HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Applied_AI

2 karmajoined 3 mesi fa
Working on LLM-based systems and agent architectures at deepsense.ai.

Submissions

[untitled]

1 points·by Applied_AI·ieri·0 comments

[untitled]

1 points·by Applied_AI·3 giorni fa·0 comments

Why is Sonnet 5 Max priced above models that outperform it?

cursor.com
2 points·by Applied_AI·4 giorni fa·1 comments

[untitled]

1 points·by Applied_AI·8 giorni fa·0 comments

[untitled]

1 points·by Applied_AI·15 giorni fa·0 comments

Can LLMs be trusted as EDA analysts? Read our paper

arxiv.org
2 points·by Applied_AI·24 giorni fa·0 comments

[untitled]

1 points·by Applied_AI·mese scorso·0 comments

Interesting Details from Microsoft's MAI-Thinking-1 Technical Report [pdf]

microsoft.ai
2 points·by Applied_AI·mese scorso·0 comments

Engineers building MCPs in regulated industries: what's been the hardest part?

deepsense.ai
1 points·by Applied_AI·mese scorso·1 comments

Spectrograms vs. MFCCs: Practical Tradeoffs in Audio ML [video]

youtube.com
2 points·by Applied_AI·mese scorso·0 comments

[untitled]

1 points·by Applied_AI·mese scorso·0 comments

[untitled]

1 points·by Applied_AI·2 mesi fa·0 comments

[untitled]

1 points·by Applied_AI·2 mesi fa·0 comments

What breaks when AI-generated code reaches production systems

deepsense.ai
2 points·by Applied_AI·2 mesi fa·0 comments

Lessons from testing GPT and Gemini native audio models for voice agents

deepsense.ai
1 points·by Applied_AI·2 mesi fa·1 comments

Lessons from early access to OpenAI's agent execution layer

deepsense.ai
1 points·by Applied_AI·2 mesi fa·0 comments

Structured planning, execution, and memory for LLM agents (ragbits 1.6)

deepsense.ai
2 points·by Applied_AI·3 mesi fa·0 comments

comments

Applied_AI
·4 giorni fa·discuss
Sonnet 5 Max performs worse than Opus 4.8 High and Fable 5 Low and yet costs more to do a task.

The comparison is even more absurd between Sonnet 5 Max vs Composer 2.5 - they perform similarly, yet Composer is... 15x cheaper.

One might argue it's Cursor's benchmark, so it might be biased, but then again, even GPT-5.5 Very High performs better and it's almost 2x cheaper.
Applied_AI
·15 giorni fa·discuss
[flagged]
Applied_AI
·24 giorni fa·discuss
[dead]
Applied_AI
·mese scorso·discuss
[dead]
Applied_AI
·mese scorso·discuss
[flagged]
Applied_AI
·mese scorso·discuss
[dead]
Applied_AI
·mese scorso·discuss
[flagged]
Applied_AI
·mese scorso·discuss
If you follow PC hardware, this is one of the more interesting long-form videos released recently.

GamersNexus interviewed multiple major hardware companies about the current state of the industry, market pressures, margins, consumer trends, and where things seem to be heading. Surprisingly candid throughout.
Applied_AI
·2 mesi fa·discuss
[flagged]
Applied_AI
·2 mesi fa·discuss
[flagged]
Applied_AI
·2 mesi fa·discuss
[dead]
Applied_AI
·3 mesi fa·discuss
[dead]