behind Kimi K3 among open-weights models.
Why it mattersTeams building on DeepSeek's first-party API face a 3.6x price change within a day, and the intelligence gain over the cheaper Flash model is a single point. The cost-per-task math changes which model is the rational default.
Qwen3.8 27B Is INSANE – This Is the BEST Local AI Model Yet!
A hands-on test of Qwen3.8 27B running locally, across browser workflows, C++ game creation, FPS development, 3D CAD modelling, multimodal coding and cinematic game generation.
Why it mattersTask-level results on a 27B model running locally give a practical read on where local inference is now good enough for coding work and where it still falls short.
videoBijan Bowen
articlesimonwillison.net
Don't classify. Hallucinate!
Doug Turnbull's trick for tagging against a large vocabulary.
Why it mattersIt turns an oversized label set from a context problem into an embedding lookup, which is directly reusable by anyone classifying against a taxonomy too large to fit in a prompt.
GLM-5.3: How Chinese labs keep stride with the frontier
Nathan Lambert on Z.ai's GLM-5.3.
Why it mattersA frontier-level agentic coding score reached purely through post-training on an existing base, at a third of a competitor's parameter count, resets what teams should assume about the cost of catching up.
articleNathan Lambert
SemiAnalysis@SemiAnalysis_
Congrats to @Zai_org on GLM-5.3. It massively beats every American open model: Nemotron, Laguna, Inkling. It's not close. GLM-5.3 uses the same base model as GLM-5.2; every gain came from post-training. If America keeps going down the "Nemotron Committee" path instead of fostering real competition, it will keep losing.
Why it mattersIt puts a concrete stake in the open-weights comparison: if post-training alone produced the jump, the gap between American and Chinese open models is a process gap rather than a compute gap.
We’ve written an FAQ to answer some of the questions we've received about waterm
Anthropic's FAQ on watermarking Claude's text.
Why it mattersAnyone shipping model output into their own product now knows what watermarking does and does not change about that text, including that it costs no extra tokens and carries no per-user attribution.
articleAnthropicAI
articleClaudeDevs
To configure auto mode for your environment, run /auto-mode-setup. Claude looks
To configure auto mode for your environment, run /auto-mode-setup. Claude looks through your repo and suggests trusted repos and domains for you to review.
Why it mattersPermission configuration is the main safety lever on an autonomous coding agent, and this documents exactly how the trusted-surface list is built and reviewed.
ClaudeDevs@ClaudeDevs
Auto mode is rolling out today as the default permission mode in Claude Code for Pro, Max, and Team. If you've already set a default mode, Claude will ask before changing anything. You can still switch modes any time with Shift+Tab, or pin one with "defaultMode" in settings. https://t.co/7LSjv7g9Wv
Why it mattersA shift in the default permission mode changes what a coding agent will do without asking, so anyone running Claude Code in a shared or automated setting needs to check their configuration.
Qwen@Alibaba_Qwen
Qwen3.8-27B is available on @ollama ！Any harness you run, the model always delivers. Let's code together, and show us what you build.😎 https://t.co/zqZahbEVCI
Why it mattersA 27B frontier-adjacent model landing on Ollama puts it within reach of a single workstation, which changes the local-inference options for anyone building agents that cannot call a hosted API.
An index of the vibe-coding frontier. Corrections welcome.