标签：#OpenAI

OpenAI's GPT-5.5, GPT-5.4, and Codex are now generally available on Amazon Bedrock, one month after OpenAI revised its exclusive Azure arrangement. Pricing matches OpenAI's direct rates with usage counting toward AWS commitments. Codex shifts to pay-per-token billing with no seat fees. GPT-5.4 is the first OpenAI model available in AWS GovCloud. By Steef-Jan Wiggers

Note: This is an English digest of the original Zenn post (Japanese) . Read there for the full timeline and commit-level trace. TL;DR We ship tasteck , a B2B SaaS for the Japanese night-leisure industry (dispatch + cast shift management). 8 years of operational data, ~100 venues live. Two days after the MCP design post , ChatGPT Plus can call our tools live: "Who's available tonight?" → MCP list_available_drivers → JSON → natural-language reply. Estimated B2 OAuth sprint = 2 weeks (6/16–7/1). Actual = 1 day , by reading the spec carefully before touching code. We hit 12 distinct traps between "OAuth issuance works" and "ChatGPT actually invokes the tool." The QA logs caught every one. What we shipped 3 read tools (B1): list_available_drivers — drivers free tonight list_cast_shifts — today's cast shift roster list_assignable_casts — joined resolution: roster ∧ stage-name set ∧ shop match Natural-language date helper: resolveBusinessDate(naturalText, company) — handles "today / tomorrow / day-after-tomorrow" and the per-tenant business-day boundary (e.g. day flips at 04:00 or 05:00, configured per Company.changeDateTime ). MCP SDK Server + SSE transport: @modelcontextprotocol/sdk wired into a NestJS controller. One SSE connection = one McpServer instance, company-scoped, with a session_id Map routing POST /messages . OAuth flow (B2, finished in one day across 7 steps) Step What Commit 1 Protected Resource Metadata endpoint (RFC 9728) d6f05ff6 2 /authorize + consent screen + PKCE start 107edbcb 3 /token + PKCE verify + JWT issue + resource (RFC 8707) ffd0468c 4 OAuthAccessTokenGuard (RS256 + HS256 fallback, extracts companyId / staffId ) f2c9bed4 5 Streamable HTTP transport (SSE → POST /sse/:companyId for JSON-RPC) 3a28d92f 6 resolveBusinessDate undefined fallback (`(naturalText 7 QA redeploy + ChatGPT live demo — The 12 traps (compressed) The full timeline is in the Japanese post; the abridged list: Discovery path mismatch. ChatGPT expected {% raw %} .well-known/oauth

OpenAI has shipped more developer-facing infrastructure in the first half of 2026 than in the prior two years combined. GPT-5.5 is live. The Agents SDK is production-ready. Codex hit 5 million weekly active users. And yet most of the coverage is about ChatGPT's chat UX. Let's skip that and talk about what actually matters: ChatGPT's biggest upgrade ever and what developers actually need to know in June 2026. What changed at the API layer, which features are production-grade versus demo-ware, and whether it's finally time to move workloads back from Claude or Gemini. I spent the last two weeks migrating an internal agent pipeline from the Chat Completions API to the new Responses API. The difference is not subtle. This isn't a model bump with a new blog post. It's a platform rearchitecture. ChatGPT's Biggest Upgrade: The Responses API Changes Everything Forget GPT-5.5 for a second. The single most important change for developers building on OpenAI is the Responses API . If you've been building with Chat Completions, you know the drill: you manage conversation history client-side, pass the full message array on every request, and bolt on your own tool-calling orchestration. The Responses API eliminates most of that. Three things that actually matter: Server-side conversation state. OpenAI manages conversation history for you now. No more serializing and replaying message arrays on every call. For long-running agentic sessions, this alone cuts your infrastructure code in half. The reasoning_effort parameter. You can tell the model, per request, how much compute to burn on chain-of-thought reasoning before answering. Low effort for latency-sensitive paths like autocomplete and classification. High effort for accuracy-critical ones like analysis and code generation. Neither Claude nor Gemini expose anything equivalent at the API level right now. Background Mode. This is the one that changes architectures. Fire off a long-running task. Get results via webhook callback ins

OpenAI on Monday checked off a preliminary step in the IPO race that it and rival Anthropic have been competing in for the better part of a year: The company announced it has confidentially submitted a Form S-1 with the US Securities and Exchange Commission, following Anthropic's decision to do the same on June 1st. […]

The ChatGPT maker announced it has filed paperwork to go public, just a week after rival Anthropic took the same step.

Per-request attribution starts with five fields on every call: provider, model, input tokens, output tokens, and ownership tags such as team, feature, and customer. A monthly vendor bill cannot explain why one feature, one tenant, or one prompt template suddenly became expensive. Request-level math can. As of June 8, 2026, OpenAI lists GPT-5.4 mini at $0.75 per 1M input tokens and $4.50 per 1M output tokens, while Anthropic lists Claude Sonnet 4 at $3 and $15 respectively. Gateway logs are useful, but they rarely solve AI cost tracking per feature unless you enrich them with business context and retry metadata. The practical operating model is simple: calculate cost on every request, attach ownership dimensions, then roll the data up into team, feature, and customer views. If you are searching for "LLM cost attribution per request," you are usually already past the basic billing problem. You can see your OpenAI or Anthropic invoice, but you cannot answer the questions finance and engineering actually care about: which feature drove the spike, which team owns it, which customers are unprofitable, and which prompt or model change caused the jump. That is why per-request attribution matters. It turns AI spend from a monthly surprise into an operational metric you can act on in the same day. Why LLM cost attribution per request matters now According to the FinOps Foundation's 2025 State of FinOps report, 63% of respondents now manage AI spending, up from 31% the year before. That jump is the real signal. AI cost is no longer a side bucket inside cloud spend. It is becoming a first-class FinOps workload. For teams spending $5,000 to $50,000 per month on LLM APIs, averages break down quickly. A support assistant, an internal coding copilot, and a customer-facing generation feature can all hit the same vendor account while having completely different margins, latency targets, and prompt shapes. If you only look at total spend by provider, you lose the unit economics. Per-r

OpenAI to recast hit chatbot as a route to higher-margin products before a potential IPO.

"Chat is dead" — at least, according to a senior OpenAI employee.

Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

President Donald Trump said he's discussing deals "where the American people can benefit from the success of AI."

“Why wouldn’t you want to be in both Pepsi and Coke?” says one venture capitalist. “It’s the same here.”

At Microsoft's annual Build conference on Tuesday, the company announced a slew of new or expanded AI initiatives, including a super app, in-house reasoning models, a cybersecurity tool, and OpenClaw-esque AI agents. All this news added up to a clear message: Microsoft is positioned to be one of the biggest players in AI, and it's […]

Last year I helped a startup integrate the OpenAI API into their product. It was a chat feature — users could ask questions about their data and get natural language answers. The integration took about a day. Three days after launch, the founder messaged me: "Hey, something's wrong. Our AWS bill just showed an unexpected charge." It was $340. For three days. They had 60 users. The issue wasn't a bug — it was that production API usage looks nothing like a tutorial. The tutorial shows you openai.chat.completions.create() and returns a response. The tutorial doesn't show you what happens when users send 500-token messages, when they open 15 browser tabs each maintaining their own chat context, or when one user fires requests 30 times per minute because they think it's broken. This guide covers what the tutorials skip: rate limiting, token counting, cost guards, streaming, error handling with retries, and model selection. These aren't optional additions — they're what separates a demo from a production feature. Why Production Is Different Here's the gap between tutorial code and production code, stated plainly: Concern Tutorial Code Production Code Cost control Not mentioned Token counting, spending limits, model selection by task Rate limiting Not mentioned Per-user and per-IP limits to prevent abuse Error handling try/catch that logs to console Typed errors, retries with backoff, user-facing messages Response delivery Wait for full completion, return at once Streaming via SSE — response appears as it generates Context management Each request is independent Conversation history managed, truncated at token limit Secrets management API key hardcoded or in .env (no rotation) Rotation strategy, usage monitoring, per-feature keys Let's build a production-grade Express API that addresses all of this. We'll go layer by layer. The Architecture ┌─────────────────────────────────────────────────────────┐ │ CLIENT (Browser / Mobile) │ │ POST /api/chat { messages: [...] } │ │ GET

Opal, the company famous for making a fancy webcam, has pivoted to making other consumer electronics. Fueled by big investments from OpenAI and Samsung, it’s working on an audio gadget first.

The lawsuit partially revolves around a shooting at Florida State University last year, and ChatGPT's alleged role in the incident.

The company said Monday it has filed confidentially for an IPO.

Large language models (LLMs) understand and generate text from prompts. OpenAI exposes models through the Responses API . The official openai npm package is the practical way to call it from Node.js. This post covers common patterns beyond a single prompt string. Prerequisites OpenAI account Generated API key Enabled billing Node.js version 26 openai package installed ( npm i openai ) For Markdown output: marked , dompurify , and jsdom ( npm i marked dompurify jsdom ) Client setup Create a client with your API key (read from the environment in production). import OpenAI from ' openai ' ; const client = new OpenAI ({ apiKey : process . env . OPENAI_API_KEY }); The same SDK can target other hosts that implement a compatible API by setting baseURL and apiKey : const client = new OpenAI ({ apiKey : process . env . LLM_API_KEY , baseURL : ' https://your-gateway.example/v1 ' , }); Azure OpenAI uses AzureOpenAI instead. Many third-party gateways support Chat Completions only; the examples below use client.responses.* , so confirm your provider supports the Responses API (especially for tools like web search). Basic integration Pass a string as input and read output_text from the response. const response = await client . responses . create ({ model : ' gpt-5.5 ' , input : ' Write a one-sentence bedtime story about a unicorn. ' , }); console . log ( response . output_text ); System prompt Use top-level instructions for stable behavior (tone, format, role). They take precedence over casual wording in the user message. const response = await client . responses . create ({ model : ' gpt-5.5 ' , instructions : ' Reply in one short sentence. Use plain language. ' , input : ' Explain what an LLM is. ' , }); console . log ( response . output_text ); Few-shot prompting Pass prior turns as an input array with user and assistant roles, then the new user message. Keep task rules in instructions . const response = await client . responses . create ({ model : ' gpt-5.5 ' , instructions :

I tried to explain OpenAI’s solution more clearly than OpenAI did.

AI จะครองโลก เป็นคำที่ได้ยินมานาน เท่าที่ผู้เขียนจำความได้ก็มี Judgement Day ยุคหนัง Terminator แต่หากจะจริงจังขนาดโยงเข้าความเป็นจริงก็ยังไม่มีอะไรชัดเจน แต่วันนี้เรามีหลักฐานพิสูจน์ได้จริงแล้ว ด้วยความ Novelty จาก OpenAI ที่สามารถค้นพบความรู้ใหม่ที่ไม่เคยมีมนุษย์ค้นพบมาก่อน หักล้างความเชื่อที่ว่า AI ทำได้เพียงนำสิ่งที่มนุษย์ค้นพบแล้วมาเรียงต่อกัน ในเดือนพฤษภาคม 2026 reasoning model ภายในของ OpenAI ได้ disprove Erdős Planar Unit Distance Problem ซึ่งเป็นปัญหาและข้อคาดการณ์ทาง Combinatorial geometry ที่ Paul Erdős ตั้งไว้ตั้งแต่ปี 1946 โจทย์ระบุว่า เมื่อวางจุด nn n จุดบนระนาบ จำนวนของคู่จุดที่ห่างกันพอดี 1 หน่วยจะมีได้มากที่สุดเท่าใด Erdős แสดงความเป็นไปได้ผ่านการจัดเรียงแบบ grid ว่าได้จำนวนคู่ที่เติบโตเหนือเส้นตรงเพียงเล็กน้อย และตั้งข้อคาดการณ์ว่าไม่มีโครงสร้างใดทำได้ดีกว่านี้อย่างมีนัยสำคัญ ข้อคาดการณ์นี้ได้รับการยอมรับในวงกว้างตลอด 80 ปีที่ผ่านมา และยังไม่มีข้อคาดการณ์ที่ดีกว่านี้ จนกระทั่ง OpenAI ได้เผยแพร่ Chain of Thought (CoT) เรียบเรียงความยาว 125 หน้า ซึ่งบันทึกลำดับการให้เหตุผลของโมเดลไว้ทั้งกระบวนการว่าโมเดลไปถึงคำตอบอย่างไร กรอบของคำตอบ: lower bound กับ upper bound ก่อนเข้ากระบวนการทำงานของโมเดล ขออธิบาย "กรอบ" ของคำตอบของปัญหานี้ก่อน เพราะคำตอบถูกล้อมไว้ด้วย lower bound จำนวนที่สร้างได้จริงแล้ว อย่างน้อยเท่านี้ และ upper bound เพดานที่พิสูจน์แล้วว่าเกินไม่ได้ ด้าน lower bound นั้น Erdős เอง (1946) ใช้การจัดเรียงแบบ grid แสดงว่าสร้างได้ถึง n1+Ω(1/log⁡log⁡n)n^{1+\Omega(1/\log\log n)} n 1 + Ω ( 1/ l o g l o g n ) ซึ่งมากกว่าเส้นตรงเพียงเล็กน้อย และเข้าใกล้ศูนย์เมื่อ nn n ใหญ่ขึ้น ส่วนด้าน upper bound นั้น Erdős พิสูจน์เพดานแรกไว้ที่ O(n3/2)O(n^{3/2}) O ( n 3/2 ) จากวงกลมหนึ่งหน่วยสองวงตัดกันได้ไม่เกินสองจุด โดยต่อมา Spencer–Szemerédi–Trotter (1984) บีบเพดานนี้ลงมาเป็น O(n4/3)O(n^{4/3}) O ( n 4/3 ) ซึ่งเป็น upper bound ที่ดีที่สุดจนถึงปัจจุบัน และยังคงอยู่หลังการค้นพบของ OpenAI model วิธีเก่าของ Erdős: วงกลมรัศมีเลือกมาลากผ่านจุด grid หลายจุดพร้อมกัน ทำให้ระยะซ้ำมีมาก สิ่งที่ Erdős คาดการณ์คือ คำตอบจริงของ Planar Unit Distance Problem ควรอยู่ชิดด้าน lower

On May 29, 2026, OpenAI published its Frontier Governance Framework — and most developers moved on to the next item in their feed. That’s a mistake worth correcting. The document doesn’t announce a new model or lower an API price. It describes how OpenAI measures whether its own systems could enable mass-casualty events, what access controls gate who can reach those capabilities, and how this maps to the regulations — the EU AI Act and California’s Transparency in Frontier AI Act — that are actively shaping compliance requirements for any enterprise deploying frontier AI this year. If you build security tools on OpenAI APIs, the framework’s Trusted Access for Cyber program directly affects what your application can and cannot do. If you operate in a regulated environment, the framework is the vendor-side accountability document your compliance team needs to reference. And if you build on frontier models at all, the risk tier system in this framework governs the capability restrictions you will encounter — and, increasingly, what auditors and procurement teams will ask about when vetting your AI vendor stack. What the Framework Actually Is The Frontier Governance Framework is OpenAI’s published methodology for evaluating the risk profile of frontier models before and after deployment. It covers six functional areas: risk assessment and mitigation, model reporting, security risk management, incident response, external expert input, and framework updates. Each area has defined processes, thresholds, and accountability mechanisms. The core architecture is a tier system applied across four risk domains. Each domain is evaluated independently, with tiers reflecting capability levels that could enable specific categories of harm. A model’s rating in any domain determines what deployment controls apply — what gets blocked at the API layer, who gets elevated access, and what triggers an incident response workflow. The framework was published explicitly to align with two regu