Viewing profile — bicepjai
bicepjai
HN member- Joined
- Tue, Apr 22, 2014, 7:33 PM UTC
- HN karma
- 574
- Public activity
- 462 items
- HN profile
- View on Hacker News ↗
About bicepjai
https://bicepjai.com
Recent public activity
-
comment
Comment #49211516
So you would trust a known writers word over non deterministic software ? I read New Orleans will soon let AI handle 911 calls, Hope the AI believes the calls are from humans :)
-
comment
Comment #49206598
As a society, we have organized ourselves in a form where the marketers get the most cut than the producers of goods and services. It’s unfortunate and amendable with capable leade…
-
comment
Comment #49205407
What can go wrong ? I hope sometimes people would stop and think the implications or at-least debate about it. If someone says “what makes you think it was not debated?” Then I wou…
-
comment
Comment #49198358
Looks beautiful and great presentation of your efforts. Hope it lives up to its expectations. All the best
-
comment
Comment #49164038
I keep cussing at it saying “don’t give me a wall of text ...” it just like eating tokens. It’s trained to eat tokens for anything. No matter what workarounds you use, claude.md/me…
-
comment
Comment #49157303
Free “Curious Karpathy Ads Service” for Anthropic :)
-
comment
Comment #49123969
It was suppose to be “can”, mis-typed
-
comment
Comment #49123933
These are some disturbing images. Are we suppose to not trust the skies anymore ? They are asking who is responsible, how is that a fair question and why is it not obvious ?
- story
-
comment
Comment #49118044
6 months ago, it was all about security and how our models are the most secure ones. Now they make models’ misbehavior an advertisement. So now companies are incentivized to have a…
-
comment
Comment #49084901
I was so skeptical of this feature, now I cannot live without this.
-
comment
Comment #49049052
So are we at a point where we can’t train llms for fun at home on less expensive AMD cards ?
-
comment
Comment #49030584
So basically the argument is we have taken too much debt to afford failure, we might bring down the economy of top 1% so ban Chinese models :)
-
comment
Comment #49029282
So there are 3 points and I cannot connect the dots on why 93 employees loosing job helps them other than AI replacing them :) subjective opinion: just calling humans creative and …
-
comment
Comment #48999094
My high level methodology: Claude code fable for planning and execution. Codex sol for review. My constraint for one task convergence is codex saying no issues found on 3 consecuti…
-
comment
Comment #48982435
I thought it was an “Aha” moment :)
-
comment
Comment #48973266
Hahaha. Attention span is in characters now. It’s just funny, thanks for sharing.
-
comment
Comment #48929814
More ways to not look at the code written. Where are we trying to go ?
-
comment
Comment #48914531
I like how you found the pattern of 3 loops. I am working on a similar blog where I had human loop outside the inference loop :) human -> llm-> tool
-
comment
Comment #48914441
Trying to understand, So you downvote the post because of AI comments in HN ?
-
comment
Comment #48914167
Nowadays, I literally don’t get any output from Claude cod to check what is happening and it’s infuriating. I have to keep interrogating to get a sense of what is happening. This i…
-
comment
Comment #48819275
Totally different topic. What is xcancel ?
-
comment
Comment #48775390
[dead]
-
comment
Comment #48763656
Try superset, it does that
-
comment
Comment #48762289
As someone who works across software, hardware, and deep learning, this project makes me happy. My $1000+ vacuum will happily get stuck on the cloth mat, eat all our lego, and it h…