◈Bluesky50
XX / Twitter50
YHacker News49
listening to
Cline
149
mentions
tracked
tracked
net sentiment
+24%
43 positive
99 neutral
7 negative
volume & sentiment over time
Jul 12 – Sep 26, 2026 · 2-day buckets
sources
most discussed
code
active days
30
what people keep raising
- code 23
- devin / anal 15
- claude / codex 9
- opencode / qwen 6
- model / open 5
- coding / plan 3
mentions
Showing 1–25 of 49 mentions
-
Y Hacker News 6d neutral codePlan mode is dead> It’s something I came up with late on a Sunday night many months ago Aider, Cline and many other agents had plan mode before Claude Code existed. > It’s something I came up with late on a Sunday night many months ago Aider, Cline and many other agents had plan mode before Claude Code existed.view source ↗
-
Y Hacker News 1w positive coding / planAI coding has made CI a bottleneck, so we reworked ours to keep upAh yes "How committees invent" is a great paper that I often think about. The role of software in reproducing organizational designs is a fascinating topic. When organizations adopt ERP, or Office, or buy into the Salesforce ecosystem, or use Jira, they are also adopting organizational designs. I think this plays a sim… Ah yes "How committees invent" is a great paper that I often think about. The role of software in reproducing organizational designs is a fascinating topic. When organizations adopt ERP, or Office, or buy into the Salesforce ecosystem, or use Jira, they are also adopting organizational designs. I think this plays a similar role to consultancy. By adopting software, organizations are implicitly learning about common practices and internalizing industry knowledge. As for the adoption of LLM-centered workflows, I suspect that the end goal is not having a great new product that does everything better as is often claimed. I think the end game is making organizations dependent on the vendor. That might backfire depending on how the ecosystem evolves in terms of subscriptions to "frontier" vs open-weight models running locally. I am watching keenly. I think there is a lot to be said in expanding Conway's analysis, and there is a lot of literature on related topics using terms such as "socio-technical systems" and some other venues in organization science that have a similar approach by other names. I think Giddens' ideas on structuration in sociology could be of interest to you. Anthropology, archaeology, and ancient history all have some great texts on the development of complexity over time, how it grows and how it collapses and why. In fact the first reference to Giddens' work I read in a fascinating little book about the development of complexity in Ancient Greece via practices of feasting, by Small. Also of course the work of Cline on the Late Bronze Age collapse, and Tainter on social complexity growth and collapse more generally, are fascinating. I do tend to be fascinated by the study of the distant past but if you look up Giddens you can probably find books and adjacent writers that might help you reflect on Conway's article.view source ↗
-
Y Hacker News 1w positive codeAX – Google’s Open Agentic OrchestratorI have been happy with Google's Antigravity harness and Jules so looking forward to playing with this. Thanks for sharing. Simultaneously I am looking to also revisit local offline models. While I feel like I have a decent understanding of the model landscape I'm feeling a bit lost at which agentic harness to leverage … I have been happy with Google's Antigravity harness and Jules so looking forward to playing with this. Thanks for sharing. Simultaneously I am looking to also revisit local offline models. While I feel like I have a decent understanding of the model landscape I'm feeling a bit lost at which agentic harness to leverage for local models. Hermes, Cline, Aider, Qwen Code, Goose, Pi, OpenCode, something else? I live in the terminal so Desktop UX is a bonus but not a must have. Can I modify the antigravity settings/program to point to a local model? Where should I spend my energy?view source ↗
-
Y Hacker News 2w ▲ 2 neutral codeAsk HN: What's the most economical approach to the most tokens?I'm doing web developement, and game development for a hobby project. I've tried lots of harnesses / IDE's - Best I've found is VSCodium.+ Cline + Openrouter, using discounted models (GLM 5.3 Flash is 50% off atm for example) I used Cursor for the last year - it's been decent. But I'm unhappy with the direction their g… I'm doing web developement, and game development for a hobby project. I've tried lots of harnesses / IDE's - Best I've found is VSCodium.+ Cline + Openrouter, using discounted models (GLM 5.3 Flash is 50% off atm for example) I used Cursor for the last year - it's been decent. But I'm unhappy with the direction their going (it's largely just Grok Code at this stage...) Nobody advertises token limits - so it's pretty hard to compare, if you've used multiple tools in the last couple of months - what's your experience been? Will I be able to beat my Openrouter setup on cost per token via a useful model by subscribing to one of these? In my opinion - Grok 4.6 seems comperable with GLM 5.3 Flash. Deepseek 4.1 is my daily driver. I use Sol or Fable for hard problems - but it's expensive man... Please share your opinions.view source ↗
-
Y Hacker News 2w ▲ 5 positive codeShow HN: Slowave – local adaptive memory for coding agentsI started building Slowave because I kept running into the same problem with coding agents: every new session has the codebase and some documentation but not the context behind it, decisions that brought you there and especially the thinking process behind the code. Most memory system solutions focus primarily on the s… I started building Slowave because I kept running into the same problem with coding agents: every new session has the codebase and some documentation but not the context behind it, decisions that brought you there and especially the thinking process behind the code. Most memory system solutions focus primarily on the storage and retrieval aspects (vector search/RAG/graphs/ Markdown files, etc.). After months of storing memories (coding 8+ hours a day produces a lot of memories) these might hallucinate your reasoning model and they can clutter your context window. To treat semantic relationship, such as contradiction, supersession, etc, most systems added an extra LLM layer that summarize memories and continuously evaluate their semantic relevance. That comes with a non-negligible cost and introduces a split-brain system, where a second model is making decisions about memory independently of the agent actually using it. I started looking up into how human brain works, and the first thing striking me was that retrieval is just a part of the whole memory problem. Brain memories are a constant flow of information where what matters gets reinforced, what doesn't decays over time. What really matters for an efficient memory system is to retrieve memories that actually help (a human or an agent) to achieve its current task or goal given the current context. Everything else should be treated as noise. Slowave is my attempt to approach this problem differently: It instructs your coding agent to participate in maintaining its own memory. Each task becomes a feedback loop between your agent and the memory layer: remember -> recall -> use -> feedback -> reinforce / weaken -> decay Your agent tells Slowave whether retrieved memories were useful, irrelevant or stale. Slowave uses that signal to adapt those memories salience. Retrieval works upon this continuous loop of feedback, reinforcement or decay. This means Slowave doesn't need a separate LLM or LLM judge for memory maintenview source ↗
-
Y Hacker News 3w neutral opencode / qwenSo you want to use OpenRouter?If you only care about open source models, cline and opencode provide usage based access and subscriptions for general API access If you only care about open source models, cline and opencode provide usage based access and subscriptions for general API accessview source ↗
-
Y Hacker News 3w positiveWe have a year to fix security everywhereIt is and it isn't. Why are you comparing the m5max instead of the m4ultra? The big deal to me is the number of compute cores for prefill tps, which is suppose to be 4x faster on the m5ultra. It's my opinion that the m5 ultra is going to be a really big deal in terms of local AI accessibility. Flash sized models (~200-… It is and it isn't. Why are you comparing the m5max instead of the m4ultra? The big deal to me is the number of compute cores for prefill tps, which is suppose to be 4x faster on the m5ultra. It's my opinion that the m5 ultra is going to be a really big deal in terms of local AI accessibility. Flash sized models (~200-300b params) are going to be reasonably fast as long as you aren't throwing 40k context at it on each or the first request (ie, agentic harnesses). Even agentic harnesses like Cline should move at a reasonable clip on m5 ultra. I suppose we will know sooner than later. FYSA: Former m4 ultra 512GB owner and current 4x rtx6000 owner here. I upgraded because I needed more prompt processing speed and concurrency.view source ↗
-
Y Hacker News 4w negative claude / codexWhich tools do Claude, Codex and Cursor choose? We measured 17k runs to find outThey said as of aug 23rd it's 100% rollout. I've noticed 0 improvement. If anything a downgrade. The agents often refuse to use the tools after 1 try because the results are so trash. An open ticket that shows my biggest gripe with the write tool https://github.com/cline/cline/issues/13276 I guess the mistake count is … They said as of aug 23rd it's 100% rollout. I've noticed 0 improvement. If anything a downgrade. The agents often refuse to use the tools after 1 try because the results are so trash. An open ticket that shows my biggest gripe with the write tool https://github.com/cline/cline/issues/13276 I guess the mistake count is down though. But that's because it's bypassing all the tools and just running commandsview source ↗
-
Y Hacker News 4w positive claude / codexWhich tools do Claude, Codex and Cursor choose? We measured 17k runs to find outCline just recently fully upgraded their harness, see here: https://x.com/cline/status/2095897914493243512?s=20 Try if you have a better experience now! Cline just recently fully upgraded their harness, see here: https://x.com/cline/status/2095897914493243512?s=20 Try if you have a better experience now!view source ↗
-
Y Hacker News 4w negative claude / codexWhich tools do Claude, Codex and Cursor choose? We measured 17k runs to find outBecause they're thinking like I did going into the article. Harnesses like Claude expose "tools" to the agent. I usually use Cline but I'm giving up on it for this exact reason. Cline tells the model "you tell me to write a file, I'll get it done" and then it messes everything up, causes tones of errors, and the model … Because they're thinking like I did going into the article. Harnesses like Claude expose "tools" to the agent. I usually use Cline but I'm giving up on it for this exact reason. Cline tells the model "you tell me to write a file, I'll get it done" and then it messes everything up, causes tones of errors, and the model goes "wow that's a broken tool. I'm going to write a python script to write the file instead"view source ↗
-
Y Hacker News 4w neutral claude / codexAsk HN: Why were OpenAI, Claude, and Grok simultaneously down?Also from Cline: After 1177 B.C.: The Survival of Civilizations (2024), ISBN 978-0691192130 Also from Cline: After 1177 B.C.: The Survival of Civilizations (2024), ISBN 978-0691192130view source ↗
-
Y Hacker News 4w positive claude / codexAsk HN: Why were OpenAI, Claude, and Grok simultaneously down?1177 B.C.: The Year Civilization Collapsed by Eric H. Cline is great and is exactly on this topic. 1177 B.C.: The Year Civilization Collapsed by Eric H. Cline is great and is exactly on this topic.view source ↗
-
Y Hacker News 4w positive codeMuse Spark 1.3Cline experiment: https://x.com/cline/status/2085237843379519737 Muse code: https://developer.meta.com/ai/resources/blog/build-with-muse... > Co-trained with the harness. Muse Code was in the training loop from day one, so tool calls succeed and plans execute cleanly. Crucially, we trained across multiple harnesses, so… Cline experiment: https://x.com/cline/status/2085237843379519737 Muse code: https://developer.meta.com/ai/resources/blog/build-with-muse... > Co-trained with the harness. Muse Code was in the training loop from day one, so tool calls succeed and plans execute cleanly. Crucially, we trained across multiple harnesses, so while the model is at its best in Muse Code, it still generalizes to other coding agents you already use.view source ↗
-
Y Hacker News 4w neutralMuse Spark 1.3You should use their harness. They trained it on multiple harnesses but have specifically optimized it for their harness. Cline also did an independent experiment w spark 1.2 where using the native harness makes it use fewer tokens / turns to accomplish tasks You should use their harness. They trained it on multiple harnesses but have specifically optimized it for their harness. Cline also did an independent experiment w spark 1.2 where using the native harness makes it use fewer tokens / turns to accomplish tasksview source ↗
-
Y Hacker News 4w ▲ 1 positiveLongCat-2.0 is now free to try in clineview source ↗
-
Y Hacker News 4w positive codeAsk HN: Who wants to be hired? (September 2026)I’ve been researching how LLMs generate code since summer 2023. My main public artifact is this repository: https://github.com/danvoronov/CodeWithLLM-Updates It’s a living research collection with 400+ commits covering practical experiments, usage patterns, step-by-step guides, model comparisons, AI coding tool evaluat… I’ve been researching how LLMs generate code since summer 2023. My main public artifact is this repository: https://github.com/danvoronov/CodeWithLLM-Updates It’s a living research collection with 400+ commits covering practical experiments, usage patterns, step-by-step guides, model comparisons, AI coding tool evaluations (Cursor, Aider, Cline, Windsurf, etc.). A large part of my work is *exploratory*: navigating large and messy information spaces, testing things hands-on, comparing different approaches, and identifying the small amount of signal that is actually useful. My strongest skill is broad technical *investigation*. I can map an entire problem space rather than focus on a single tool, model, or hypothesis: find the relevant projects, papers, tools, workflows, discussions, benchmarks, and practical examples; test and compare what matters; and organize the results into a clear picture of the field. The goal is not to arrive with a predetermined answer or recommend one particular tool. I can cover the *surrounding landscape* as thoroughly as possible and provide the evidence, comparisons, and structure. Your team can then decide which conclusions matter and what to do with them. I can deliver the results as a structured PDF or HTML research artifact, or discuss the findings in a call. Depending on the project, I can also combine both formats: prepare a written report with the relevant evidence and comparisons, then walk your team through it and answer questions live. I’m interested in projects where someone needs a broad, hands-on investigation of AI-assisted software development: understanding what exists, how different approaches compare, where they work, where they fail, and what is worth paying attention to. I don’t know the conventional job title for this niche. If your team needs someone who can cover a large and changing technical field, turn scattered information into a structured overview, and give you a solid basis for making decisions, I’d be interview source ↗
-
Y Hacker News 4w positive codeMy local model setup on an M4 Pro Mac MiniRecent performance data on my M1 Max 32GB MacBook using oMLX. I have been working on identifying suitable model and config for my use case and system. Using a refactor and suggest improvements prompt for a specific Django code block using VSCode Cline extension. --- Qwen3.8-27B-4bit, Prompt Processing (PP) 66.3 tok/s, … Recent performance data on my M1 Max 32GB MacBook using oMLX. I have been working on identifying suitable model and config for my use case and system. Using a refactor and suggest improvements prompt for a specific Django code block using VSCode Cline extension. --- Qwen3.8-27B-4bit, Prompt Processing (PP) 66.3 tok/s, Token Generation (TG) 11.8 tok/s Ornith-1.5-35B-A3B-MLX-4bit, PP 379.7, TG 45.8 Ornith-1.5-35B-A3B-MLX-4bit, PP 381.5, TG 46.4 Qwen3.6-35B-A3B-mxfp4, PP 389.6, TG 47.6 Qwen3.6-35B-A3B-OptiQ-4bit, PP 342.6, TG 44.4 --- Qwen3.8-27B-4bit generally runs out of output token before completing the task though excellent partial results. Ornith-1.5-35B-A3B-MLX-4bit seems to get in the loop often specially with tool calls. Qwen3.6-35B-A3B-mxfp4 seems to be optimal with speed and quality output. I am going to test Qwen3.6-35B-A3B-4bit soon with same code block just to check my intuition that any derivatives don't seem to perform better than the originals.view source ↗
-
Y Hacker News 4w ▲ 4 neutral codeShow HN: Skills MCPJust shipped: skills-mcp One MCP server. ~7,000 AI agent skills. Search → preview → install into Cursor, Claude Code, Claude Desktop, Cline, Windsurf. npx -y @gengirish/skills-mcp Open source, MIT. github.com/gengirish/skills-mcp #BuildWithAIGiri Just shipped: skills-mcp One MCP server. ~7,000 AI agent skills. Search → preview → install into Cursor, Claude Code, Claude Desktop, Cline, Windsurf. npx -y @gengirish/skills-mcp Open source, MIT. github.com/gengirish/skills-mcp #BuildWithAIGiriview source ↗
-
Y Hacker News 1mo positive model / openAnomalyco/OpenCode, Aider-AI/aider, and Cline ReviewTried Cline with a local Qwen2.5-Coder 14B model through llama.cpp. Same story. The model works perfectly when called directly, but the agent integration doesn't actually execute the tools. It generates things like: <tools> {"name": "read_files", ...} </tools> as plain text and then just sits there until I tell it to "… Tried Cline with a local Qwen2.5-Coder 14B model through llama.cpp. Same story. The model works perfectly when called directly, but the agent integration doesn't actually execute the tools. It generates things like: <tools> {"name": "read_files", ...} </tools> as plain text and then just sits there until I tell it to "do it" again. It repeats the exact same fake tool call. So instead of: Qwen → tool call → grep/find/read → result → Qwen I get: Qwen → pretend tool call → nothing happens → repeat.view source ↗
-
Y Hacker News 1mo ▲ 1 neutral opencode / qwenAnomalyco/OpenCode, Aider-AI/aider, and Cline Reviewview source ↗
-
Y Hacker News 1mo positiveLiterary Fiction Has Lost the PlotFor the record, I haven't read either of the two books discussed here ("Switzy" by Emma Cline and "Ply" by Hernan Diaz). And the one book of literary fiction i did read this month (Nelio Biedermann's much-hyped "Lazar") did not fall into these traps and is wonderful. You can find the first page of that one in Google Pr… For the record, I haven't read either of the two books discussed here ("Switzy" by Emma Cline and "Ply" by Hernan Diaz). And the one book of literary fiction i did read this month (Nelio Biedermann's much-hyped "Lazar") did not fall into these traps and is wonderful. You can find the first page of that one in Google Preview if you're curious.view source ↗
-
Y Hacker News 1mo ▲ 5 positive codeAsk HN: Are you still using AI code autocomplete?With all the recent progress in coding assistants, I've been wondering whether AI-powered autocomplete is still an important part of developers' workflows. I personally never got into the habit of using it very heavily. By the time I started having access to decent AI autocomplete tools, things like Cline and Augment w… With all the recent progress in coding assistants, I've been wondering whether AI-powered autocomplete is still an important part of developers' workflows. I personally never got into the habit of using it very heavily. By the time I started having access to decent AI autocomplete tools, things like Cline and Augment were already around, so I ended up relying more on assistants instead. That made me curious about how other people use it today. Do you still use Cursor Tab, Copilot, or something similar? If you also use coding assistants, do you find yourself using AI autocomplete less, or do the two complement each other?view source ↗
-
Y Hacker News 1mo positive codeT3rnel Browser – the most advanced cross browser web development tool ever builtT3raTech Solutions has launched the most advanced cross browser web development tool ever built. T3rnel Browser — a cross-platform web browser extension with 87 MCP tools for browser automation and web development. Lifetime free access does: • Full page screenshots & cropping (PNG & PDF export) • CSS Element Scanning &… T3raTech Solutions has launched the most advanced cross browser web development tool ever built. T3rnel Browser — a cross-platform web browser extension with 87 MCP tools for browser automation and web development. Lifetime free access does: • Full page screenshots & cropping (PNG & PDF export) • CSS Element Scanning & Export • Markdown (.md) file viewer • DOM compression for LLM context • LLM security firewall • Live shadow testing Model Control Protocol bridge for AI agent allows: • Total Browser Control (Fill forms, Click, Hover, Select, Type) • Upload & Download • Full tab control (Open, Close, Switch) • History Search • Visual Compare PayNow/PayPal Pro license integration grants: • Logged in page browsing (reuse existing sessions & credentials) • Playwright/Puppeteer code generator • Record & Replay automation • DOM time travel debugging • Encrypted identity vault for automatic website login Works standalone with Google #Chrome, #Brave, #Chromium and any #MCP compatible AI client (#Claude Desktop, #Windsurf, #Cursor, #Antigravity, #Codex, #Grok Build, #Cline, #KiloCode, #JCode). Optional #T3rnel daemon integration adds approvals, workflows, memory, and multi-agent orchestration. One-time license: $29.99. No subscriptions. Available at the Google Chrome Webstore: https://chromewebstore.google.com/detail/t3rnel-browser/egpc...view source ↗
-
Y Hacker News 1mo ▲ 2 neutral claude / codexPersonetta – One YAML Persona for Cursor, Copilot, Claude, and Clineview source ↗
-
Y Hacker News 1mo neutral coding / planAsk HN: How much money do you spend monthly on subscriptions for AI models?$30/mo for Synthetic (open weight models with ZDR and high throughput) + whatever coding plan the flavour of the month is (last month was $20 on NeuralWatt, this month $4.99 on ClinePass for DSFlashV4 mostly) $30/mo for Synthetic (open weight models with ZDR and high throughput) + whatever coding plan the flavour of the month is (last month was $20 on NeuralWatt, this month $4.99 on ClinePass for DSFlashV4 mostly)view source ↗