Viewing profile — pmxi
pmxi
HN member- Joined
- Sun, Jan 26, 2025, 6:52 AM UTC
- HN karma
- 140
- Public activity
- 42 items
- HN profile
- View on Hacker News ↗
About pmxi
No profile information was provided.
Recent public activity
-
comment
Comment #49238654
This test would be passed by a Waymo with ChatGPT.
- story
-
comment
Comment #49124410
I have updated OpenAI's chart[1] from yesterday to include one more datapoint: DeepSeek V4 Flash 0731. It's on the frontier. https://files.parasmittal.com/openai_aa_luna_dsflash.sv…
-
comment
Comment #49098973
That’s cool. I knew o1 hid it since launch, so I assumed Anthropic would also have never shown it.
-
comment
Comment #49076913
The agent loop doesn’t run in the browser.
-
comment
Comment #49070984
That's a summarized and filtered view of the actual reasoning. OpenAI and Anthropic guard the real reasoning closely. Users have never been able to see it and the API returns an en…
-
comment
Comment #49070762
Clearly you do, given you expressly maintain that China includes Taiwan (an uncommon opinion)?
-
comment
Comment #48966042
The key claim here is, paraphrased: “LLM coding assistants” cannot “help someone write code better or faster.” This is not true.
-
comment
Comment #48852338
This is expected behavior; the Codex app has been rebranded as the ChatGPT app.
-
comment
Comment #48735343
This catches Claude resellers. Meaning companies who proxy Claude traffic for users in, say, China. https://www.chinatalk.media/p/how-to-buy-cheap-claude-tokens...
-
comment
Comment #48646449
This has been a niche where Mistral has actually been successful. Btw, Hindi and Japanese are bucketed in "Rare Languages," which is odd.
-
comment
Comment #48533232
PG acknowledged that growth is limited by market size. Markets to support "avogadrillionaire" level wealth may not current exist. However, there obviously exist markets to support …
-
comment
Comment #48467475
I had Claude straighten it out: Model In Out BIn BOut Haiku 4.5 $ 1.00 $ 5.00 $0.50 $ 2.50 Sonnet 4.6 $ 3.00 $15.00 $1.50 $ 7.50 Opus 4.7 $ 5.00 $25.00 $2.50 $12.50 Opus 4.8 $ 5.00…
-
comment
Comment #48454062
It’s near the frontier meaning it’s the best intelligence for the price. It’s not even close to frontier meaning it’s the best intelligence.
- comment
-
comment
Comment #48384526
This will load the PR easily: https://diffshub.com/oven-sh/bun/pull/30412
-
comment
Comment #48326523
The first part, describes a decision to ask AI over calling a good friend and domain expert. Typically the domain expert is not an option. (looking at my last 10 Claude chats, I kn…
-
comment
Comment #48312235
Yeah. They are aware: "Users will find Opus 4.8 to be a modest but tangible improvement on its predecessor."
-
comment
Comment #48312186
In the "What's next?" section, "There’s still more to be done: we’re working on developing and releasing models that provide many of the same capabilities as Opus at a lower cost."…
-
comment
Comment #47783743
I wanted to ask someone about the firepass subscription. It implies unlimited usage - sounds too good to be true. Is it? Can you leave your agent running all day?
-
comment
Comment #47776744
These CLIs are for AI agents. If I have a CLI to WhatsApp, then I can direct an agent (such as OpenClaw) to manage my messages for me.
-
comment
Comment #47580430
I didn't like them either. Thankfully, they can easily be disabled. See my config: https://github.com/pmxi/dotfiles/blob/e779c5921fbe308fad0c95...
-
comment
Comment #45499610
You can select models on Perplexity. He used Sonnet 4.5 Thinking
-
comment
Comment #45321195
This may be interesting to you "Vibe code is legacy code (val.town)" https://news.ycombinator.com/item?id=44739556
-
comment
Comment #45186355
Fortunately, the GitHub README opens with a list of links to install ublock Origin. https://github.com/gorhill/uBlock?tab=readme-ov-file#ublock-...