Coding Agents and Future Software Engineering

Oct 26, 2026

Machine Learning Street Talk Mathematics Just Changed Forever — Kevin Hartnett

• Machine Learning Street Talk AI code verification offers a potential application, conditional on specifying the right behavior. A compression program can satisfy a round-trip proof simply by returning its input unchanged; correctness of the proof does not establish …

Oct 24, 2026

20VC 20VC: Unconventional's Naveen Rao on robotics and $10TRN inference

• Naveen Rao AI’s immediate bottleneck is shifting from producing artifacts to judging whether they work. Rao describes reducing a research question from roughly two weeks to an hour, then warns: “I think we've moved the problem from producing to …

Oct 23, 2026

No Priors Democratizing Security for the Agentic Web with CloudFlare CTO Dane Knecht

• Dane Knecht AI-generated software still needs simpler architecture and human judgment. Early models “like to create complexity,” making smaller codebases, explicit engineering principles, and independent reviews essential. …

Oct 22, 2026

20VC 20VC: Trillion or Bust, CoreWeave’s Sell-Off and the $90B Anduril Test

• 20VC The panel’s strongest software call is that production readiness has become more important than generating another feature. Jason argues models get developers most of the way there, while testing and fixing can consume the next three days. He broadens “code …

Oct 21, 2026

Latent Space AI in NYC: How Tenex Builds an AI-Native Engineering Team — Alex Lieberman & CJ Hess

• Alex Lieberman The most tradeable data point is Alex Lieberman’s enterprise adoption funnel: of about 100 enterprises 10X talks to, 90% have rolled out a general-purpose LLM (Claude or Codex), about 60% provide training and enablement, and about 50% have deployed coding agents — versus the 70–80% many AI Engineer attendees guess. Agents in production for non-engineering work fall to about 5%. Alex describes this as the biggest gap between raw intelligence and …
• CJ Hess CJ Hess estimates engineer output has roughly doubled over the period from the “Opus 4.5 moment” in December to Opus 5.5 today, which he calls a “magnificent model.” Opus is fast, cheap, and covers the range for which he previously used two or three models. The team often pairs it with Codex for review; …

Oct 18, 2026

十字路口Crossing New startup opportunities are taking shape around Claude Code and Codex | A conversation with Treg

• 石天鑫 Both tool stacks and career choices are shifting with the models. Jason moved from heavy Claude Code use to Codex mainly because the Astra model is strong; he often runs 5 to 10 sessions at once and moved …

Oct 17, 2026

The Cognitive Revolution AI:AM: Where's the Steering Wheel? My Agent Set the Password, Hidden Valence, Proofs Find Linux Bugs

• Everett Hildenbrandt Runtime Verification found Linux kernel bugs through a methodical process using formal methods and a single Claude Code instance; CEO Everett Hildenbrandt predicts “writing code is a dead art in two years tops.” The team targeted device drivers, ported C to Rust with an LLM, used differential fuzzing, then verified the Rust; they found bugs at both …

Oct 16, 2026

Sourcery Vercel CEO Guillermo Rauch on Building the Internet for Agents

• Guillermo Rauch Engineering is becoming capital allocation across agents, but Rauch rejects both blind vibe coding and the claim that human judgment no longer matters. His rule is “reject non-understanding”: people should direct agents, inspect their work, verify critical systems, and choose what deserves …

The a16z Show Why AI Can Write Code But Can’t Keep It Running (Yet)

• The a16z Show AI coding has crossed from autocomplete into industrial-scale leverage, but the gains accrue disproportionately to engineers who already understand complex systems. Martin Casado describes shipping production code for a data-lake “auto-promotion” capability alone in 10 days versus roughly six months …
• Jad Naous The bottleneck has moved from writing syntax to specifying architecture and verifying behavior. Jad runs three or four Claude Code sessions, has agents review design and PR documents, parallelizes implementation, then personally …

Oct 15, 2026

硅谷坐标 Silicon Valley Vector Silicon Valley Coordinates x Datadog Chief Product Officer | HYSTA Chair 李严冰: AI Deployment Enters the ROI Era

• 李严冰 Coding agents may account for the largest share of Datadog’s internal AI investment, but the real KPI is engineering output, not token consumption. The company links usage to PR velocity, product stability, feature delivery, and security improvements; the more immediate risk comes from …

Oct 12, 2026

Sourcery Perplexity CEO: SMBs Could Drive the Next Economic Boom

• Aravind Srinivas Srinivas says writing code is nearly solved while problem selection remains scarce. Once constraints, specifications, security risks, and go-to-market logic are clear, writing code is “almost already a solved problem”; the …

Oct 8, 2026

硅谷101 E255 | Models Keep Getting Stronger—Why Don’t Users Feel It? A Return Visit with 张阔, President of Alibaba.com

• 张阔 张阔 estimates Coding Agent penetration at 99%, while commercial Agents remain at an early stage; the fundamental differences are digitization, verifiability, and feedback cycles. Whether code compiles and whether the output is correct can be checked immediately; business outcomes may take days, weeks, months, or even …

Oct 7, 2026

The Cognitive Revolution Software That Never Breaks: OutSystems CEO Woodson on Building Enterprise-Grade Apps at AI Speed

• Woodson Martin OutSystems’ AI thesis is that faster code generation only matters if enterprises can preserve the promise that software “never breaks.” Coding agents work against an abstract model of application intent, after which the platform deterministically generates software with …

Oct 2, 2026

Latent Space Recursive Language Models — Alex Zhang, MIT PhD

• Latent Space AI-generated GPU kernels are already competitive, but expert intuition remains the scarce input because benchmark wins do not guarantee system-level reliability. Recent GPU Mode leaderboards are dominated by AI-assisted submissions, yet longtime kernel developer Gorst produced nearly the only top-10 …

Sharp Tech Preview: All About Agents — Dots Arrive Before OpenAI Is Ready

• Sharp Tech Claude and Codex currently occupy complementary roles in Ben’s workflow. Claude is the context-preserving “chief of staff,” while Codex is better for executing a defined project—Andrew’s analogy is that “Claude is …

Sep 30, 2026

Machine Learning Street Talk AI Can Write the Proof. Who Checks It? — Leonardo de Moura

• Leonardo de Moura AI could make specification-driven development routine, but it cannot eliminate the hard work of deciding what software should do. Specifications emerge through user feedback, change after deployment, and can invalidate generated code and its proofs; AI’s value is in …

Sep 29, 2026

Latent Space The Future of Claude Code: Mods, Mutable Software, & Multiplayer Agents — Thariq Shihipar, Anthropic

• Thariq Shihipar Claude Code’s frontier is moving from a single coding CLI toward a distributed system of intelligence, interfaces, and execution. Anthropic’s emerging architecture separates a cloud-based “brain,” local or remote “hands,” and artifact-based surfaces that can coordinate …
• The highest-leverage coding skill remains precise communication, because smarter agents amplify both good intent and unresolved ambiguity. Thariq compares prompting to public speaking for a specific audience: users must understand what Claude can one-shot, identify unknowns …
• Frontier models may become Pareto-dominant even on simple work because intelligence reduces the tokens wasted on verification and retries. Thariq expects smarter models eventually to complete straightforward tasks once, rather than repeatedly inspecting screenshots or exploring …
• CLAUDE.md may be a transitional artifact rather than permanent infrastructure. Thariq now thinks a new project might be better started without one, adding instructions only after repeated failures, because model- and …
• Latent Space Claude Code mods turn the harness itself into mutable software, expanding customization from scripts into the agent loop and UI. Mods can inspect messages, turns, and token use; spawn forked agents that preserve the prompt cache; return structured classifications; …
• Claude Code’s enterprise value is less “chat in Slack” than becoming an organizational harness with shared context, permissions, and proactive workflows. Incidents, legal review, prospect research, alerts, and project channels are inherently multiplayer; Claude can answer reviewers directly …

Sep 24, 2026

20VC Meta's Muse tops charts; Menlo's AI bubble alarm; Factory at $5B

• 20VC The mock IC approves Factory at $5B, passes on Lagora at $11B and Crusoe at $30.9B. Factory rides Rory's core thesis — "Coding is the mother lode. It's everything" — plus data sovereignty, since enterprises "don't trust Anthropic and OpenAI with their data" ("Of course they're gonna …

Sep 21, 2026

20VC UiPath's Dines: AI Needs Workflows, Not Just Models

• Daniel Dines AI’s probabilistic nature makes it the design layer, while deterministic software remains the execution layer for consequential work. Dines illustrates that a 99%-reliable step repeated 100 times leaves only roughly a 60% chance of completing the whole sequence. He …
• Vibe coding has collapsed prototyping costs without eliminating the expensive path from prototype to production. UiPath built a procurement tool only with AI, then found missing connectors, permissions, audits, security requirements, insufficient tests, …

Latent Space From InstructGPT to Jev: What Comes After ChatGPT — Diogo Almeida, TypeSafe Co-founder & CEO

• Latent Space His coding-agent thesis is that the named incumbent agents are built around a single-model world, while open agents can experiment with multi-model designs. His follow-on research agenda is "coding agents free from the tyranny of the KV cache": labeled subtask trees, shared state across parallel …