Edition

RSS

Archive

97 stories, newest first.

November 2026 19

  1. IndustryAnalysisWhat thousands of AI research agents contribute to a science project
  2. ResearchAnalysisWhat changes when an AI agent gets laboratory feedback
  3. IndustryAnalysisTorchNeuron makes the AI chip contest a software story
  4. ModelsAnalysisApertus 1.5 opens the recipe, including the parts that did not work
  5. NewsAnalysisClaude wrote software proofs. Here is what they actually guarantee
  6. ModelsAnalysisGenie 4 turns generated scenes into interactive worlds
  7. ToolsExplainerWhat Google's Deep Review can check in a technical document
  8. ToolsAnalysisGPT-6.1 Terra and the shift from reading screens to acting on them
  9. ModelsAnalysisMuse Spark Open: what changes when the weights are available
  10. ToolsAnalysisWhy OpenAI rebuilt the machinery behind Git
  11. ResearchExplainerCan an AI response prove which model produced it?
  12. ResearchAnalysisCan one small model inherit several specialists' skills?
  13. NewsAnalysisThe UK AISI Claude incident, reconstructed from the reports
  14. ResearchExplainerWhy Google wants language models to sleep between tasks
  15. ToolsExplainerIs LiteLLM written in Rust? What the codebase and migration tracker show
  16. ToolsAnalysisThe '4.5x more requests per dollar' claim is a model, not a measurement
  17. ToolsExplainerPeak RSS vs memory at rest: reading LiteLLM's '9x less memory' figure
  18. ToolsComparisonLiteLLM Rust vs LiteLLM Python vs Bifrost: what the data means for teams running LiteLLM today
  19. ToolsExplainerThroughput vs latency: why LiteLLM Rust and Bifrost tie at 2,722 vs 2,719 RPS

October 2026 59

  1. ResearchAnalysisDeveloper tools drew half of all stated AI deal money from 9% of deals
  2. ResearchAnalysisAI-native companies post 24% more for AI engineers, and two labs carry most of it
  3. ResearchAnalysisTracked AI lawsuits tripled since 2023, and 58 of 66 are still unresolved
  4. ResearchAnalysisSalesforce, Meta and Microsoft cut 16,800 jobs and kept buying AI companies
  5. ToolsSurveyBest Claude Code skills in 2026: 11 tested and ranked for production AI teams
  6. NewsBifrost's Agent Gateway puts A2A agent calls behind virtual keys and logs
  7. NewsBifrost now grades each prompt's difficulty before it picks a model
  8. NewsBifrost Edge moves the AI gateway from the data centre onto every laptop
  9. NewsBifrost's MCP gateway upgrades target tool bloat, per-user auth and REST APIs
  10. NewsBifrost's Warp puts a plain-language analyst inside the AI gateway
  11. ToolsExplainerClaude Code enterprise rollout: a phased plan with budgets, managed settings and logs
  12. ToolsExplainerCodex skills: how Agent Skills work in OpenAI Codex, and which ones to install
  13. ToolsExplainerCursor skills: how Agent Skills work in Cursor, and the six worth installing
  14. ToolsExplainerLLM observability: what to capture, how to trace agents, and which tools fit
  15. ToolsExplainerMCP best practices: tool budgets, permissions and approvals for real agent teams
  16. ToolsExplainerOWASP LLM Top 10 (2026): every risk, the vulnerable code and the fix
  17. ToolsExplainerClaude skills marketplace: when to use public ones and when to run your own
  18. ToolsExplainerPrompt caching: how it cuts LLM costs at Anthropic, OpenAI and Gemini
  19. ToolsExplainerskills.sh and npx skills add: the complete guide to installing agent skills
  20. ToolsExplainerThe definitive guide to Atlassian MCP: setup, auth, admin controls and limits
  21. ToolsExplainerClaude API keys: how to create, scope, secure and rotate them
  22. ToolsExplainerClaude --dangerously-skip-permissions: a practical guide to what it bypasses
  23. ToolsExplainerClaude API platform admin: roles, workspaces and the Admin API explained
  24. ModelsExplainerClaude Sonnet 5.5: a practical guide to price, effort, benchmarks and migration
  25. ToolsExplainerModel Context Protocol: the definitive guide to how MCP works in 2026
  26. ToolsExplainerSlack MCP server: the definitive guide to tools, setup and security
  27. ToolsExplainerWhat is an MCP server? Meaning, anatomy and how to vet one
  28. ToolsExplainerWhat is MCP? A practical guide to connecting AI apps to your tools
  29. ToolsExplainerA2A vs MCP: what each protocol does and when you need both
  30. IndustryExplainerAI governance framework: the definitive guide, from NIST and ISO to runtime
  31. ModelsComparisonBest LLM for coding in October 2026: ten models ranked on the evidence
  32. ToolsExplainerClaude Code pricing: every plan, its usage limits and a developer's real monthly cost
  33. ToolsExplainerClaude Code Router explained: running Claude Code on GPT, Gemini and local models
  34. ToolsExplainerClaude Skills explained: how Agent Skills work in Claude Code, apps and the API
  35. ToolsComparisonCodex vs Claude Code in October 2026: models, sandboxes, pricing and which to pick
  36. ToolsComparisonCursor vs Claude Code in October 2026: IDE agent or terminal agent?
  37. ToolsExplainerMCP security and authentication: how the OAuth flow works and where attacks land
  38. ToolsComparisonOpenRouter alternatives in 2026: where teams go after a hosted aggregator
  39. ResearchExplainerPrompt injection attacks: real examples, why they work and the defences that hold
  40. ModelsExplainerSelf-hosted LLM guide for 2026: VRAM maths, Ollama vs vLLM and the break-even
  41. IndustryComparisonTop AI governance tools in 2026: nine platforms, two different jobs
  42. ToolsComparisonTop 10 AI guardrails tools in 2026, ranked by where they enforce
  43. ResearchExplainerWhat is an agent harness? The loop, tools and context around the model
  44. ToolsComparisonTop 5 AI gateways for air-gapped and in-VPC LLM deployments in 2026
  45. ToolsComparisonTop 5 AI gateways for failover across Bedrock, Vertex AI and Azure OpenAI in 2026
  46. ToolsComparisonTop 5 AI gateways for Claude Code, Codex CLI and Cursor in 2026
  47. ToolsComparisonTop 5 AI gateways for multimodal workloads in 2026
  48. ToolsComparisonTop 5 AI gateways for Anthropic, OpenAI and Gemini in 2026
  49. ToolsComparisonTop 5 AI gateways for routing between vLLM, Ollama and cloud LLMs in 2026
  50. ToolsComparisonTop 10 agent orchestration frameworks in 2026, ranked for production
  51. ToolsComparisonTop 10 AI gateways in 2026, ranked for production use
  52. ModelsComparisonTop 10 AI models in October 2026, ranked by what they are good at
  53. IndustryComparisonTop 10 managed agent orchestration platforms for enterprises in 2026
  54. ToolsComparisonTop 10 MCP gateways in 2026, compared for enterprise agent teams
  55. ToolsComparisonTop 10 MCP servers in 2026, and how to run them safely
  56. ToolsComparisonTop 10 MCP servers for coding agents in 2026, ranked on what they cost and what they risk
  57. ToolsComparisonTen open-source AI gateways you can self-host in 2026, ranked
  58. ToolsComparisonTop 10 open-source MCP gateways you can self-host in 2026
  59. ModelsComparisonTop 10 open-weight models in October 2026, ranked for teams that self-host

September 2026 19

  1. NewsBifrost now routes TypeSafe's Jev, with a decisions API and LLM fallbacks
  2. NewsAnalysisWhat Jev is actually for: seven jobs for a model that only decides
  3. ToolsComparisonLiteLLM alternatives in 2026: why teams switch and where they go
  4. ToolsExplainerMCP gateway explained: what it does and when agent teams need one
  5. ToolsExplainerSemantic caching for LLMs: how it works and where it goes wrong
  6. IndustryAnalysisShadow AI: why blocking fails and what actually governs it
  7. NewsTypeSafe AI launches Jev, a $40M bet on AI that decides instead of chats
  8. IndustryExplainerWhat are System One models, and will the category outlast Jev?
  9. ToolsExplainerWhat is an AI gateway? How it works, when you need one and how to choose
  10. NewsAnalysisInference prices keep falling. Here is who actually keeps the saving
  11. NewsExplainerThe EU AI Act's model rules, one year in: what changed, who signed and who enforces
  12. ModelsExplainerHow to read a model card without being fooled: the 2026 field guide
  13. ModelsAnalysisOpen weights trail the frontier by months. The economics say the gap will not close
  14. ResearchExplainerWhat reasoning models actually do: a training recipe and a token budget
  15. ResearchAnalysisTest-time compute changed the scaling roadmap. Here is what it costs, and who pays
  16. ToolsComparisonFive LLM gateways compared: failover, governance, MCP and where each one fits
  17. ToolsSurveyAgent frameworks in 2026: four camps, two protocols and how to choose
  18. IndustryEditorialBenchmarks became a marketing channel. Read the footnotes, then run your own
  19. IndustryExplainerThe real cost of an AI product, line by line: tokens are rarely the biggest line