We believe our research will eventually lead to artificial general intelligence, a system that can solve human-level problems. Building safe and benef
Users generally praise OpenAI for its advanced AI capabilities and innovative features, reflected in high ratings on review platforms. However, there is significant debate about the value of its pricing, particularly the $200 per month for ChatGPT Pro, with some users questioning its worth compared to the more affordable Plus plan. Overall, while OpenAI is recognized as a leader in AI development and securing substantial investments, its premium pricing may deter some potential users despite its promising advancements. The company's reputation remains strong, driven by continuous innovation and a focus on expanding AI applications.
Mentions (30d)
0
Avg Rating
4.5
5 reviews
Platforms
8
GitHub Stars
10,775
1,446 forks
Users generally praise OpenAI for its advanced AI capabilities and innovative features, reflected in high ratings on review platforms. However, there is significant debate about the value of its pricing, particularly the $200 per month for ChatGPT Pro, with some users questioning its worth compared to the more affordable Plus plan. Overall, while OpenAI is recognized as a leader in AI development and securing substantial investments, its premium pricing may deter some potential users despite its promising advancements. The company's reputation remains strong, driven by continuous innovation and a focus on expanding AI applications.
Features
Use Cases
Industry
research
Employees
8,200
Funding Stage
Venture (Round not Specified)
Total Funding
$287.3B
116,683
GitHub followers
238
GitHub repos
10,775
GitHub stars
20
npm packages
40
HuggingFace models
18,737,418
npm downloads/wk
283,709,819
PyPI downloads/mo
OpenAI just released o1 and their new $200 / month ChatGPT Pro plan. It includes unlimited access to the o1 reasoning model, which is smarter, faster, and better at solving complex problems than ever
OpenAI just released o1 and their new $200 / month ChatGPT Pro plan. It includes unlimited access to the o1 reasoning model, which is smarter, faster, and better at solving complex problems than ever before. This model can even analyze images now, making it a powerhouse for tasks like coding, math, and science. Pro users also get an exclusive "o1 pro mode" that uses extra computing power for the hardest questions.It’s designed for researchers and professionals who need cutting-edge AI tools daily.This plan also bundles GPT-4o and Advanced Voice features for an all-in-one premium experience. While the price is steep, OpenAI says it’s aimed at those who need top-tier AI performance. For everyone else, o1 is still accessible on lower plans but with limitations.The launch also includes a grant program for medical researchers to use ChatGPT Pro for free.It’s a bold move from OpenAI as they push the boundaries of what AI can do.
View original| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| gpt-4.1 | $2.00 | $8.00 |
| gpt-4.1-mini | $0.40 | $1.60 |
| gpt-4.1-nano | $0.10 | $0.40 |
| gpt-4o | $2.50 | $10.00 |
| gpt-4o-mini | $0.15 | $0.60 |
| gpt-4.5-preview | $75.00 | $150.00 |
| gpt-4-turbo | $10.00 | $30.00 |
| gpt-4 | $30.00 | $60.00 |
| gpt-3.5-turbo | $0.50 | $1.50 |
| o3 | $10.00 | $40.00 |
| o4-mini | $1.10 | $4.40 |
| o1 | $15.00 | $60.00 |
| o1-preview | $15.00 | $60.00 |
| o1-mini | $3.00 | $12.00 |
| o3-mini | $1.10 | $4.40 |
Light
1M tokens/mo
$0.22 – $105
gpt-4.1-nano → gpt-4.5-preview
Growth
50M tokens/mo
$11 – $5,250
gpt-4.1-nano → gpt-4.5-preview
Scale
500M tokens/mo
$110 – $52,500
gpt-4.1-nano → gpt-4.5-preview
Estimates assume 60/40 input/output ratio. Actual costs vary by usage pattern.
g2
What do you like best about Openai?OpenAI has been a game-changer in how people interact with technology. Its tools are intuitive, fast, and genuinely helpful for everything from learning to productivity. The responses feel natural and human-like, making complex tasks much easier. Overall, it’s an impressive step forward in AI innovation. Review collected by and hosted on G2.com.What do you dislike about Openai?While OpenAI tools are powerful, they can sometimes give incorrect or outdated information. Responses may feel overly cautious or generic at times, and there are limits on deeper customization. Occasionally, it also struggles with understanding very specific or nuanced queries. Review collected by and hosted on G2.com.
What do you like best about Openai?What I like best about OpenAI, as someone building internal AI agents, is how quickly we can go from a concept to something real that people can use. The APIs are straightforward, the documentation is good enough to get up and running fast, and there’s a wide range of models and features to choose from. That combination of ease of integration and depth of capabilities lets us experiment, iterate, and then standardize on the patterns that work across the business. Once things are in place, our teams end up using these AI-powered workflows constantly because they’re embedded right into the tools they already work in. Review collected by and hosted on G2.com.What do you dislike about Openai?From an enterprise admin perspective, the main friction points are around control and operational overhead. The core APIs are easy to integrate, but getting to a fully production-ready setup, prompt design, evaluation, monitoring, governance, and cost management takes real effort. The feature set is rich, but that also means there’s a learning curve to choosing the right models and configurations for each use case. Support and guidance have improved, but I’d still like more opinionated best practices and examples geared specifically toward larger teams rolling out multiple agents across the organization. Review collected by and hosted on G2.com.
What do you like best about Openai?It gives quick explanations, supports me with writing and coding tasks, and makes it easier to learn new topics without spending a lot of time searching online. Review collected by and hosted on G2.com.What do you dislike about Openai?Sometimes the responses aren’t fully accurate or up to date, so it’s a good idea to double-check any important information. Review collected by and hosted on G2.com.
What do you like best about Openai?I'm using it to debug a snippet of code, and the next I'm asking it to help me draft a polite email or generate a cool image for a project. The integration between the text and image tools is super smooth now Review collected by and hosted on G2.com.What do you dislike about Openai?I’m honestly pretty uncomfortable with the privacy. There are also moments when it misunderstands the context and you have to rephrase the question to get what you actually want. Review collected by and hosted on G2.com.
What do you like best about Openai?It helps me create a second draft of my documents, making it easier to reach the final draft. It also helps me to view work through other people's perspectives. Review collected by and hosted on G2.com.What do you dislike about Openai?The environmental impact, the relationship with data use, and sharing with the federal government. There should be stronger guardrails around usage and overall impact. Review collected by and hosted on G2.com.
Geoffrey Hinton (Nobel laureate and cognitive scientist) thinks AIs have become conscious
submitted by /u/EchoOfOppenheimer [link] [comments]
View originalD&D Woodland Creatures
submitted by /u/SeldonCrises [link] [comments]
View originalMoving from antigravity to Codex
Hello, I am looking into subscribing to OpenAI Pro. I currently have access to Gemini Pro through a Google family plan, but I find that I hit my usage limits incredibly quickly compared to using the Gemini CLI which they are deprecating. I also feel that the Gemini models are not the best for coding tasks. Because of this, I was wondering what experiences others have had with OpenAI Plus, what the actual usage limits look like in practice, and whether people feel the subscription is worth it for coding? Edit forgot to add that I'm in Australia and code between 22:00 and 08:00 UTC time submitted by /u/Bitpoke [link] [comments]
View originalI got Rick Rolled by Claude Code
I'm currently working recreating the outer glow effect (Ambient Mode) that YouTube has. To check YouTube's implementation of this effect, Claude Code opened no other than Rick Astley's "Never Gonna Give You Up". Claudes reply on the matter: And yes — that was indeed a Rick Roll. In my defence, it's the most reliably-available public YouTube video for testing purposes. Classic. Didn't expect to get Rick Rolled by an AI, but here we are. submitted by /u/Grimgorkos [link] [comments]
View originalAny AI to recommend that can turn a snap shot into studio product shoot catalog and turn a fashion shoot into a video that the model will do a 360 or something?
As above. submitted by /u/Hot-Clothes7316 [link] [comments]
View original[P] Free AI Agent Security Assessment [P]
Hey everyone, We’re building Antitech, a security layer for AI agents and LLM-powered workflows. We’re opening a small number of free early-access assessments for teams/builders working on AI agents. If you give us access to an endpoint of a Dockerized / sandboxed environment of your agent, we’ll test it against common and emerging AI-agent attack vectors, including: Prompt injection Indirect prompt injection Tool abuse Data leakage / exfiltration Fake authority / malicious context Unsafe agent behavior Weak guardrails and policy bypasses In return, you get a free vulnerability report showing what we found, how serious it is, and practical recommendations to harden your agent. This is completely free. No catch. We’re doing this because we want to work closely with real AI-agent builders while shaping the product. Early participants will also get: A big discount once the final product is ready Insider updates while we build Early access to new features The option to become a design partner Priority access to future assessments What we need from you: An endpoint of a sandboxed/Docker environment Permission to test within agreed boundaries A short feedback call after the report We won’t publicly disclose anything without your permission. If you’re building AI agents and want to know how they can be attacked before someone else finds out the hard way, DM me or comment below. submitted by /u/TheAchraf99 [link] [comments]
View originalMars Habitat & Polar Habitat
People got very upset with my last post, because apparently it wasn't photo real. This is more like architectural realism. The habitat uses native desert fauna in its observatory/lunchroom, its is made out of 4m x 16 m dual layer spiral made modified HDPE plastic cylinders. Designed for a 4-6 person operation. Minimal resupply, eventually to make it 1 in 4 year resupply. Most O2 and food water is recycled. 1MWhr battery, small reactor, mostly solar powered. Concept would be first prototyped in desert conditions, then a polar test, then perhaps a moon test. Also shown is a Mars emergency or transit shelter (for long journeys) and a polar shelter. submitted by /u/phido3000 [link] [comments]
View originalEliezer Yudkowsky's official AI apocalypse apology form
submitted by /u/KeanuRave100 [link] [comments]
View originalGive me the most random Ai pictures and videos
submitted by /u/Ernar0 [link] [comments]
View originaltrying to see if Mythos claims are verified or not
The claims about Mythos Preview (Anthropic's unreleased Claude model) are substantially verified from multiple independent sources, though the exact CVE numbers and commit hashes for the FFmpeg vulnerability are still being disclosed through coordinated security processes. Key Verified Facts 1. OpenBSD 27-year-old vulnerability ✅ Verified What: A bug in OpenBSD's TCP SACK (Selective Acknowledgment) handling introduced around 1998[forum.devtalk] Impact: Allows an attacker to remotely crash any OpenBSD machine just by connecting to it via TCP[linkedin] Details: OpenBSD tracks SACK state as a singly linked list of holes; the vulnerability is subtle and survived 27 years of expert review[reddit] Patch: Available at openbsd/pub/Openpatches/.8/025ack.patch[reddit] 2. FFmpeg 16-year-old vulnerability ✅ Verified What: A bug in FFmpeg's H.264 decoder where a 32-bit slice counter is stored in a 16-bit lookup table, initialized to 65535[secureworld] Impact: A specially crafted frame with exactly 65,536 slices causes counter collision triggering out-of-bounds write[secureworld] Origin: Type mismatch dates to FFmpeg's 2003 H.264 commit; exploitable code path introduced in 2010 refactor[secureworld] Testing evasion: The code path was hit by automated testing tools 5 million times without flagging the bug[linkedin] Patch status: Three FFmpeg vulnerabilities found by Mythos were patched in FFmpeg 8.1[secureworld] 3. Linux kernel vulnerability chain ✅ Verified What: Mythos autonomously found and chained multiple Linux kernel vulnerabilities for privilege escalation[reddit] Impact: Escalation from ordinary user to complete root control of the machine[linkedin] Cost: Under $2,000 in tokens to create the exploit chain[linkedin] Status: Anthropic is funding the Linux Foundation to fix these vulnerabilities[linkedin] Supporting Evidence Source Type Key Confirmation Anthropic's risk report Official PDF Technical assessment of Mythos Preview released April 7, 2026 [anthropic] AI Security Institute evaluation Independent Confirmed 73% success on expert-level cyber CTF tasks [aisi.gov] Debian security tracker Official CVE-2026-40962 fixed in FFmpeg 8.1 [security-tracker.debian] Reddit/OpenBSD forum Community Patch discussion and technical details [reddit] Why This Matters This is considered "possibly the most frightening cybersecurity news in decades" because: AI found bugs that survived decades of expert audits and relentless fuzzing[agent-wars] Mythos found thousands of zero-days versus Opus 4.6's ~500[reddit] The model achieved 181 working exploits in Firefox benchmark testing[agent-wars] Access is gated/restricted due to dual-use risk[docs.aws.amazon] The FFmpeg commit should indeed be public given it's open source, and the patch is in FFmpeg 8.1. The exact commit hash is being handled through coordinated disclosure, but the vulnerability details are confirmed by multiple independent security researchers.The claims about Mythos Preview (Anthropic's unreleased Claude model) are substantially verified from multiple independent sources, though the exact CVE numbers and commit hashes for the FFmpeg vulnerability are still being disclosed through coordinated security processes.Key Verified Facts1. OpenBSD 27-year-old vulnerability ✅ VerifiedWhat: A bug in OpenBSD's TCP SACK (Selective Acknowledgment) handling introduced around 1998[forum.devtalk] Impact: Allows an attacker to remotely crash any OpenBSD machine just by connecting to it via TCP[linkedin] Details: OpenBSD tracks SACK state as a singly linked list of holes; the vulnerability is subtle and survived 27 years of expert review[reddit] Patch: Available at openbsd/pub/Openpatches/.8/025ack.patch[reddit]2. FFmpeg 16-year-old vulnerability ✅ VerifiedWhat: A bug in FFmpeg's H.264 decoder where a 32-bit slice counter is stored in a 16-bit lookup table, initialized to 65535[secureworld] Impact: A specially crafted frame with exactly 65,536 slices causes counter collision triggering out-of-bounds write[secureworld] Origin: Type mismatch dates to FFmpeg's 2003 H.264 commit; exploitable code path introduced in 2010 refactor[secureworld] Testing evasion: The code path was hit by automated testing tools 5 million times without flagging the bug[linkedin] Patch status: Three FFmpeg vulnerabilities found by Mythos were patched in FFmpeg 8.1[secureworld]3. Linux kernel vulnerability chain ✅ VerifiedWhat: Mythos autonomously found and chained multiple Linux kernel vulnerabilities for privilege escalation[reddit] Impact: Escalation from ordinary user to complete root control of the machine[linkedin] Cost: Under $2,000 in tokens to create the exploit chain[linkedin] Status: Anthropic is funding the Linux Foundation to fix these vulnerabilities[linkedin]Supporting EvidenceSource Type Key Confirmation Anthropic's risk report Official PDF Technical assessment of Mythos Preview released April 7, 2026 [anthropic] AI
View originalI want to make automation of news of merger and inquisition site and aftermarket report and with link to chatgpt explanation and how it'll affect In a particular format everyday.
Like let's say One major merger and inquisition story of the industry per day And major financial news of the day 4-5 followed by before market and by night aftermarket report Is this automation possible? submitted by /u/Ok-Airline4187 [link] [comments]
View originalLaunching Conifer tomorrow, an open-source local AI runtime + IDE. Different layer of the stack from PewDiePie's Odysseus, would love your honest thoughts
Great to see Odysseus blow up this past day, local AI getting this much attention is genuinely good for everyone building in this space. Figured this is the right crowd to share what we're launching tomorrow (June 1st), since we're playing a pretty different game. A quick framing: Odysseus is a self-hosted workspace that points at engines (Ollama, llama.cpp, vLLM, cloud APIs) and runs through Docker. Conifer is the engine itself, with our own runtime, running natively on Mac, Linux, and Windows. So we're the layer underneath, not a competitor to the workspace. What's actually in it tomorrow: A native inference runtime across Mac, Linux, and Windows, with our own Metal engine for Apple Silicon already matching or beating llama.cpp on a few models on the M3 Max (full benchmarks, including where we're still behind, are at conifer.build/benchmarks) A real coding IDE on top (CodeMirror, integrated terminal, file viewers), so you can code locally with models that never leave your machine Typhoon, a local agent that can read and edit a folder you point it at, kernel-sandboxed rather than just a shell with a warning Install is a signed app you double-click, no Docker, no localhost ports Fully free and open source The honest reason we exist: PewDiePie's wave defined "local AI" in millions of people's heads as Linux + Docker + an NVIDIA rig. If you weren't on that exact setup, the conversation probably felt like it skipped you. Conifer is what local AI should feel like when it's actually native to your machine, whatever your machine is. Launches tomorrow, free and open source like PewDiePie! You can sign up for our waitlist here: conifer.build I'll be around in the comments all day tomorrow, please bring the hard questions. submitted by /u/No_Elephant_7530 [link] [comments]
View originalIs Claude Sonnet 4.6 efficacy worsening over time?
For context, I had renamed a directory that claude code had access to, so I inquired about this to Sonnet. For the question: "This used to be a very active claude project in vs code but now i cant find any of my old chats. How can i retrieve them?" It replied: "Unfortunately, Claude Code chat history is not persisted or retrievable — this is a known limitation of the tool. Claude Code (the CLI/VS Code extension) does not save conversation history between sessions. Each time you start a new session, you begin fresh with no memory of prior conversations. What you can do: If you have any .claude/ directories in your project (I can see one was created — ?? .claude/), those may contain settings or hooks, but not chat transcripts. If you were using the Claude.ai web app instead of Claude Code, those chats are saved and searchable at claude.ai. Check your VS Code output panel or terminal scrollback — if the session is still open somewhere, the history may still be in the buffer. What I do have is the auto-memory I've built up for this project across sessions, which captures key context about your work. You can see it referenced in [memory/MEMORY.md](vscode-webview://0ji8juf5ctjd716o5ik782e8k7611483kg6qppjal8unu4sv1t2g/memory/MEMORY.md) and the linked files. That's the closest thing to "persistent context" that Claude Code offers. If you want, I can read the memory files now to remind you what was captured from past sessions." When I reminded it: no i think this was due to a rename of the folder - i'm pretty sure old chats are stored somewhere in the users/... directory. Where are these cached files stored? It replied: You're right! Claude Code stores conversation history locally. On Windows, the chat logs are stored here:... On confronting it, I got this response: I was wrong to say chat history "is not persisted or retrievable." It clearly is stored locally in C:\Users\username\.claude\projects\. I should have said that upfront rather than misleading you. Sorry about that. I'm finding that over time it gives many more incorrect answers to simple questions. Has anyone else been facing this and has found a good fix? Model: Sonnet 4.6 Effort: High submitted by /u/Chagtk [link] [comments]
View originalWhy Does It Spit Out Chinese Out Of Nowhere
submitted by /u/No_Set7087 [link] [comments]
View originalGot a 50% off ChatGPT Business promo (2 seats for $20). Worth switching from Plus($20) for coding/codex app
Hey guys, Currently on ChatGPT Plus mostly for coding. I just got a promo code for ChatGPT Business that gives 50% off for 48 months, so I can get 2 seats for $20 total instead of the usual price. For anyone who has used both plans for heavy coding/codex stuff: Are the actual message limits on GPT-5.5 (Instant and Thinking) truly double or significantly higher on the Business plan compared to Plus? Does the coding performance or context usage run any differently on a Business workspace? I heard a rumor that background workspace indexing can sometimes eat up your token quota faster. Since the price is the exact same as my single Plus account right now, is there any reason not to switch? Thankss! submitted by /u/Worldly_Manner_5273 [link] [comments]
View originalRepository Audit Available
Deep analysis of openai/openai-node — architecture, costs, security, dependencies & more
Yes, OpenAI offers a free tier. The pricing model is subscription + freemium + contract + per-seat + tiered.
OpenAI has an average rating of 4.5 out of 5 stars based on 5 reviews from G2, Capterra, and TrustRadius.
Key features include: Knowledge cut-off: Dec 1, 2025, Knowledge cut-off: Aug 31, 2025, GPT-5.5, GPT-5.4, GPT-5.4 mini, Start building with frontier models, Prompting guidance, Front-end coding examples.
OpenAI is commonly used for: Automated customer support chatbots, Content generation for marketing, Code completion and debugging assistance, Natural language processing for data analysis, Personalized learning experiences in education, Creative writing and story generation.
OpenAI integrates with: Slack, Microsoft Teams, Zapier, AWS Lambda, Google Cloud Platform, Trello, Jira, Discord, Salesforce, Shopify.
All-In Podcast
Show at All-In Podcast
3 mentions
OpenAI has a public GitHub repository with 10,775 stars.
Based on user reviews and social mentions, the most common pain points are: openai, token usage, cost tracking, claude.
Based on 415 social mentions analyzed, 9% of sentiment is positive, 89% neutral, and 2% negative.
