---
title: "LLMs"
description: "673 posts about LLMs, summarised, each linking to the original."
---

# LLMs
> 673 posts about LLMs, summarised, each linking to the original.

## Articles

### [Securing Software at the Speed of AI](https://yomu.fyi/post/securing-software-at-the-speed-of-ai.md)
- Company: [Palantir](https://yomu.fyi/company/palantir.md)
- Author: Palantir
- Published: Aug 20, 2026
- Type: Explainer

Palantir describes how its Product Security Team built an agentic software security strategy around multi-agent review, vulnerability hunting, triage, and runtime validation. The approach treats models as replaceable components within a governed harness that controls tools and data access, preserves evidence, coordinates specialized stages, independently challenges findings, and deduplicates reports using source-to-sink paths. Foundry supplies organizational context and lineage across code, services, findings, decisions, and remediation, while Apollo provides a controlled path for delivering verified fixes across heterogeneous software environments. The strategy positions remediation, rather than vulnerability identification, as the central bottleneck and extends these capabilities through Security Forge, a model-agnostic platform for customer cyber defense.


### [PyCharm for AI-assisted Django Workflows](https://yomu.fyi/post/pycharm-for-ai-assisted-django-workflows.md)
- Company: [Jetbrains](https://yomu.fyi/company/jetbrains.md)
- Author: Will Vincent
- Published: Aug 20, 2026
- Type: Announcement

According to the 2026 Django Developers Survey, ninety percent of respondents incorporate artificial intelligence into their weekly or daily workflows. While agents generate code rapidly, developers remain accountable for understanding, evaluating, and shipping changes within their applications. PyCharm addresses these demands by integrating support for external agents, local models via Ollama and LM Studio, and customizable agent skills across codebases. The IDE maintains version-specific framework assistance, including auto-completion for Django 6.0 template partials, alongside architectural inspection tools and visual diffs. Furthermore, developers can trace application components, inspect API endpoints, execute HTTP requests, and query database migrations directly through built-in tooling.


### [From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1)](https://yomu.fyi/post/from-php-to-team-lead-of-agents-rethinking-judgment-review-and-data-wi.md)
- Company: [Stack Overflow](https://yomu.fyi/company/stack-overflow.md)
- Author: Eira May
- Published: Aug 20, 2026
- Type: Explainer

Software development is experiencing an architectural shift as artificial intelligence agents transition individual contributors into orchestrators and reviewers of automated workflows. Rather than spending effort on manual coding, developers increasingly focus on defining system architecture, guiding agent execution, and managing operational risk through tiered human and agent review loops. The primary bottleneck for agentic systems lies in preparing organizational data so that agents can effectively reason over enterprise knowledge. To address this challenge, Google published an open knowledge format and is adopting agent-driven semantic ontology generation to infer relationships across messy data estates. This evolution transforms ontology building from manual human toil into automated generation, allowing engineers to focus on high-value data curation and strategic system design.


### [I Found My Coordinates: Code, Community, and Okta](https://yomu.fyi/post/i-found-my-coordinates-code-community-and-okta.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Vanshika Pandey
- Published: Aug 20, 2026
- Type: Announcement

A career progression through community leadership and software engineering led to a new role at Okta. Starting as a campus ambassador and Google Developer Student Clubs lead in India, the author organized hackathons, workshops, and meetups to foster peer learning. To effectively advocate for developers, an internship as a Developer Advocate at Zuplo prompted hands-on engineering experience as a Software Development Engineer at JPMorgan. After mentoring over 10,000 students and growing a technical community to over 600,000 members, the author joined Okta as a Senior Builder Advocate. In this role, advocacy extends beyond traditional coders to support AI builders, low-code creators, and developers utilizing identity and access management tools.


### [How AgentFlo built AI sales agents with Amazon Bedrock AgentCore – Part 1](https://yomu.fyi/post/how-agentflo-built-ai-sales-agents-with-amazon-bedrock-agentcore-part.md)
- Company: [AWS](https://yomu.fyi/company/aws.md)
- Author: Muhammad Musab Iqbal
- Published: Aug 20, 2026
- Type: Problem & solution

AgentFlo built autonomous AI sales agents to address cart abandonment, unassisted messaging channels, and severe traffic spikes across eCommerce platforms. The system uses the Strands Agents SDK alongside Amazon Bedrock AgentCore to manage intent, recommend products, and execute transactions. Incoming customer communications pass through AWS Fargate before entering AgentCore runtime, which executes model-driven agents inside isolated microVMs with stateful sessions lasting up to eight hours. Tool execution is brokered separately through AgentCore Gateway to ensure operations like cart modifications scale independently from model reasoning. This deployment model enables merchants to launch specialized conversational agents in minutes without pre-provisioning capacity or maintaining custom container configurations.


### [Enterprise-Managed Authorization for your MCP server: Setting Up and Testing XAA in Auth0](https://yomu.fyi/post/enterprise-managed-authorization-for-your-mcp-server-setting-up-and-te.md)
- Company: [Auth0](https://yomu.fyi/company/auth0.md)
- Author: Miguel Pedregosa
- Published: Aug 20, 2026
- Type: Tutorial

Connecting AI agents to enterprise APIs and MCP servers creates governance challenges when relying on traditional OAuth consent prompts. Cross App Access shifts authorization decisions to the enterprise identity provider, allowing IT administrators to manage agent permissions centrally. In this architecture, an identity provider like Okta authenticates the user and issues an Identity Assertion JWT Authorization Grant based on administrative policy. The requesting AI agent presents this assertion to Auth0, which validates the signature and exchanges it for a standard access token via a JWT-bearer grant. Protected APIs can then validate the final token normally without requiring code changes or direct user consent interactions.


### [Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions](https://yomu.fyi/post/multilingual-knowledge-transfer-under-data-constraints-via-lexical-int.md)
- Company: [Apple](https://yomu.fyi/company/apple.md)
- Published: Aug 20, 2026
- Type: Problem & solution

Cross-lingual knowledge transfer is critical for training multilingual language models when target-language data is scarce and downstream tasks demand reasoning or world knowledge. Existing transfer approaches often depend on scarce resources such as large parallel corpora, translation systems, auxiliary models, or extra training phases. To address this limitation, the authors introduce LINK, a data-level intervention method that operates directly during pretraining via bilingual vocabularies. LINK swaps randomly selected words in a portion of the high-resource English corpus with word-level translations according to a specified replacement ratio. Across evaluations spanning eight languages and five model sizes, the technique delivered notable performance gains on downstream target-language tasks while achieving up to a 2x speedup in training to reach equivalent performance.


### [Scaling Laws for Mixture Pretraining Under Data Constraints](https://yomu.fyi/post/scaling-laws-for-mixture-pretraining-under-data-constraints.md)
- Company: [Apple](https://yomu.fyi/company/apple.md)
- Published: Aug 20, 2026
- Type: Problem & solution

Scaling language models demands large volumes of data, but high-value target sources like low-resource languages and specialized domains remain inherently scarce. Practitioners frequently combine limited target data with abundant generic data, creating a balance between domain underexposure and excessive repetition leading to overfitting. An empirical evaluation across more than 2,000 language-model training runs demonstrates that mixture training tolerates substantially higher data repetition than single-source training, allowing scarce target corpora to be repeated 15 to 20 times. Researchers introduced a repetition-aware mixture scaling law that accounts for both the diminishing returns of repeated target tokens and the regularizing effect of generic data. Optimizing this scaling law offers a principled framework for calculating effective mixture configurations and practical pretraining recommendations under severe data constraints.


### [Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents](https://yomu.fyi/post/developing-nvidia-holoscan-applications-with-cli-skills-and-ai-coding.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Elizabeth Goodman
- Published: Aug 19, 2026
- Type: Tutorial

NVIDIA Holoscan is a platform for real-time AI applications at the edge, and HoloHub provides reference applications and components. This post describes an engineer-guided workflow in which a coding agent builds a separate Python endoscopic tool segmentation application from the existing MONAI model, sample video, and Holoscan patterns. The Holoscan CLI, invoked through ./holohub, exposes shared commands for scaffolding, running, modes, tests, and benchmarking, while development skills and documentation guide the agent through project-specific operations. The application connects video replay, preprocessing, TensorRT inference, segmentation postprocessing, telemetry, and HoloViz visualization, with visual, smoke, and benchmark modes; the post reports that the CLI-plus-skills-plus-docs/examples configuration produced a separate application in 40 minutes using 11M tokens, and concludes that this combination offered the lowest resource overhead among the compared configurations.


### [How we think about text classification in the LLM era](https://yomu.fyi/post/how-we-think-about-text-classification-in-the-llm-era.md)
- Company: [Medium](https://yomu.fyi/company/medium.md)
- Author: Raphael Montaud
- Published: Aug 19, 2026
- Type: Problem & solution

Medium revisited its aging NSFW text-classification model, which had outdated code, infrequent retraining, and poorly documented training and performance history. The replacement uses an LLM prompt containing NSFW guidelines and story content, requesting a 0-to-100 score, structured output, and a short reason rather than requiring a training set. To evaluate it, the team created a curator-labeled dataset with deliberate oversampling of NSFW stories, then compared several LLMs with the legacy model using false-positive and false-negative metrics. Some models matched or exceeded the legacy model; the team selected Mixtral 8×7b based on cost and performance and ran inference in Snowflake. The post presents this as a strong fit where training data is costly, trends are relatively stable, and only distribution-eligible stories need scoring, while topic and spam models still benefit from continuously updated datasets.


### [Designing effective Genie Agents from a single prompt](https://yomu.fyi/post/designing-effective-genie-agents-from-a-single-prompt.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Megan Tupper
- Published: Aug 19, 2026
- Type: Tutorial

Generic agents may select the first relevant-looking revenue table rather than the finance-maintained source because they lack business context. Genie Agents address this by using a single prompt to assemble a domain-specific agent from governed Unity Catalog context, including structured data, documents, and files. The prompt identifies the desired outcome and relevant sources, while the agent can retrieve content from PDFs, Word documents, presentations, images, and tables under the requesting user’s permissions. The recommended process is to begin with one focused, repetitive job, test it against known questions or incidents, and expand only after measuring performance. Built-in benchmarks provide accuracy scores, while monitoring surfaces user questions and feedback that can reveal gaps in the curated context.


### [Evaluating AI Agent Skill Performance with NVIDIA SkillEvaluator](https://yomu.fyi/post/evaluating-ai-agent-skill-performance-with-nvidia-skillevaluator.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Aug 19, 2026
- Type: Benchmark

NVIDIA SkillEvaluator measures whether packaged agent skills improve agent performance by comparing task runs with and without a skill installed. It combines three evaluation tiers: static safety and structure checks, embedding-based distinctiveness analysis, and live evaluations in isolated Harbor sandboxes. In the August 12, 2026 benchmark snapshot, more than 300 verified skills spanning over 30 NVIDIA products were tested across Claude Code and Codex, with macro-averaged Skill Lift of +31 points across all dimensions and +39 excluding Security. Correctness rose from 46 to 87 and Effectiveness from 39 to 78, while Security moved from 97 to 98; token and runtime effects varied by skill, with one reducing both and another increasing them.


### [How Clario technology detects PHI/PII in DICOM images using Amazon Bedrock](https://yomu.fyi/post/how-clario-technology-detects-phi-pii-in-dicom-images-using-amazon-bed.md)
- Company: [AWS](https://yomu.fyi/company/aws.md)
- Author: Alex Boudreau
- Published: Aug 19, 2026
- Type: Problem & solution

Clario developed an automated PHI and PII detection solution on AWS to process thousands of DICOM image slices and PDF files in clinical trials. Medical imaging workflows require strict privacy compliance under HIPAA, GDPR, and ICH E6 guidelines across standard tags, custom vendor metadata, and pixel-burned text. To address this, the pipeline retrieves files from Amazon S3 and runs memory-intensive detection workloads on Amazon EKS backed by Amazon RDS for PostgreSQL. Amazon Textract handles optical character recognition, while Anthropic's Claude Sonnet on Amazon Bedrock classifies sensitive data using domain-optimized prompt engineering. The system identifies precise coordinates and sensitive entity types rather than directly altering files, enabling human-in-the-loop review before downstream redaction occurs.


### [AI-powered clinical trial eligibility and safety using Amazon Bedrock AgentCore](https://yomu.fyi/post/ai-powered-clinical-trial-eligibility-and-safety-using-amazon-bedrock.md)
- Company: [AWS](https://yomu.fyi/company/aws.md)
- Author: Sachin Jain
- Published: Aug 19, 2026
- Type: Problem & solution

Manual chart review across fragmented clinical sources slows clinical trial enrollment, contributing to timeline delays and high screen failure rates. To address this bottleneck, an architecture on AWS automates eligibility and safety assessments while preserving human clinician authority. AWS HealthLake ingests and normalizes records into FHIR R4 resources, while Amazon Bedrock AgentCore orchestrates pre-screening, detailed screening, and site enrollment agents. Amazon Bedrock AgentCore Evaluations scores screening determinations using an LLM-as-a-judge approach for clinical accuracy, operational effectiveness, and safety compliance. This human-in-the-loop workflow produces structured recommendations with source citations, reducing patient matching time from days to minutes while maintaining compliance audit trails.


### [Accelerate automation with AI and the Ansible development tools MCP servers](https://yomu.fyi/post/accelerate-automation-with-ai-and-the-ansible-development-tools-mcp-se.md)
- Company: [Red Hat](https://yomu.fyi/company/red-hat.md)
- Author: Leonardo Gallego
- Published: Aug 19, 2026
- Type: Announcement

Ansible automation development often involves frequent context switching and struggles with AI assistants generating syntactically valid code that hallucinates module parameters or misses local dependencies. To address this gap, the Ansible development tools Model Context Protocol server connects AI assistants to external development tooling through structured interfaces. The server wraps command-line utilities, enabling AI models to deterministically run ansible-lint with automatic fixes, scaffold projects via ansible-creator, manage environments, and build execution environment container images. By surfacing local workspace schemas, documentation, and organizational linting standards, the system grounds AI responses in real environment configurations. The integration operates across multiple MCP-compatible clients without requiring a specific model provider.


### [Gisting: Compressing LLM Agent context to ↑ throughput and ↓ cost](https://yomu.fyi/post/gisting-compressing-llm-agent-context-to-throughput-and-cost.md)
- Company: [Shopify](https://yomu.fyi/company/shopify.md)
- Author: 2023-10-18
- Published: Aug 19, 2026
- Type: Explainer

Long system prompts improve agent behavior but increase inference time, cost, and the GPU capacity needed to serve a given traffic level. Shopify compresses the Sidekick GraphQL agent’s roughly 6,000-token system prompt into about 1,500 gist tokens, using special vocabulary tokens whose embeddings are learned by knowledge distillation while the model weights remain frozen. Training compares teacher logits from the full prompt with student logits from the gist-token prompt using KL divergence; at inference, the prompt is replaced with the gist-token string, requiring no custom serving path. In load tests at 350 requests per minute, compression reduced median time to first token from 438ms to 354ms and end-to-end latency from 6.8s to 4.2s, while raising throughput from 20.2 to 23.4 QPS and enabling 14% fewer GPUs in production without losing prediction quality.


### [Building Secure AI Agents with Microsoft Agent Framework and Auth0: Sending Email with Token Vault](https://yomu.fyi/post/building-secure-ai-agents-with-microsoft-agent-framework-and-auth0-sen.md)
- Company: [Auth0](https://yomu.fyi/company/auth0.md)
- Author: Andrea Chiarelli
- Published: Aug 19, 2026
- Type: Tutorial

An expense-reviewing AI agent required manual manager intervention to email employees about missing report data such as amounts, merchants, or justifications. To automate follow-ups safely, the agent uses Auth0 Token Vault to acquire and refresh Google OAuth tokens without storing credentials in the application database. The implementation configures Auth0 with offline access, My Account API permissions, and multi-resource refresh tokens to handle silent token retrieval across user sessions. Rather than exposing Gmail credentials to the underlying language model, the agent executes email actions via an internal backend endpoint that retrieves a short-lived access token, sends the email, and immediately discards the token.


### [Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts](https://yomu.fyi/post/examining-human-like-behaviors-in-llms-a-multi-dimensional-analysis-of.md)
- Company: [Apple](https://yomu.fyi/company/apple.md)
- Published: Aug 19, 2026
- Type: Benchmark

Large language models frequently exhibit human-like behaviors such as expressing emotions, building relationships, and setting boundaries, yet empirical guidance on appropriate usage remains limited. To address this gap, researchers analyzed 21,000 multi-turn conversations across four models: gpt-4o, gpt-4.1-mini, claude-sonnet-4.6, and gemini-2.5-flash. The study combined LLM-as-a-judge techniques with human evaluation to measure behavior prevalence, perceived appropriateness, and prompt controllability across diverse user goals and profiles. Human evaluators judged LLM self-referential and relationship-building behaviors as less appropriate than identical human actions, whereas boundary-maintaining behaviors were rated as more appropriate for models. System prompting effectively steered these behaviors, though the authors emphasize that rigorous evaluation remains necessary to prevent unintended side effects.


### [Databricks Document Intelligence: pushing the frontier for complex document extraction](https://yomu.fyi/post/databricks-document-intelligence-pushing-the-frontier-for-complex-docu.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Jane Zhang, Arnav Singhvi, Ivan Zhou, Archika Dogra, Matthew Ding, Nihit Desai
- Published: Aug 18, 2026
- Type: Announcement

Databricks introduces Precision Mode for its ai\_extract document extraction API, targeting enterprise workloads that challenge existing LLM and rules-based systems. The mode addresses long documents with cross-references, large nested outputs such as thousands of line items, and schemas requiring reasoning across financial statements or applying discounts. It combines custom-trained, efficient extraction models with an agent harness that decomposes jobs semantically, runs smaller tasks in parallel, preserves intermediate results, and reconciles them into a final structured output. On benchmarks covering roughly 9,000 documents, including files up to 2,000 pages and schemas with more than 300 deeply nested fields, Precision Mode reached 94.7% accuracy, seven points above the strongest frontier-model chunk-and-merge baseline, GPT-5.6 Sol; the source says it is now available through ai\_extract and the Information Extraction UI.


### [How Much Memory Does Your Agent Actually Need?](https://yomu.fyi/post/how-much-memory-does-your-agent-actually-need.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Vatche Isahagian, Gaodan Fang, Jayaram Radhakrishnan, Punleuk Oum, Ashwath Vaithinathan Aravindan, Evelyn Duesterwald, G Thomas, Vinod Muthusamy, Merve Unuvar, Ayhan Sebin
- Published: Aug 18, 2026
- Type: Benchmark

The post examines how much agentic memory different models can use effectively, evaluating ALTK-Evolve's self-distilled guidelines across eight models on AppWorld's 585 multi-step tasks. Memory is produced by extracting and consolidating lessons from successful and unsuccessful trajectories, then delivering either the full guideline set on every ReAct step or a fixed core plus task-relevant retrieval, without updating model weights. Results identify three patterns: strong models with headroom benefited from the full set, gpt-oss-120b gained 16.1 percentage points in task completion from curated retrieval, and GLM-5 showed no measurable gain; stricter scenario completion sometimes improved more. Curated retrieval gave gpt-oss-120b that gain with only 5% more tokens versus 51% for its full set, while prompt caching is presented as a way to reduce recurring input cost, supporting calibration to model capability rather than simply accumulating memory.


[Newer posts](https://yomu.fyi/topic/llm/page/8.md) · [Older posts](https://yomu.fyi/topic/llm/page/10.md)