HNHacker News
TopNewBestAskShowJobs

c0rruptbytes

490 karma · joined May 3, 2017

submissionscomments
c0rruptbytes··on The dead economy theory
https://github.com/OpenCoworkAI/open-cowork

https://www.eigent.ai/

c0rruptbytes··on The dead economy theory
this is also possible with local models, MCP is an open standard

if you already have claude, you can even get it to set it all up for you too

the issue with local models is just the compute required, it's hard to compete with 100t/s cloud models

c0rruptbytes··on Anthropic raises $65B in Series H funding at $965B post-money valuation
yes but Sequoia invested like 200m, we're talking like Google investing 30b...very different scales and bureaucracies
c0rruptbytes··on Anthropic raises $65B in Series H funding at $965B post-money valuation
i would assume investors giving billions of dollars have done their due diligence and not base it off vibes...
c0rruptbytes··on Xiaomi MiMo-v2.5 Series API Permanent Price Reduction Up to 99%
I love ds4, us models are better imo, but like 5% not 500% better, so the valuation doesn't really make sense

that being said, deepseek v4 needs to be on amazon bedrock to actually be feasible in the US Enterprise market and start driving other provider prices down

c0rruptbytes··on Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
been testing forge with ternary bonsai 8b mlx 2bit, pretty sweet even if the model is limited - real potential with this project, good luck!!

  - Broad slice:
      - Full Forge: 48/72 accurate, 72/72 complete, score 66.7%
      - Bare: 18/72 accurate, 24/72 complete, score 25.0%
      - Lift: +30 correct runs, no paired regressions
      - Bare had 42 ToolCallErrors and 6 ToolExecutionErrors; full Forge had none.
  - Advanced reasoning:
      - Full Forge: 3/24 accurate, 24/24 complete, score 12.5%
      - Bare: 3/24 accurate, 9/24 complete, score 12.5%
      - Lift: completion improved, but accuracy did not.
c0rruptbytes··on Launch HN: Chert (YC P26) – Twilio for iMessage
Why use this over Twilio which works pretty hard to make sure you’re compliant (and supports iMessage for business)?
c0rruptbytes··on The Eternal Sloptember
sounds like bad deployment practices - canaries, guardrails, fast rollbacks, ring based promotions, cell based architecture, blah blah etc... humans write bad code too, there should be systems in place to protect it from releasing
c0rruptbytes··on The Eternal Sloptember
ai agents can program, in fact, in our current time with current models, i'd say they program better than most people in the industry (an industry where people were literally copying and pasting from stack overflow for years prior)

being able to program is not the only skill required to be a successful software engineer, so no ai agents cannot be software engineers

very important distinction - i personally like the radiologist example - looking at scans is a part of a radiologist job, AI can do it better than most of them, but looking at scans is a small part of the job, most of it communicating with doctors to help their patients

c0rruptbytes··on Is AI Profitable Yet?
Deepseek is really killing it if that's their total spend
c0rruptbytes··on DeepSeek makes the V4 Pro price discount permanent
I personally really like DS4 Flash - it's the largest I can run locally with decent speeds and I feel like it's good enough to maintain a codebase with less effort
c0rruptbytes··on Googlebook
Do you have a source for this local stuff?

i can kinda see it, they spent a lot of time getting Gemma 4 pretty efficient and then seeing everyone buy macs to run them and realize it’s maybe a real moat since Apple doesn’t make any AI

Would be an interesting product if it could actually give you GPT performance locally, will be an awful experience if it’s essentially just cloud AI…like a premium laptop where most of the features are locked behind a subscription would be wild

c0rruptbytes··on Googlebook
hackernews will tell you the public hates AI and then OpenAI will report like a billion active users
c0rruptbytes··on Agent Skills
i treat it like Minecraft automation - it's just for funsies and to pass the time haha

I don't think agentic workflows are there yet, but implementing skills to manually call and use while working side by side with an AI is definitely nice - our company is focused a lot on sandboxing right now and having safe skills

I don't think we've gotten feature development well yet, but the review skills + grafana skills they wrote have been pretty solid

c0rruptbytes··on Zig → Rust porting guide
i mean AI docs are usually the result of collabs between users and AI using /plan

with superpowers, i see a lot of specs -> impl plan -> execute plan

c0rruptbytes··on AI uses less water than the public thinks
i believe it was like amount of water gold uses in the USA alone is 10x more than water used by AI globally
c0rruptbytes··on Show HN: Rapid-MLX – Run local LLMs on Mac, 2-3x faster than alternatives
i use this, big fan - i have unlimited codex tokens if you ever need some dev assistance

Would definitely love benchmarks against omlx and fast-mlx one day (i also have a 256gb m3 ultra)

c0rruptbytes··on I bought Friendster for $30k – Here's what I'm doing with it
i understand the intent, but selena is still extremely popular, especially amongst women...maybe a bad example
c0rruptbytes··on I am building a cloud
it's always a skill issue when it comes to people complaining with k8s

knowing when and when not to use k8s, is also a skill

c0rruptbytes··on GPT-5.5
literally cannot launch the codex app anymore
c0rruptbytes··on The dangers of California's legislation to censor 3D printing
Guns are legal, in fact building your own gun, may be the most legal thing in the history of the 2A - there's an enormous amount of "historical" context to back this

It's such a waste of time and resources - you wanna handle gun violence? handle normal violence with proven mechanisms (education, social welfare, etc...)

c0rruptbytes··on As Computer Coding Classes Swell, So Does Cheating
anyone who relies on cheating never seems to do well during the harder major courses at my school (Texas). A lot of the professors have really rigorous cheating detections, and will make you explain every line of code in person if they suspect something. (At least in honor classes) Also, I don't know what these people expect when they have to do a technical interview?
c0rruptbytes··on Q – Initiative to build commercially available universal quantum computers
you could factor an 8 bit number really fast heh
← PreviousPage 4 of 4