I think tuning is doing something lol
Search
29 results for “tunix”
-
-
Thanks for tuning in! Drop by #SatMat for Hammer Horror Dracula fun (info➡️ https://mastodon.social/@analgesicsleep/117469855410878734) AND I’m hosting both #SymSat (info➡️ https://mastodon.social/@analgesicsleep/117469857600594584) and #BaroqueSun (info➡️ https://mastodon.social/@analgesicsleep/117485945166041193) + next week we pregame #HappyHalloween with found horror on #LaEsoterica, Halloween tv shows on #MusComEnt & a goth dance party on #RetroView.. Enjoy the rest of your week💕
-
Stop debating RAG vs Fine-Tuning. Enterprise AI requires both.
Our hands-on MLOps implementation guide covers:
🧩 Semantic Chunking: Local BGE-M3 embeddings with zero egress
⚙️ 4-Bit QLoRA: BitsAndBytes + PEFT to prevent GPU OOM crashes
🛡️ Security Defense: Sanitizing indirect prompt injection (OWASP LLM01)
🚀 Bare Metal Speed: Zero cloud API taxes & unmetered NVMe -
Oh ho! Tuning into an #AI workshop for work and seeing some interesting questions from the audience. Like, "What is the environmental impact of this?" or "How much is this going to cost us a year?" Yup. I'm not the only AI skeptic in this workshop. Keep asking questions, people!
-
WRITING TIPS: Your Turn—Lifelines—Writing as Deep Listening: Tuning the Writer’s Ear
Hearing what the page is telling you. #writingtips
revisionsrevelations.substack.com/p/your-turnl...
Your Turn—Lifelines—Writing as... -
“#VibeCoding is the new product management.
Training & tuning models is the new #coding." -
JetBrains Junie Review 2026: The IDE Agent That Respects Your Refactor You have spent four years tuning your JetBrains IDE keymap, and the last thing#ai #webdev #programming #devops #software #coding #development #engineering #inclusive #community
JetBrains Junie Review: An IDE Agent That Respects Refactors -
AWS Enterprise Ukulele provides fully managed string orchestration across up to four production environments, with additional tuning configurations available at standard data transfer rates. Like all AWS managed services, the actual tuning is your responsibility. Pricing is calculated per string per availability zone, and your first chord is free until it isn't.
#aws #AmazonWebServices #CloudComputing #cloud #parody #humor
-
Getting ready for creating a larger contact print of this image tonight... Just some more fine tuning of the talus fields needed...
#Photography #BlackAndWhite #NoirCountry #Darkroom #PrintMaking
-
The Audacity: Audio tool finds new and exciting ways to annoy contributors with a Contributor License Agreement
> Is that a tuning Fork we hear?
-
Our AAAI 2026 poster on private in-context learning: LLMs can use sensitive records as in-context examples, with formal differential privacy guarantees and no fine-tuning.
Poster: https://doi.org/10.48448/8as1-z797
Paper: https://arxiv.org/abs/2509.13625
Code: https://github.com/bhusalb/privacy-preserving-icl -
Faint pulses on wires lurk underneath the most lofty conversations. #Linux #OpenSource https://cromwell-intl.com/open-source/performance-tuning/ethernet.html?s=mc
-
👂 Voxtral Small Transcribe 3 covers 50+ languages, including all 24 official EU languages, with diarization (who said what) and context biasing for domain vocabulary without fine-tuning. On FLEURS it reaches 4.1% WER, ahead of Gemini 3.5 Transcribe, Scribe v2, GPT Transcribe and Whisper large-v3. The 4B Mini variant costs $0.0035/min.
-
1/ Can an LLM use sensitive records as in-context examples without leaking them? Our AAAI 2026 paper: yes, with formal differential privacy guarantees and no fine-tuning.
Paper: https://arxiv.org/abs/2509.13625
Code: https://github.com/bhusalb/privacy-preserving-icl -
Enable Azure's built-in PgBouncer on Postgres Flexible Server via CLI, then tune pool size and transaction mode. Step-by-step: #azure #postgresql #database https://www.valtersit.com/vault/enabling-integrated-pgbouncer-and-tuning-pool-size-on-azure--6c856e/
-
Today's sense of impending doom brought to me by unboxing a shiny new desktop computer and now having to migrate years of fine-tuning over to it.
#Apple #MacMini #NewShiny #WorldAltTextChampionshipEntry #hashtag
-
https://www.europesays.com/de/1359159/ GT World Challenge Europe brachte Pech für Car Collection Motorsport #24StundenLeMans #24h #AktuelleNachrichten #AktuelleNews #Auto #dakar #DTM #EMobility #EU #Europa #EuropäischeUnion #Europe #EuropeanUnion #f1 #FiaWec #Formel1 #FormelE #Games #GtMasters #Headlines #MotorsportMagazin #Nachrichten #News #Nürburgring #Rallye #Schlagzeilen #SpeedMagazin #speedmagazin #Tuning #wrc
-
🔔 Position Open! | JavaScript / TypeScript Full-Stack Developer (Javascript)
Remote contract with Turing, pay discussed during screening
✅ Building and maintaining code that trains AI models
✅ Running evals to benchmark model performance
✅ Supervised fine-tuning with task-specific datasets👉 Apply here: https://nearskill.in/jobs/javascript-typescript-full-stack-developer-20414?utm_source=mastodon&utm_medium=social
-
🚀 Fastest-growing AI projects today
1. Projects like Mapika/decider leading the pack with innovative approaches to decision-ma...
2. Mapika's decider has garnered significant attention thweek, amassing 1,124 stars.
3. The project aims to provide one-pass typed decisions with calibrated probabilities usin...Full report → https://pullrepo.com/report/todays-fine-tuning-training-fastest-growing-projects-october-12-2026
-
🚀 Fastest-growing AI projects today
1. The trend underscores the growing importance of customizing pre-trained models to speci...
2. Mapika/decider stands out with a significant growth score of 37.08, accumulating over 1...
3. Thproject fine-tunes System One style models from Qwen3.5-2B to make one-pass typed dec...Full report → https://pullrepo.com/report/todays-fine-tuning-training-fastest-growing-projects-october-11-2026
-
What can a traditional music ensemble teach modern startup founders about leadership?
In a traditional Malaysian gamelan, there is no single conductor standing at the front. Instead, musicians rely on interlocking rhythms, non-standard tuning, and constant role rotation.
-
Csak nem hagyott nyugodt. Hat dollárt megért a próba.
Jelenleg ráengedtem egy fejlesztés alatt álló, de messze nem éles, messze nem RC, hanem inkább késő béta projektemre.
Hát... szedi rendesen a hibákat, pedig a flash-t, használom.Nyilván külön branch és nincs merge, hanem tolok rá egy Claude+Codex felülvizsgálatot is, hogy mit szólnak ehhez, mennyire volt jogos, vagy jó az észrevétel a biztonsági és logikai audit során.
De, ahogy nézem közben én is azért itt-ott kézzel és szemmel, korrektnek tűnik elsőre.
Oké, oké, szenzitív rendszer esetén kívánában landol majd a kód, meg mit tudom én. Igen.
De annak a szenzitív rendszernek a kódja a többi ügynök esetén pedig az USA-ban landol, ha akar, szóval, valahogy elengedtem ezt a paranoia témát ilyen téren. -
The AI Stack
1/ The AI Stack, Part 1: Building Product-First
Application Development Layer (Product-First). This is the layer where most of the user experience is built
https://newsletter.optimistengineer.com/p/the-a-side-the-ai-stack-part-1-building
2/ The AI Stack, Part 2: The Art of Specialization
Never fine-tune just to teach your model static facts (that’s what RAG is for). Use fine-tuning exclusively for behavior, tone, and formatting!
https://newsletter.optimistengineer.com/p/the-ai-stack-part-2-the-art-of-specialization
3/ The AI Stack, Part 3: The Engine Room
In modern AI engineering, this layer is strictly dictated by one huge bottleneck: GPU/TPU scarcity and compute costs.
https://newsletter.optimistengineer.com/p/the-ai-stack-part-3-the-engine-room
-
🚀 Fastest-growing AI projects today
1. One of the most notable trends the growing interest in LoRA (Low-Rank Adaptation) fine-...
2. Mapika/decider has seen substantial growth thweek, boasting a Growth Score of 38.31 and...
3. The project aims to provide one-pass typed decisions with calibrated probabilities, fin...Full report → https://pullrepo.com/report/todays-fine-tuning-training-fastest-growing-projects-october-10-2026
-
Anglo-Finnish quantum spinout QuantrolOx, founded at Oxford and now based in Finland, has raised 12M EUR (about 14M USD) in a Series A led by IW Capital, with the EIC Fund and Transpose Capital joining. Its software automates the tuning and control of quantum computers across hardware architectures, a bottleneck holding the field back. https://tech.eu/2026/10/22/anglo-finnish-oxford-university-quantum-spinout-raises-eur12m/ #Tech #Startup #News #Quantum
-
#WordWeavers 10/21: Your MC wakes up with the ability to read minds for 24 hours. Whose thoughts do they most want to hear? Whose thoughts do they least want to hear?
The ones she most and least wants to hear belong to the very same man: Elric. Zerika would want to hear his thoughts, and then would immediately cringe at the thought of "tuning in" to hear. What if he secretly finds her unattractive, boring as far as company goes, or think she's completely idiotic for not being good at talking to strangers? How would he feel about her not knowing how to read? (Spoiler alert, he doesn't care. In fact, he offers to teach her. He actually adores her.) All of these questions and thoughts would immediately flood her. I can feel her anxiety through the screen, poor thing.
Also... Not even kidding about this, but it gives me some ideas for an upcoming tale in the series, so thank you for that!
#WritingCommunity #WritersOfMastodon #TheScarletMirror #FatedByFire #CozyFantasy #Fantasy #SwordAndSorcery #Romance
-
----------------
🛠️ Tool: PacketSmith v5 Integrates Yara-X into Network Traffic Analysis
===================PacketSmith from Netomize shipped version 5, codenamed Pinus strobus, and the headline feature is an integrated Yara-X engine. The vendor describes the release as the result of extended R&D for network detection engineers, SOC analysts, and malware and vulnerability researchers, adding "unique, unparalleled" capabilities. Marketing aside, the integration itself looks substantive: Yara-X is not only pointed at payloads, it is wired into a structure of protocol attributes that the compiler can reference.
Key features
• Scoping across data categories: raw frames, individual TCP/UDP packets, reassembled TCP/UDP streams, and ICMP (v4/v6) payloads.
• Deep protocol attributes provided as custom Pattern Identifiers (PaIDs), nested identifiers that let rules target network metadata instead of raw bytes only.
• Cross-layer correlation: a single YARA condition can reference link-layer, network-layer, and transport-layer dissected data simultaneously.
• Results as high-detail console output, JSON, or XML Workbook, with the option of logging matched content.Technical implementation
The dns case study is the most concrete part of the announcement. It targets the Denis backdoor, publicly documented by Kaspersky on Securelist under "Use of DNS tunneling for C&C communications".
Sample indicators:
MD5: 1a4d58e281103fea2a4ccbfab93f74d2
SHA-1: 1a2cd9b94a70440a962d9ad78e5e46d7d22070d0
SHA-256: f5872f49943c39b73026fc3982b85330953a138cc27c23487a28103337bfdbb5
Win32 EXE, Microsoft Visual C++, 179,202 bytesDetected behavior: the malware sends check-in DNS requests to Google's public resolver 8.8.8.8 on port 53, base64-encoded with the custom alphabet [A-Za-z0-9_-], and the initial check-in consists of one tunneling label at a fixed 32-byte length. The vendor ships a reference capture (denis_bkdr_dns, 2,292 bytes) together with a sample rule combining ip4 and dns PaIDs. The rule condition shown:
dns.is_set and not dns.over_tcp and not dns.flag.response
and dns.flag.opcode == 0
// optional check:
ip4.is_set and ip.dst.addr == "8.8.8.8"Use cases
1. Detection engineering against known malware captures, where rules are validated directly on pcaps.
2. Tunneling signatures built on protocol structure, which holds when payload content is encrypted, since the pattern lives in field shape, resolver choice, and flag combinations.
3. Offline pcap triage. The vendor's own analogy: PacketSmith plus Yara-X is to a pcap what an IDS/IPS is to live traffic.Limitations and open questions
• The claim that no other tool on the market has this capability is vendor-provided and unverified.
• The post demonstrates only the ip4 and dns PaIDs. The announced protocol list at other layers is larger, but per-protocol identifiers require the official documentation.
• The sample rule is tailored to this sample's fixed 32-byte label, so expect tuning for other tunneling families and false-positive pressure from legitimate long DNS labels.
• The release material is framed around pcap analysis; nothing in the post describes high-volume live traffic handling.References
• PacketSmith official documentation, with technical specifications and advanced use cases for identifying malware C&C traffic and network exploitation attempts.
• Kaspersky Securelist: Use of DNS tunneling for C&C communications.🔹 tool #PacketSmith #YaraX #NetworkDetection #DNSTunneling
🔗 Source: https://packetsmith.ca/yara-x-packetsmith-detection-module/
-
The Local Office Document Gap in AI Workflows
When prototyping with Claude Code or Cursor's agent mode, I hit a recurring friction point: generating structured documents. LLMs excel at producing markdown or JSON, but translating that into actual.docxreports or.xlsxdata exports meant context-switching to manual Python scripts withpython-docxor copying output into Google Docs.The genspark-ai/genoffice project solves this by exposing a unified CLI that creates and edits native Office files locally—no API keys for document generation services, no cloud dependencies. It bundles Docs, Sheets, Slides, PDF, Markdown, and HTML editors with a built-in AI agent, plus an MCP skill spec designed for Cursor and Claude Code integration.
Architecture: CLI + MCP Skill Registration
genoffice operates as a standalone binary with two execution modes:- Interactive GUI: Launch
genofficeto open the Electron-based editor suite. - Headless CLI: Use
genoffice create-doc --template report.docx --output quarterly.docxfor scripted workflows.
The critical piece for Cursor integration is the MCP (Model Context Protocol) skill manifest. When registered, Cursor's agent can invoke genoffice commands directly through natural language prompts:
{
"mcpServers": {
"genoffice": {
"command": "genoffice",
"args": ["mcp"],
"env": {
"OPENAI_API_KEY": "your-key-or-relay"
}
}
}
}Drop this into
.cursor/mcp_settings.json(create if missing). Restart Cursor, and the agent gainscreate_document,edit_spreadsheet,generate_slidescapabilities.Hardening the Relay Gateway for Multi-Model Fallback
genoffice's AI agent defaults to OpenAI endpoints, but production workflows demand cost optimization and failover. I route requests throughhttps://b-lost.com/v1as a relay gateway to abstract provider switching:export OPENAI_BASE_URL="https://b-lost.com/v1"
export OPENAI_API_KEY="your-relay-token"
genoffice mcpThis setup allows seamless model rotation (GPT-4 → Claude → Gemini) without reconfiguring genoffice. When testing document generation with varying context sizes, routing through the relay reduced average token costs by 22% compared to direct OpenAI calls, primarily by auto-selecting cheaper models for formatting-heavy tasks.
Practical Integration: Automated Sprint Report Pipeline
Here's a real workflow: generating weekly sprint reports from Jira exports.Step 1: Export Jira data to JSON
curl -u user:token "https://jira.company.com/rest/api/2/search?jql=sprint=42" > sprint.json
Step 2: Cursor agent prompt
@genoffice create a Word document from sprint.json with sections:
- Completed stories (table)
- Blockers (bullet list)
- Velocity chart (placeholder image)
Output: sprint_42_report.docxCursor's agent parses the JSON, invokes
genoffice create-doc, and generates a formatted.docxin 8 seconds. The velocity chart placeholder requires manual insertion (genoffice doesn't render charts yet), but tables and text formatting are production-ready.Step 3: Programmatic edits via CLI
genoffice edit-doc sprint_42_report.docx \
--append "## Action Items" \
--insert-table "blockers.csv" \
--style "Heading 2"This avoids reopening the GUI for minor tweaks.
Operational Boundaries and Failure Modes
Performance: Document creation scales linearly with content size. A 50-page.docxwith 20 tables takes ~15 seconds on M2 MacBook Air. This is acceptable for CI pipelines but too slow for real-time preview workflows.Format Fidelity: Complex PowerPoint animations and Excel macros aren't preserved. genoffice reads/writes Office Open XML (
.docx,.xlsx,.pptx) but strips VBA and embedded media beyond images.Concurrency: The MCP server spawns one genoffice process per request. Running 5 parallel document generations maxed CPU at 340%, with no queue throttling. For batch jobs, wrap calls in
xargs -P 2to avoid resource exhaustion.Error Propagation: When the AI agent fails to generate valid Office XML (rare, but happens with malformed JSON input), genoffice returns exit code 1 with no intermediate output. You lose the partial document. Always validate input schemas before invoking CLI commands.
Configuration Tuning for Cursor Agent Context
The default MCP skill allows 8KB of context per prompt. For document generation from large datasets (e.g., 500-row CSV), this truncates input. Override in.cursor/mcp_settings.json:{
"genoffice": {
"maxContextTokens": 32768,
"env": {
"OPENAI_BASE_URL": "https://b-lost.com/v1",
"GENOFFICE_TEMP_DIR": "/tmp/genoffice-cache"
}
}
}The
GENOFFICE_TEMP_DIRflag prevents cluttering/tmpwith orphaned XML fragments during failed runs.Open Trade-Off: Native Execution vs. Containerized Isolation
Running genoffice as a native binary on macOS/Windows/Linux simplifies installation (single Homebrew formula or.exe), but mixing Node.js dependencies with system-wide Electron bundles risks version conflicts. I've seen collision with VS Code's internal Chromium runtime on Arch Linux, causing segfaults.The alternative—wrapping genoffice in Docker—adds 200MB image overhead and breaks MCP socket communication unless you expose Unix domain sockets. There's no universal clean solution yet. If you're standardizing CI environments, containers win. For local dev, accept the native binary's brittleness and pin versions in
package.jsonorbrew pin.For teams already managing polyglot dev environments through Cursor's MCP ecosystem, does the convenience of local Office file generation outweigh the dependency surface area risk?#cursor #vscode #devtools #productivity #software #coding #development #engineering #inclusive #community
Wiring genoffice CLI into Cursor MCP: Real Office Document Generation from AI Context - Interactive GUI: Launch