AICoder

AI Coding Live News

First-hand AI coding updates from 𝕏/Twitter frontier labs and researchers, distilled by AI with entity benchmarks.

Explore live on 𝕏 ↗

AI Coding Live News

G
Greg Isenberg@gregisenberg·
👀16
🔥81
View on 𝕏 ↗

X Discussion: Greg Isenberg Says He Talks to His Agents More Than His Human Teammates, Shares a Full Agent-Run Company Stack

On November 3, founder and Late Checkout CEO Greg Isenberg (@gregisenberg) posted a long thread on X saying his team has 50+ people in 12 countries, yet he "talks to my agents more than my human teammates." He listed an agent-driven stack covering ideation, design, build, user testing, bug fixing and data review. Within hours it drew about 1,050 likes, 2,300 bookmarks and 183 replies. This is a personal workflow and opinion, not verified productivity data.

Key Takeaways

  • Engagement: about 1,050 likes, 2,300 bookmarks, 183 replies and 75K views within hours (per the X API); bookmarks far exceed likes, so readers are saving it as a checklist
  • Coverage: ideation, design, build, user testing, bug fixing and data review are all handed to agents; humans handle "creative feedback, relationships and telling the agents what they got wrong"
  • Build: pingdotgg/t3code as the control surface and stablyai/orca to run parallel agents, each in its own git worktree
  • Quality control: every output is scored 1-10 by an LLM judge and anything under 8 goes back; every agent mistake becomes a new skill
  • All of this is self-reported; no verifiable productivity or cost figures were published
Read full story
Linked Models & Agents:
⚡ Claude Opus🤖 Claude Code🤖 Codex🤖 OpenCode🤖 t3code🤖 Orca🌐 Anthropic🌐 Linear🌐 Sentry🌐 Vercel🌐 Supabase
#X discussion#Greg Isenberg#agent workflow#Skills#MCP#git worktree#AI-run company
J
John Burn-Murdochjburnmurdoch·
👀29
🔥81
View on 𝕏 ↗

X discussion: FT chief data reporter John Burn-Murdoch says the US productivity jump "doesn't look like AI" and is mostly tech layoffs, while Gavin Baker argues it shows "ROI on AI"

On November 1, John Burn-Murdoch, a Financial Times columnist and chief data reporter, posted a long X thread with his FT piece arguing that the productivity rise in AI-adopting US sectors began in 2020, before AI agents existed, shows up only in the US, and comes mainly from tech layoffs and hiring pullbacks rather than AI. The thread opener has about 1,344 likes, 306 reposts and 186K views. Gavin Baker, managing partner and CIO of Atreides Management, quoted the FT charts and said it is hard not to see some evidence of "ROI on AI," citing a16z and EPB Research data; his post has about 793 likes and 102K views. Burn-Murdoch replied that he is "slightly on the fence" and that the data cannot rule out a role for AI. These are two readings of the same data, not a settled finding.

X discussion: FT chief data reporter John Burn-Murdoch says the US productivity jump "doesn't look like AI" and is mostly tech layoffs, while Gavin Baker argues it shows "ROI on AI"

Key Takeaways

  • Opener: John Burn-Murdoch's thread, posted 2026-11-01 15:04 UTC, with about 1,344 likes, 306 reposts and 186K views; his X bio says he is an FT columnist and chief data reporter
  • His core argument: the productivity rise in AI-adopting US sectors started in 2020, and even a 2022 re-acceleration is "too early to be AI. Back then it was chatbots, not agents"; other rich countries use AI just as widely but show no similar jump
  • Splitting productivity into output and headcount, he argues the US acceleration since 2022 is mainly a tech layoffs story: output stayed on trend while employment fell
  • Counterpoint: Gavin Baker's reply, with about 793 likes and 102K views; citing EPB Research, he says the 3 industries that adopted AI most went from 2.2% to 5% productivity growth, and that the US is 72% of Anthropic revenue (figures he cites from third parties; AICoder has not verified them)
  • Replying to Baker, Burn-Murdoch said he is "slightly on the fence": the "this looks like AI" case is overstated, but the data cannot rule out a role for AI either
Read full story
Linked Models & Agents:
#AI productivity#Financial Times#labor market#tech layoffs
H
Hugging Face Daily Papers@HuggingFace·
👀99
🔥96

Tencent Hunyuan Releases LifeSearch: The First Real-World Life & Productivity Benchmark for Deep Research Agents, 4,500 Hours of Human Annotation Shows Frontier SOTA at Just 63.4%

While deep research (DR) agents excel on synthetic and academic queries, their reliability in realistic personal life and professional workflows remains uncharted. Tencent Hunyuan introduces LifeSearch, a rigorous benchmark featuring 203 real-user tasks across 7 domains backed by 4,500+ hours of expert annotation and 4,000+ fine-grained rubrics. Evaluating 12 leading DR agents reveals that the strongest frontier agent scores only 63.4%, unmasking persistent bottlenecks in multi-step information synthesis and constraint verification.

Tencent Hunyuan Releases LifeSearch: The First Real-World Life & Productivity Benchmark for Deep Research Agents, 4,500 Hours of Human Annotation Shows Frontier SOTA at Just 63.4%

Key Takeaways

  • Pioneering real-world life & productivity testbed: spans 203 bilingual tasks across 7 realistic domains including travel itinerary synthesis, procurement, and healthcare analysis
  • 4,500 hours and 4,000+ expert rubrics: evaluates both synthesized report depth and concrete attributes (exact values, units, dates, and live URLs) with Spearman rank correlation of 0.89
  • Revealing severe frontier agent limits: the highest-performing deep research agent scores a modest 63.4%, exposing widespread failures in temporal conflict resolution and deep search navigation
Read full story
Linked Models & Agents:
⚡ GPT-5.6 Sol⚡ Hunyuan-Large (Open MoE)⚡ Deep Research Agent⚡ Perplexity Deep Research🤖 Deep Research Agents🤖 Autonomous Web Agents🌐 Tencent🌐 Tencent Hunyuan
#LifeSearch#Deep Research#Agent Benchmark#Tencent Hunyuan#Web Agents#Productivity
T
Tibo Sottiaux@thsottiaux·
👀75
🔥92
View on 𝕏 ↗

OpenAI: Astra productivity surge pulls some plans forward to DevDay

OpenAI engineer Tibo Sottiaux says GPT-6 Astra was a major competitive advantage while it was not generally available; after a large internal productivity jump, some plans previously aimed for mid next year were pulled forward about six months to ship at DevDay.

Key Takeaways

  • Astra was a major OpenAI edge before general availability.
  • Internal productivity gains pulled roadmap items forward ~6 months.
  • Those plans are now targeted for DevDay instead of mid next year.
Read full story
Linked Models & Agents:
⚡ GPT-6 Astra🌐 OpenAI
#GPT-6 Astra#OpenAI#DevDay#Productivity#Roadmap#Release
ADSponsored
C
Claude@claudeai·
👀50
🔥90
View on 𝕏 ↗

Claude Can Now Use Your Computer in the Background

Anthropic enabled Claude to use a user's computer in the background inside Claude Cowork and Claude Code—clicking, typing, and opening apps while the user works on something else. The beta is available to Pro and Max plans in the macOS desktop app. It moves Claude from a chat assistant to a parallel desktop coding and productivity agent.

Key Takeaways

  • Clicks, types, and opens apps in the background while you work
  • Available in both Claude Cowork and Claude Code
  • Beta for Pro and Max plans on the macOS desktop app
Read full story
Linked Models & Agents:
⚡ Claude🤖 Claude Cowork🤖 Claude Code🌐 Anthropic
#AI#LLM#Coding#Agents#Computer Use
A
Anthropic@AnthropicAI·
👀55
🔥93
View on 𝕏 ↗

Anthropic Opens Claude and Claude Code Usage Data; METR Measuring Coding-Agent Productivity

Anthropic gave external researchers privacy-preserving access to real Claude usage for the first time. Stanford SALT, Oxford HIP Lab, and METR independently analyzed about 250,000 Claude.ai or Claude Code conversations from April–May 2026, with METR estimating real-world productivity gains from coding agents.

Key Takeaways

  • Three external labs analyzed ~250,000 Claude.ai / Claude Code chats; SALT found over half involved consequential work that affects others or is hard to undo
  • METR is estimating coding-agent productivity from Claude Code traces; early results show newer models save more time, and Claude's time estimates correlate with real developer times
  • Aggregate data is public on Hugging Face (Anthropic/enabling-independent-research), with an open call for the next research cohort
Read full story
Linked Models & Agents:
⚡ Claude Opus 4.8⚡ Claude Sonnet 4.6⚡ Claude 3.7 Sonnet (Hybrid Reasoning)🤖 Claude Code (Anthropic)🌐 Anthropic
#Anthropic#Claude Code#METR#SALT Lab#Independent Research#Productivity
You've caught up with all stories