News for hackers. Stuff that matters.

makeavish

makeavish on Hacker News

Re:GPT-6 Sol and Luna on Wednesday September 23, 2026 @06:38AM (#49814034)
Don’t think in zero sum terms. OpenAI can’t burn money infinitely, efficient models are better for everyone
Re:Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max) on Tuesday September 22, 2026 @01:31PM (#49805027)
Nice catch, AA only shows max effort by default and I got disappointed thinking it's a token guzzler though: https://artificialanalysis.ai/models/claude-opus-5-5?models=...

Not sure about how adaptive reasoning works though as they mention adaptive reasoning for every reasoning level

Re:Claude Status – Elevated errors for multiple models on Tuesday September 22, 2026 @01:23PM (#49804871)
I follow Leo for the rumors, he has been pretty accurate but again they are rumors so nothing is guaranteed. I don't know his sources. https://x.com/synthwavedd
Re:Claude Status – Elevated errors for multiple models on Monday September 21, 2026 @09:14PM (#49795648)
There are rumors of Opus 5.5 launching on Tuesday so maybe it due to that? Previously as well there have been incidents just before launch.
Re:Manus will return to operating as an independent company on Tuesday August 11, 2026 @11:44AM (#49260105)
No it’s Chinese state who is preventing founders from leaving China https://www.cnbc.com/amp/2026/06/12/meta-reportedly-begins-d...
Re:HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 7... on Monday June 29, 2026 @02:01PM (#48722774)
True, I have found it to be valid as well
Re:HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 7... on Monday June 29, 2026 @07:51AM (#48718046)
True :(
Re:HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 7... on Monday June 29, 2026 @05:49AM (#48717055)
I have been at both side of the market. And it sucks so bad at both ends. Companies which deeply care about next hire are struggling to hire and actual great people looking out are outcompeted by AI slop and AI bulk applying.

It is actually a very hard to solve problem.

Re:HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 7... on Monday June 29, 2026 @01:41AM (#48715271)
Hiring and job search has been so hard and AI has amplified the existing problems instead of solving any.
Re:Claude Agent SDK vs. Messages API for a Production AI Assistant? on Friday April 10, 2026 @12:55AM (#47713793)
Claude launched Managed Agents which fulfills our usecase! https://platform.claude.com/docs/en/managed-agents/overview
Re:Claude Agent SDK vs. Messages API for a Production AI Assistant? on Tuesday April 07, 2026 @10:43PM (#47684347)
Interesting, let me check it out

Claude Agent SDK vs. Messages API for a Production AI Assistant?

Posted by makeavish on Monday April 06, 2026 @10:14PM
from the self-post dept.

We're building a chat assistant into our B2B developer tool. It needs to call domain-specific tools (MCP), stream responses (SSE), and persist conversation history.The Claude Agent SDK looks like it would save us a lot of work — agent loop, compaction, hooks, session management all built in. But the more we look at it, the more the architecture feels oriented toward single-user CLI use. The...

( Read More... | 3 comments | 2 points | on HN )
Re:Gemini 3.1 Pro on Thursday February 19, 2026 @12:12PM (#47076190)
Yeah maybe that but atleast let us know about this Or have dynamic limits? Nerfing breaks trust. Though I am not sure if they actually nerf it intentionally. Haven't heard from any credible source. I did experience in my workflow though.
Re:Gemini 3.1 Pro Preview on Thursday February 19, 2026 @12:09PM (#47076157)
I don't use AI studio for my work. I used Antigravity/Gemini CLI and 3 pro was great for few weeks and now it's worse than 3 flash or any smaller model from competitor which are rated lower on benchmarks
Re:Gemini 3.1 Pro Preview on Thursday February 19, 2026 @11:44AM (#47075757)
Looks great!
Re:Gemini 3.1 Pro on Thursday February 19, 2026 @11:42AM (#47075725)
Great model until it gets nerfed. I wish they had a higher paid tier to use non nerfed model.
Re:Gemini 3.1 Pro Preview on Thursday February 19, 2026 @11:39AM (#47075689)
I hope to have great next two weeks before it gets nerfed.
Re:Google Antigravity on Tuesday November 18, 2025 @03:35PM (#45971667)
Tried Antigravity for 2 queries and my model quota limit breached. Model definitely felt better than GPT 5.1 (my current daily driver). I am continuing to use Gemini 3 Pro on Cursor to evaluate further.
Re:Cloudflare Global Network experiencing issues on Tuesday November 18, 2025 @08:35AM (#45965676)
NPM also seems to be down due to this! https://status.npmjs.org
Re:OpenTelemetry: Escape Hatch from the Observability Cartel on Friday November 07, 2025 @10:47PM (#45853967)
It’s a full fledged tool like DataDog which is opensource and can be selfhosted. You can replace honeycomb with it. What features do you think it’s missing compared to honeycomb?
Re:Are LLMs being "nerfed"? A crowdsourced vibe check on AI models on Friday October 24, 2025 @02:42AM (#45691590)
Discovered this while I was researching about why some LLM models perform significantly worse at times. I have experienced this more with Claude.
Re:Airbnb CEO says ChatGPT isn't ready on Wednesday October 22, 2025 @01:44AM (#45665277)
“We’re relying a lot on Alibaba’s Qwen model. It’s very good. It’s also fast and cheap,” he said.
Re:Attention Is a Luxury Good on Sunday October 19, 2025 @11:28AM (#45634899)
It’s possible with this extension: https://chromewebstore.google.com/detail/unhook-remove-youtu...

I use it on firefox

Older »