Hackernews posts about Claude 3.5 Sonnet

RSS feed for Claude 3.5 Sonnet

01
newBreaking changes in third-party APIs are turning into a full-time job
▲ 1stosssik 13d 💬 1
02
newShow HN: Enso Method – agent skills for building software for someone elseensomethod.org
▲ 2dwkerwin 29d discuss
03
newQwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Codingqwenlm.github.io
▲ 23BUFU 729d discuss
04
new"Grok 3's Think mode identifies as Claude 3.5 Sonnetwww.websmithing.com
▲ 22nickfox 533d 💬 13
05
newAsk HN: Claude 3.5 Sonnet vs. o1 vs. for coding. Let's talk!
▲ 9notnotrishi 717d 💬 20
06
newNew Gemini model beats GPT 4o and Claude 3.5 Sonnetlmarena.ai
▲ 8handfuloflight 726d discuss
07
newNuclear fusion with Claude 3.5 Sonnettwitter.com
▲ 5davedx 658d discuss
08
newClaude 3.5 Sonnet Added to Visual Studio Codetwitter.com
▲ 3turrini 683d 💬 1
09
newThe New Claude 3.5 Sonnet, Computer Use, and Building SOTA Agentswww.latent.space
▲ 3swyx 712d discuss
10
newAsk HN: What are you using o1 and "new" Claude 3.5 Sonnet for?
▲ 2dtquad 672d discuss
11
newGemini 2.0 vs. OpenAI o1 vs. Claude 3.5 Sonnet: The game of AI thronescomposio.dev
▲ 2sunilkumardash9 684d discuss
12
newOpenAI O1 vs. Claude 3.5 Sonnet: Which One's Worth Your $20?composio.dev
▲ 2sunilkumardash9 698d discuss
13
newAI Safety Inst.: Pre-Deployment Eval of Anthropic's Upgraded Claude 3.5 Sonnetwww.aisi.gov.uk
▲ 2doomrobo 721d discuss
14
newEQ-Bench 3 Claude-3.5-sonnet Resultseqbench.com
▲ 1dbrans 579d discuss
15
newCursor Is Running a Weaker Version of Claude 3.5 Sonnetwww.vincentschmalbach.com
▲ 1vincent_s 649d discuss
16
newOne Week with Claude 3.5 Sonnet: Surprising Realities of AI Pair Programmingdocspring.com
▲ 1nathan_f77 652d discuss
17
newShow HN: Instantly visualize any codebase as an interactive diagramgitdiagram.com
▲ 222ahmedkhaleel 683d 💬 62
18
newShow HN: Onit – Source-available ChatGPT Desktop with local mode, Claude, Geminigithub.com
▲ 174telenardo 655d 💬 58
19
newShow HN: Personalized Duolingo (kind of) for vocabulary buildinggithub.com
▲ 161arbayi 659d 💬 68
20
newAsk HN: How do you prompt the "advanced" models
▲ 18_jogicodes_644d 💬 12
21
newShow HN: QwQ-32B APIs – o1 like reasoning at 1% the cost
▲ 17ozgune 664d 💬 3
22
newShow HN: Open Responses – Drop-In OpenAI Responses API Alternative for Any LLM
▲ 13ishita159 594d 💬 5
23
newShow HN: A minimalist habit tracker with a wheel-based visualizationgithub.com
▲ 5aldo712 681d 💬 1
24
newAsk HN: Have you hit a context ceiling with an LLM? What did you do about it?
▲ 3jMyles 694d 💬 4
25
newI spent $900 on AI coding agents in 8 weeks
▲ 3nthypes 361d 💬 2
26
newShow HN: EchoCopi Local-first, model-agnostic alternative to Google Antigravity
▲ 3sparksupernova 342d 💬 1
27
newShow HN: CSS Advent Calendar 2024cssadventcalendar.dev
▲ 3steveharrison 709d discuss
28
newShow HN: Query Fast - Lightweight data analytics with AIwww.query-fast.com
▲ 2sverg 672d 💬 6
29
newShow HN: A simple and local project management tool made 100% by Claudecgarduno1garduno.github.io
▲ 2ccccrrriis 653d 💬 3
30
newShow HN: Acting as Claude's Research Helper in AI (Sheaf Cohomology and LLMs)fixmydocuments.com
▲ 2eigenvalue 684d 💬 2
31
newAsk HN: DeepSeek V3's AI Code Review Performance – A Reality Check with Data
▲ 2Jet_Xu 681d 💬 1
32
newShow HN: Corteza – Capture team decisions and makes them searchable with AI
▲ 2ctumani 259d discuss