nowfound

AI · alternatives · 2026

24 alternatives to Jev vs. GPT-5.6 and Claude Haiku at Pong

Jev returns a decision in 227 ms. The chat models take 2.5 to 3.5 seconds. Pong where the ball moves one step per model decision. Slow model, slow ball.

Jev vs. GPT-5.6 and Claude Haiku at Pong is a comparison tool that plays the classic Atari game simultaneously with different AI models. Each model controls a paddle in its own lane, and the ball moves one step per… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.

  1. 1
    Jev▲544

    Fast, structured AI decisions for software automation

    Sep 2026 · console.typesafe.ai · its alternatives →

  2. 2

    Six AI decision models played Pac-Man in real time against the classic arcade ghosts. See the leaderboard, watch their games, or play against them.

    Oct 2026 · opper.ai · its alternatives →

  3. 3

    LLM-generated real-time commentary for Pong. Contribute to pncnmnp/xpong development by creating an account on GitHub.

    2025 · github.com · its alternatives →

  4. 4

    Have a natural, spoken conversation with AI! Contribute to KoljaB/RealtimeVoiceChat development by creating an account on GitHub.

    2025 · github.com · its alternatives →

  5. 5

    Fast and efficient models optimized for coding and subagents

    Mar 2026 · openai.com · its alternatives →

  6. 6

    September 2026. Every number here is from the benchmarks, and bash experiments/bench.sh --no-record reruns them without an API key.

    Sep 2026 · jevstiller.pages.dev · its alternatives →

  7. 7

    Watch the AI decision model Jev play Pokémon Red in its entirety, live.

    Sep 2026 · jev-pokemon.vercel.app · its alternatives →

  8. 8

    Tighter instruction adherence in speech agents

    Feb 2026 · developers.openai.com · its alternatives →

  9. 9

    How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations…

    Dec 2025 · github.com · its alternatives →

  10. 10

    A visual quiz for people and models: race Jev, TypeSafe

    29d ago · jevcards.com · its alternatives →

  11. 11

    Explore large language models in 512MB of RAM. Contribute to jncraton/languagemodels development by creating an account on GitHub.

    2023 · github.com · its alternatives →

  12. 12

    Last year when GPT-4 was released I started making lots of little voice + LLM experiments. Voice interfaces are fun; there are several interesting new problem spaces to explore. I'm convinced that voice is going to be a bigger and bigger part of how we all interact with generative AI. But one thing that's hard, today, is building voice bots that respond as quickly as humans do in conversation. A 500ms voice-to-voice response time is just barely possible with today's AI models. You can get down to 500ms if you: host transcription, LLM inference, and voice generation all together in one place;…

    2024 · fastvoiceagent.cerebrium.ai · its alternatives →

  13. 13
    V-JEPA 2▲198

    Meta's world model for physical world understanding

    2025 · ai.meta.com · its alternatives →

  14. 14

    I'm Vivek, co-founder/CEO of HackerRank (YC S11); You may know us as a hiring tool for developers/companies. Over the years, we have built up deep expertise in generating programming challenges, and we are now using that to make coding models better. Our first launch is Model Kombat -- an arena where you can directly compare anonymized coding models, side by side, on real problems. * Pick an arena (Java, Python, etc.) * Each battle has 3 rounds: see the problem + two model outputs -> vote on which you’d actually prefer * Leaderboards + problem statements are updated weekly. We…

    2025 · astra.hackerrank.com · its alternatives →

  15. 15

    Agent evals and guardrails in one request. Built on Jev, Kev and Laya. - openlayer-ai/jevals

    Sep 2026 · github.com · its alternatives →

  16. 16CV
  17. 17TT

    Simulate anything on a map from a text prompt -- and conduct risk analysis against LiveUA map's global realtime data points from social media and news sources. I trained a GPT-2-size model on historical incident data used to predict things that will go wrong. As historian Benjamin Breen mentions, the leading language models are good historians, so the application will simulate historical events pretty well also. I include a Multi-Agent RL Urban Mobility model in progress displayed on the map as small white cubes representing traffic and pedestrians. Around SF, it uses real census data and…

    2025 · mused.com · its alternatives →

  18. 18

    The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.

    Mar 2026 · github.com · its alternatives →

  19. 19

    TLDR: We created a personalised Andrej Karpathy tutor that can response to questions about his Youtube videos in sub 1 second responses (voice-to-voice). We do this using a voice enabled RAG agent. See later in the post for demo link, Github Repo and blog write up. A few weeks ago we released the worlds fastest voice bot, achieving 500ms voice-to-voice response times, including a 200ms delay waiting for a user to stop speaking. After reaching the front page of HN, we thought about how we could take this a step further based on feedback we were getting from the community. Many companies were…

    2024 · educationbot.cerebrium.ai · its alternatives →

  20. 20

    Faster speech off signals for spec gen voice pipelines - KoljaB/RealtimeVAD

    6d ago · github.com · its alternatives →

  21. 21IM

    Also inspired by this HN submission: https://www.chiark.greenend.org.uk/~sgtatham/quasiblog/findl... The model is gpt-4o-mini-2024-07-18.

    2024 · app4.hc11.org · its alternatives →

  22. 22

    Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence. - pochenai/nano-llm-posttraining

    Aug 2026 · github.com · its alternatives →

  23. 23

    Centralized AI workspaces for any LLM. Secure and private. Save your team hours per week.

    2023 · adventure.typingcloud.com · its alternatives →

  24. 24

    HAI 1.0: 1.2GB local AI. Beats GPT-5 at coding

    Jul 2026 · github.com · its alternatives →

Also compare

Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →