Skip to content

Topic

AI Coding Assistants

Software tools that use AI models to help write, review, or complete code, integrated into IDEs, command-line interfaces, and cloud-based agents.

Current stories

buildOne report1 publisher

Copilot's model picker loses Opus 4.8, Opus 5 and GPT-5.6 Terra on Nov 16

GitHub will remove Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra from Copilot on November 16, according to its October 15 changelog. The vendors keep all three on their own APIs, so teams can call those directly or switch.

Publishers:dev.to

Reality

Evidence62
Adoption
Not scored
Hype gap0
Incentives30
Confidence60
buildOne report1 publisher

Claude Code compacts idle sessions of 200k tokens or more before the prompt cache expires

Anthropic switched on idle compaction in Claude Code around v2.1.286, replacing long idle conversations with a summary, a dev.to analysis reports. Version 2.1.290 adds idleCompaction: false, a choice that falls on anyone keeping large sessions open past an hour.

Publishers:dev.to

Reality

Evidence58
Adoption
Not scored
Hype gap−5
Incentives
Not scored
Confidence60
investConfirmed7 publishers

Epic tells its Disney shooter team to stop writing code by hand, Bloomberg reports

Epic Games told developers on its delayed Disney shooter to build with AI first, Bloomberg reported, a game tied to Disney's $1.5 billion stake in Epic. Epic has not set a new release date.

Perspective Coverage

15 publishers
Builder
Builder 34%
Operator
Operator 35%
Investor
Investor 31%

Reality

Evidence55
Adoption30
Hype gap+25
Incentives55
Confidence62
buildConfirmed3 publishers

Torvalds' Claude Code branch lets Linux page-cache reads skip the folio reference count

Linus Torvalds built an experimental Linux page-cache branch with Claude Code that cuts one contended read test to about a quarter of its CPU cost. His own cover letter flags open problems, so the series is a request for review.

Publishers:dev.to lwn.net phoronix.com

Perspective Coverage

3 publishers
Builder
Builder 63%
Operator
Operator 28%
Investor
Investor 9%

Reality

Evidence50
Adoption3
Hype gap+30
Incentives35
Confidence62
productOne report1 publisher

Seven of eight Surface Laptop Ultra configurations lack the memory in Microsoft's local coding test

Microsoft's on-device coding model peaked at 75.5GB of memory at full context in the company's own test, according to a Command Line post. Only the 128GB model, at $5,899 and not yet on sale, has more, TweakTown reported.

Publishers:techradar.com

Reality

Evidence45
Adoption
Not scored
Hype gap+55
Incentives60
Confidence50
buildOne report1 publisher

GitHub's HydraFusion preview plans each Copilot prompt as a workflow of model calls

GitHub says its HydraFusion preview costs an estimated 67% less than Claude Opus 5 on TerminalBench 2.1 by planning model calls per prompt. Whether that saving reaches your bill depends on how often a cheap draft clears the quality gate.

Publishers:dev.to

Reality

Evidence35
Adoption
Not scored
Hype gap+20
Incentives55
Confidence55
investOne report1 publisher

Aptos rolls out AI tooling that lets coding assistants learn Move from its documentation, with an MCP server installed via one npx command

Aptos shipped an MCP server, LLMs.txt feeds and agent skills so AI coding assistants can read Move documentation directly, cryptobriefing.com reported. The only quality control it describes is a set of skills for audits and tests.

Reality

Evidence35
Adoption
Not scored
Hype gap+20
Incentives
Not scored
Confidence40
buildOne report1 publisher

In Claude Code 2.1.285, an admin-only setting decides which providers each machine may call

Anthropic's Claude Code 2.1.285 lets administrators restrict which of eight API providers a machine may use. A company that standardized on one cloud for data residency or committed spend can now hold developers to that choice inside the client.

Publishers:dev.to

Reality

Evidence45
Adoption
Not scored
Hype gap+5
Incentives
Not scored
Confidence50
buildOne report1 publisher

Two of Claude Code's five October changes are worth switching on this week

Claude Code shipped five developer-facing changes from 1 to 6 October 2026, among them Claude Mods and an effort parameter on the Agent tool. The effort setting can go on at once, and the young You should know side agent deserves a one-repository trial first.

Publishers:dev.to

Reality

Evidence55
Adoption
Not scored
Hype gap+10
Incentives
Not scored
Confidence50
investConfirmed6 publishers

Meta halves internal use of Anthropic's Claude Code to about 30,000 staff

Meta's internal Claude Code users fell from about 60,000 to 30,000 this year, and Microsoft cut a projected $1 billion-plus Anthropic budget by over a third. With two unnamed customers supplying a quarter of Anthropic's revenue, investors need to know whether those cuts reach them.

Publishers:benzinga.com cryptobriefing.com digitimes.com finance.yahoo.com stocktwits.com techradar.com techstartups.com the-decoder.com

Perspective Coverage

8 publishers
Builder
Builder 16%
Operator
Operator 33%
Investor
Investor 51%

Reality

Evidence58
Adoption55
Hype gap+25
Incentives62
Confidence55
productOne report1 publisher

New PS5 jailbreak works on firmware Sony released in July

Hackers released a PS5 exploit last week that works through firmware 13.60, a July release, Gizmodo reported. The outlet wonders whether AI coding assistants are shrinking the gap between Sony's patches and working jailbreaks, though it says it cannot know without the hackers.

Publishers:gizmodo.com

Reality

Evidence35
Adoption
Not scored
Hype gap+40
Incentives
Not scored
Confidence40
leadershipOne report1 publisher

Nuxt CLI 4.0 reserves its agent-ready error overlay for apps on Nuxt 4.6

Nuxt CLI 4.0 arrives with more than 200 commits of dev-server work, including an error overlay that can copy a failure as a prompt for an AI agent. That overlay runs only on Nuxt 4.6, so teams get the full benefit by planning the framework and CLI upgrades as one project.

Publishers:github.com

Reality

Evidence55
Adoption
Not scored
Hype gap+10
Incentives40
Confidence60
buildOne report1 publisher

Stack Overflow's 2026 survey puts 18% of developers in an office every day

Stack Overflow's 16th developer survey, answered by more than 30,000 people, finds only 18% go into an office every day. For engineering leads, the results bear on attendance rules and on how close to production AI tooling should be allowed to work.

Reality

Evidence45
Adoption70
Hype gap+15
Incentives45
Confidence50
buildOne report1 publisher

Syft and Trivy list under half of JavaScript lockfile packages in a 3,326-repository study

Syft and Trivy reported 43.78% and 32.71% of lockfile packages across 2,050 JavaScript repositories in an Inria and ANSSI study, against 98.72% for cdxgen. The tool, its version and its flags decide what an SBOM lists, so that recipe belongs under version control.

Publishers:dev.to

Reality

Evidence55
Adoption
Not scored
Hype gap+10
Incentives
Not scored
Confidence50
buildOne report1 publisher

Applied Intuition splits its engineering interview between a no-AI screen and a two-hour AI build

Applied Intuition screens engineers with a 45-minute no-AI coding task, then gives onsite candidates two hours to build a design with any AI model. Other teams can copy the split now, though its only published evidence is interviewer confidence from the company's own trial.

Publishers:dev.to

Reality

Evidence35
Adoption25
Hype gap+15
Incentives60
Confidence50
buildOne report1 publisher

Developers' approval of AI tools fell 12 points in the year their use reached 79%

Stack Overflow's 2025 Developer Survey found 79% of developers using AI tools as positive sentiment fell from 72.0% to 59.7% and negative views tripled. Several comparisons span reworded questions or a smaller pulse sample, so the direction holds better than the size of each move.

Reality

Evidence55
Adoption72
Hype gap+12
Incentives35
Confidence58

Earlier coverage

  1. Microsoft moves Copilot's hand-off features onto usage billing in a rebuilt desktop app

    Product · September 27, 2026 · Confirmed9 publishers

  2. Cursor's case for being bought is unit economics, and the post-close note promises nothing else

    Product · August 14, 2026 · Confirmed4 publishers

  3. Cursor is SpaceX property now, which makes your editor a vendor bet

    Build · August 16, 2026 · Confirmed3 publishers

  4. An AI commit deleted a Snowflake workflow's injection guard. An agent walked in five days later.

    Build · August 17, 2026 · Confirmed2 publishers

  5. Faster AI-written code pays off only where writing was the bottleneck

    Leadership · September 25, 2026 · One report1 publisher

  6. ZCode encrypted a 313MB snapshot of a commercial repo to a key only its server holds

    Build · September 20, 2026 · Confirmed3 publishers

  7. Hundreds of failed uploads exposed ZCode's 313-megabyte bundle of a developer's repository

    Invest · September 21, 2026 · Confirmed3 publishers

  8. Copilot's hard stop on AI coding spend ships switched off

    Build · September 24, 2026 · One report1 publisher

  9. GitHub will meter every Copilot plan by token consumption from June 1

    Science · September 23, 2026 · Confirmed2 publishers

  10. Foundry offers Provisioned Throughput for two of the three GPT-6 models

    Build · September 22, 2026 · Confirmed2 publishers

  11. The credential an agent inherits sets the ceiling on the damage

    Build · September 18, 2026 · One report1 publisher